Class CU


  • public class CU
    extends java.lang.Object
    Contains bindings to the CUDA Driver API.

    Functionality up to CUDA version 3.2, which is the minimum version compatible with the LWJGL bindings, is guaranteed to be available. Functions introduced after CUDA 3.2 may or may not be missing, depending on the CUDA version available at runtime.

    • Method Detail

      • getLibrary

        public static org.lwjgl.system.SharedLibrary getLibrary()
        Returns the NVCUDA SharedLibrary.
      • ncuGetErrorString

        public static int ncuGetErrorString​(int error,
                                            long pStr)
        Unsafe version of: GetErrorString
      • cuGetErrorString

        public static int cuGetErrorString​(int error,
                                           org.lwjgl.PointerBuffer pStr)
        Gets the string description of an error code.

        Sets *pStr to the address of a NULL-terminated string description of the error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

        Parameters:
        error - error code to convert to string
        pStr - address of the string pointer
      • ncuGetErrorName

        public static int ncuGetErrorName​(int error,
                                          long pStr)
        Unsafe version of: GetErrorName
      • cuGetErrorName

        public static int cuGetErrorName​(int error,
                                         org.lwjgl.PointerBuffer pStr)
        Gets the string representation of an error code enum name.

        Sets *pStr to the address of a NULL-terminated string representation of the name of the enum error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

        Parameters:
        error - error code to convert to string
        pStr - address of the string pointer
      • cuInit

        public static int cuInit​(int Flags)
        Initialize the CUDA driver API.

        Initializes the driver API and must be called before any other function from the driver API. Currently, the Flags parameter must be 0. If cuInit() has not been called, any function from the driver API will return CUDA_ERROR_NOT_INITIALIZED.

        Parameters:
        Flags - initialization flag for CUDA
      • ncuDriverGetVersion

        public static int ncuDriverGetVersion​(long driverVersion)
        Unsafe version of: DriverGetVersion
      • cuDriverGetVersion

        public static int cuDriverGetVersion​(java.nio.IntBuffer driverVersion)
        Returns the latest CUDA version supported by driver.

        Returns in *driverVersion the version of CUDA supported by the driver. The version is returned as (1000 × major + 10 × minor). For example, CUDA 9.2 would be represented by 9020.

        This function automatically returns CUDA_ERROR_INVALID_VALUE if driverVersion is NULL.

        Parameters:
        driverVersion - returns the CUDA driver version
      • ncuDeviceGet

        public static int ncuDeviceGet​(long device,
                                       int ordinal)
        Unsafe version of: DeviceGet
      • cuDeviceGet

        public static int cuDeviceGet​(java.nio.IntBuffer device,
                                      int ordinal)
        Returns a handle to a compute device.

        Returns in *device a device handle given an ordinal in the range [0, cuDeviceGetCount()-1].

        Parameters:
        device - returned device handle
        ordinal - device number to get handle for
      • ncuDeviceGetCount

        public static int ncuDeviceGetCount​(long count)
        Unsafe version of: DeviceGetCount
      • cuDeviceGetCount

        public static int cuDeviceGetCount​(java.nio.IntBuffer count)
        Returns the number of compute-capable devices.

        Returns in *count the number of devices with compute capability greater than or equal to 2.0 that are available for execution. If there is no such device, cuDeviceGetCount() returns 0.

        Parameters:
        count - returned number of compute-capable devices
      • ncuDeviceGetName

        public static int ncuDeviceGetName​(long name,
                                           int len,
                                           int dev)
        Unsafe version of: DeviceGetName
        Parameters:
        len - maximum length of string to store in name
      • cuDeviceGetName

        public static int cuDeviceGetName​(java.nio.ByteBuffer name,
                                          int dev)
        Returns an identifer string for the device.

        Returns an ASCII string identifying the device dev in the NULL-terminated string pointed to by name. len specifies the maximum length of the string that may be returned.

        Parameters:
        name - returned identifier string for the device
        dev - device to get identifier string for
      • ncuDeviceGetUuid

        public static int ncuDeviceGetUuid​(long uuid,
                                           int dev)
        Unsafe version of: DeviceGetUuid
      • cuDeviceGetUuid

        public static int cuDeviceGetUuid​(CUuuid uuid,
                                          int dev)
        Return an UUID for the device.

        Note there is a later version of this API, DeviceGetUuid_v2. It will supplant this version in 12.0, which is retained for minor version. compatibility.

        Returns 16-octets identifing the device dev in the structure pointed by the uuid.

        Parameters:
        uuid - returned UUID
        dev - device to get identifier string for
      • ncuDeviceGetUuid_v2

        public static int ncuDeviceGetUuid_v2​(long uuid,
                                              int dev)
        Unsafe version of: DeviceGetUuid_v2
      • cuDeviceGetUuid_v2

        public static int cuDeviceGetUuid_v2​(CUuuid uuid,
                                             int dev)
        Return an UUID for the device (11.4+).

        Returns 16-octets identifing the device dev in the structure pointed by the uuid. If the device is in MIG mode, returns its MIG UUID which uniquely identifies the subscribed MIG compute instance.

        Parameters:
        uuid - returned UUID
        dev - device to get identifier string for
      • ncuDeviceGetLuid

        public static int ncuDeviceGetLuid​(long luid,
                                           long deviceNodeMask,
                                           int dev)
        Unsafe version of: DeviceGetLuid
      • cuDeviceGetLuid

        public static int cuDeviceGetLuid​(java.nio.ByteBuffer luid,
                                          java.nio.IntBuffer deviceNodeMask,
                                          int dev)
        Return an LUID and device node mask for the device

        Return identifying information (luid and deviceNodeMask) to allow matching device with graphics APIs.

        Parameters:
        luid - returned LUID
        deviceNodeMask - returned device node mask
        dev - device to get identifier string for
      • ncuDeviceTotalMem

        public static int ncuDeviceTotalMem​(long bytes,
                                            int dev)
        Unsafe version of: DeviceTotalMem
      • cuDeviceTotalMem

        public static int cuDeviceTotalMem​(org.lwjgl.PointerBuffer bytes,
                                           int dev)
        Returns the total amount of memory on the device

        Returns in *bytes the total amount of memory available on the device dev in bytes.

        Parameters:
        bytes - returned memory available on device in bytes
        dev - device handle
      • ncuDeviceGetTexture1DLinearMaxWidth

        public static int ncuDeviceGetTexture1DLinearMaxWidth​(long maxWidthInElements,
                                                              int format,
                                                              int numChannels,
                                                              int dev)
      • cuDeviceGetTexture1DLinearMaxWidth

        public static int cuDeviceGetTexture1DLinearMaxWidth​(org.lwjgl.PointerBuffer maxWidthInElements,
                                                             int format,
                                                             int numChannels,
                                                             int dev)
        Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.

        Returns in maxWidthInElements the maximum number of texture elements allocatable in a 1D linear texture for given format and numChannels.

        Parameters:
        maxWidthInElements - returned maximum number of texture elements allocatable for given format and numChannels
        format - texture format
        numChannels - number of channels per texture element
        dev - device handle
      • ncuDeviceGetAttribute

        public static int ncuDeviceGetAttribute​(long pi,
                                                int attrib,
                                                int dev)
        Unsafe version of: DeviceGetAttribute
      • cuDeviceGetAttribute

        public static int cuDeviceGetAttribute​(java.nio.IntBuffer pi,
                                               int attrib,
                                               int dev)
        Returns information about the device.

        Returns in *pi the integer value of the attribute attrib on device dev. The supported attributes are:

        Parameters:
        pi - returned device attribute value
        attrib - device attribute to query
        dev - device handle
      • ncuDeviceGetNvSciSyncAttributes

        public static int ncuDeviceGetNvSciSyncAttributes​(long nvSciSyncAttrList,
                                                          int dev,
                                                          int flags)
        Unsafe version of: DeviceGetNvSciSyncAttributes
      • cuDeviceGetNvSciSyncAttributes

        public static int cuDeviceGetNvSciSyncAttributes​(java.nio.ByteBuffer nvSciSyncAttrList,
                                                         int dev,
                                                         int flags)
        Return NvSciSync attributes that this device can support.

        Returns in nvSciSyncAttrList, the properties of NvSciSync that this CUDA device, dev can support. The returned nvSciSyncAttrList can be used to create an NvSciSync object that matches this device's capabilities.

        If NvSciSyncAttrKey_RequiredPerm field in nvSciSyncAttrList is already set this API will return CUDA_ERROR_INVALID_VALUE.

        The applications should set nvSciSyncAttrList to a valid NvSciSyncAttrList failing which this API will return CUDA_ERROR_INVALID_HANDLE.

        The flags controls how applications intends to use the NvSciSync created from the nvSciSyncAttrList. The valid flags are:

        At least one of these flags must be set, failing which the API returns CUDA_ERROR_INVALID_VALUE. Both the flags are orthogonal to one another: a developer may set both these flags that allows to set both wait and signal specific attributes in the same nvSciSyncAttrList.

        Parameters:
        nvSciSyncAttrList - return NvSciSync attributes supported
        dev - valid Cuda Device to get NvSciSync attributes for
        flags - flags describing NvSciSync usage
      • cuDeviceSetMemPool

        public static int cuDeviceSetMemPool​(int dev,
                                             long pool)
        Sets the current memory pool of a device

        The memory pool must be local to the specified device. MemAllocAsync allocates from the current mempool of the provided stream's device. By default, a device's current memory pool is its default memory pool.

        Note

        Use MemAllocFromPoolAsync to specify asynchronous allocations from a device different than the one the stream runs on.

      • ncuDeviceGetMemPool

        public static int ncuDeviceGetMemPool​(long pool,
                                              int dev)
        Unsafe version of: DeviceGetMemPool
      • cuDeviceGetMemPool

        public static int cuDeviceGetMemPool​(org.lwjgl.PointerBuffer pool,
                                             int dev)
        Gets the current mempool for a device.

        Returns the last pool provided to DeviceSetMemPool for this device or the device's default memory pool if DeviceSetMemPool has never been called. By default the current mempool is the default mempool for a device. Otherwise the returned pool must have been set with DeviceSetMemPool.

      • ncuDeviceGetDefaultMemPool

        public static int ncuDeviceGetDefaultMemPool​(long pool_out,
                                                     int dev)
        Unsafe version of: DeviceGetDefaultMemPool
      • cuDeviceGetDefaultMemPool

        public static int cuDeviceGetDefaultMemPool​(org.lwjgl.PointerBuffer pool_out,
                                                    int dev)
        Returns the default mempool of a device.

        The default mempool of a device contains device memory from that device.

      • cuFlushGPUDirectRDMAWrites

        public static int cuFlushGPUDirectRDMAWrites​(int target,
                                                     int scope)
        Blocks until remote writes are visible to the specified scope.

        Blocks until GPUDirect RDMA writes to the target context via mappings created through APIs like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information), are visible to the specified scope.

        If the scope equals or lies within the scope indicated by DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING, the call will be a no-op and can be safely omitted for performance. This can be determined by comparing the numerical values between the two enums, with smaller scopes having smaller values.

        Users may query support for this API via DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.

        Parameters:
        target - the target of the operation, see CUflushGPUDirectRDMAWritesTarget
        scope - the scope of the operation, see CUflushGPUDirectRDMAWritesScope
      • ncuDeviceGetProperties

        public static int ncuDeviceGetProperties​(long prop,
                                                 int dev)
        Unsafe version of: DeviceGetProperties
      • cuDeviceGetProperties

        public static int cuDeviceGetProperties​(CUdevprop prop,
                                                int dev)
        Returns properties for a selected device.

        Deprecated: This function was deprecated as of CUDA 5.0 and replaced by DeviceGetAttribute.

        Returns in *prop the properties of device dev.

        Parameters:
        prop - returned properties of device
        dev - device to get properties for
      • ncuDeviceComputeCapability

        public static int ncuDeviceComputeCapability​(long major,
                                                     long minor,
                                                     int dev)
        Unsafe version of: DeviceComputeCapability
      • cuDeviceComputeCapability

        public static int cuDeviceComputeCapability​(java.nio.IntBuffer major,
                                                    java.nio.IntBuffer minor,
                                                    int dev)
        Returns the compute capability of the device.

        Deprecated: This function was deprecated as of CUDA 5.0 and its functionality superceded by DeviceGetAttribute.

        Returns in *major and *minor the major and minor revision numbers that define the compute capability of the device dev.

        Parameters:
        major - major revision number
        minor - minor revision number
        dev - device handle
      • ncuDevicePrimaryCtxRetain

        public static int ncuDevicePrimaryCtxRetain​(long pctx,
                                                    int dev)
        Unsafe version of: DevicePrimaryCtxRetain
      • cuDevicePrimaryCtxRetain

        public static int cuDevicePrimaryCtxRetain​(org.lwjgl.PointerBuffer pctx,
                                                   int dev)
        Retain the primary context on the GPU.

        Retains the primary context on the device. Once the user successfully retains the primary context, the primary context will be active and available to the user until the user releases it with DevicePrimaryCtxRelease or resets it with DevicePrimaryCtxReset. Unlike CtxCreate the newly retained context is not pushed onto the stack.

        Retaining the primary context for the first time will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

        Please note that the primary context always supports pinned allocations. Other flags can be specified by DevicePrimaryCtxSetFlags.

        Parameters:
        pctx - returned context handle of the new context
        dev - device for which primary context is requested
      • cuDevicePrimaryCtxRelease

        public static int cuDevicePrimaryCtxRelease​(int dev)
        Release the primary context on the GPU.

        Releases the primary context interop on the device. A retained context should always be released once the user is done using it. The context is automatically reset once the last reference to it is released. This behavior is different when the primary context was retained by the CUDA runtime from CUDA 4.0 and earlier. In this case, the primary context remains always active.

        Releasing a primary context that has not been previously retained will fail with CUDA_ERROR_INVALID_CONTEXT.

        Please note that unlike CtxDestroy this method does not pop the context from stack in any circumstances.

        Parameters:
        dev - device which primary context is released
      • cuDevicePrimaryCtxSetFlags

        public static int cuDevicePrimaryCtxSetFlags​(int dev,
                                                     int flags)
        Set flags for the primary context.

        Sets the flags for the primary context on the device overwriting perviously set ones.

        The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

        • CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
        • CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
        • CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
        • CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

          Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

        • CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
        • CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

          Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled.

        Parameters:
        dev - device for which the primary context flags are set
        flags - new flags for the device
      • ncuDevicePrimaryCtxGetState

        public static int ncuDevicePrimaryCtxGetState​(int dev,
                                                      long flags,
                                                      long active)
        Unsafe version of: DevicePrimaryCtxGetState
      • cuDevicePrimaryCtxGetState

        public static int cuDevicePrimaryCtxGetState​(int dev,
                                                     java.nio.IntBuffer flags,
                                                     java.nio.IntBuffer active)
        Get the state of the primary context.

        Returns in *flags the flags for the primary context of dev, and in *active whether it is active. See DevicePrimaryCtxSetFlags for flag values.

        Parameters:
        dev - device to get primary context flags for
        flags - pointer to store flags
        active - pointer to store context state; 0 = inactive, 1 = active
      • cuDevicePrimaryCtxReset

        public static int cuDevicePrimaryCtxReset​(int dev)
        Destroy all allocations and reset all state on the primary context.

        Explicitly destroys and cleans up all resources associated with the current device in the current process.

        Note that it is responsibility of the calling function to ensure that no other module in the process is using the device any more. For that reason it is recommended to use DevicePrimaryCtxRelease in most cases. However it is safe for other modules to call cuDevicePrimaryCtxRelease() even after resetting the device. Resetting the primary context does not release it, an application that has retained the primary context should explicitly release its usage.

        Parameters:
        dev - device for which primary context is destroyed
      • ncuDeviceGetExecAffinitySupport

        public static int ncuDeviceGetExecAffinitySupport​(long pi,
                                                          int type,
                                                          int dev)
        Unsafe version of: DeviceGetExecAffinitySupport
      • cuDeviceGetExecAffinitySupport

        public static int cuDeviceGetExecAffinitySupport​(java.nio.IntBuffer pi,
                                                         int type,
                                                         int dev)
        Returns information about the execution affinity support of the device.

        Returns in *pi whether execution affinity type type is supported by device dev. The supported types are:

        Parameters:
        pi - 1 if the execution affinity type type is supported by the device, or 0 if not
        type - execution affinity type to query
        dev - device handle
      • ncuCtxCreate

        public static int ncuCtxCreate​(long pctx,
                                       int flags,
                                       int dev)
        Unsafe version of: CtxCreate
      • cuCtxCreate

        public static int cuCtxCreate​(org.lwjgl.PointerBuffer pctx,
                                      int flags,
                                      int dev)
        Create a CUDA context.
        Note

        In most cases it is recommended to use DevicePrimaryCtxRetain.

        Creates a new CUDA context and associates it with the calling thread. The flags parameter is described below. The context is created with a usage count of 1 and the caller of cuCtxCreate() must call CtxDestroy or when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call to CtxPopCurrent.

        The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

        • CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
        • CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
        • CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
        • CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

          Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

        • CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
        • CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.
        • CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

          Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with CtxSetLimit.

        Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

        Parameters:
        pctx - returned context handle of the new context
        flags - context creation flags
        dev - device to create context on
      • ncuCtxCreate_v3

        public static int ncuCtxCreate_v3​(long pctx,
                                          long paramsArray,
                                          int numParams,
                                          int flags,
                                          int dev)
        Unsafe version of: CtxCreate_v3
        Parameters:
        numParams - number of execution affinity parameters
      • cuCtxCreate_v3

        public static int cuCtxCreate_v3​(org.lwjgl.PointerBuffer pctx,
                                         CUexecAffinityParam.Buffer paramsArray,
                                         int flags,
                                         int dev)
        Create a CUDA context with execution affinity.

        Creates a new CUDA context with execution affinity and associates it with the calling thread. The paramsArray and flags parameter are described below. The context is created with a usage count of 1 and the caller of CtxCreate must call CtxDestroy or when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call to CtxPopCurrent.

        The type and the amount of execution resource the context can use is limited by paramsArray and numParams. The paramsArray is an array of CUexecAffinityParam and the numParams describes the size of the array. If two CUexecAffinityParam in the array have the same type, the latter execution affinity parameter overrides the former execution affinity parameter. The supported execution affinity types are:

        • EXEC_AFFINITY_TYPE_SM_COUNT limits the portion of SMs that the context can use. The portion of SMs is specified as the number of SMs via CUexecAffinitySmCount. This limit will be internally rounded up to the next hardware-supported amount. Hence, it is imperative to query the actual execution affinity of the context via CtxGetExecAffinity) after context creation. Currently, this attribute is only supported under Volta+ MPS.

        The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

        • CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
        • CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
        • CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
        • CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

          Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

        • CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
        • CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.
        • CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

          Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with CtxSetLimit.

        Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

        Parameters:
        pctx - returned context handle of the new context
        paramsArray - execution affinity parameters
        flags - context creation flags
        dev - device to create context on
      • cuCtxDestroy

        public static int cuCtxDestroy​(long ctx)
        Destroy a CUDA context.

        Destroys the CUDA context specified by ctx. The context ctx will be destroyed regardless of how many threads it is current to. It is the responsibility of the calling function to ensure that no API call issues using ctx while cuCtxDestroy() is executing.

        Destroys and cleans up all resources associated with the context. It is the caller's responsibility to ensure that the context or its resources are not accessed or passed in subsequent API calls and doing so will result in undefined behavior. These resources include CUDA types such as CUmodule, CUfunction, CUstream, CUevent, CUarray, CUmipmappedArray, CUtexObject, CUsurfObject, CUtexref, CUsurfref, CUgraphicsResource, CUlinkState, CUexternalMemory and CUexternalSemaphore.

        If ctx is current to the calling thread then ctx will also be popped from the current thread's context stack (as though CtxPopCurrent were called). If ctx is current to other threads, then ctx will remain current to those threads, and attempting to access ctx from those threads will result in the error CUDA_ERROR_CONTEXT_IS_DESTROYED.

        Parameters:
        ctx - context to destroy
      • cuCtxPushCurrent

        public static int cuCtxPushCurrent​(long ctx)
        Pushes a context on the current CPU thread.

        Pushes the given context ctx onto the CPU thread's stack of current contexts. The specified context becomes the CPU thread's current context, so all CUDA functions that operate on the current context are affected.

        The previous current context may be made current again by calling CtxDestroy or CtxPopCurrent.

        Parameters:
        ctx - context to push
      • ncuCtxPopCurrent

        public static int ncuCtxPopCurrent​(long pctx)
        Unsafe version of: CtxPopCurrent
      • cuCtxPopCurrent

        public static int cuCtxPopCurrent​(org.lwjgl.PointerBuffer pctx)
        Pops the current CUDA context from the current CPU thread.

        Pops the current CUDA context from the CPU thread and passes back the old context handle in *pctx. That context may then be made current to a different CPU thread by calling CtxPushCurrent.

        If a context was current to the CPU thread before CtxCreate or CtxPushCurrent was called, this function makes that context current to the CPU thread again.

        Parameters:
        pctx - returned new context handle
      • cuCtxSetCurrent

        public static int cuCtxSetCurrent​(long ctx)
        Binds the specified CUDA context to the calling CPU thread.

        Binds the specified CUDA context to the calling CPU thread. If ctx is NULL then the CUDA context previously bound to the calling CPU thread is unbound and CUDA_SUCCESS is returned.

        If there exists a CUDA context stack on the calling CPU thread, this will replace the top of that stack with ctx. If ctx is NULL then this will be equivalent to popping the top of the calling CPU thread's CUDA context stack (or a no-op if the calling CPU thread's CUDA context stack is empty).

        Parameters:
        ctx - context to bind to the calling CPU thread
      • ncuCtxGetCurrent

        public static int ncuCtxGetCurrent​(long pctx)
        Unsafe version of: CtxGetCurrent
      • cuCtxGetCurrent

        public static int cuCtxGetCurrent​(org.lwjgl.PointerBuffer pctx)
        Returns the CUDA context bound to the calling CPU thread.

        Returns in *pctx the CUDA context bound to the calling CPU thread. If no context is bound to the calling CPU thread then *pctx is set to NULL and CUDA_SUCCESS is returned.

        Parameters:
        pctx - returned context handle
      • ncuCtxGetDevice

        public static int ncuCtxGetDevice​(long device)
        Unsafe version of: CtxGetDevice
      • cuCtxGetDevice

        public static int cuCtxGetDevice​(java.nio.IntBuffer device)
        Returns the device ID for the current context.

        Returns in *device the ordinal of the current context's device.

        Parameters:
        device - returned device ID for the current context
      • ncuCtxGetFlags

        public static int ncuCtxGetFlags​(long flags)
        Unsafe version of: CtxGetFlags
      • cuCtxGetFlags

        public static int cuCtxGetFlags​(java.nio.IntBuffer flags)
        Returns the flags for the current context.

        Returns in *flags the flags of the current context. See CtxCreate for flag values.

        Parameters:
        flags - pointer to store flags of current context
      • cuCtxSynchronize

        public static int cuCtxSynchronize()
        Block for a context's tasks to complete.

        Blocks until the device has completed all preceding requested tasks. cuCtxSynchronize() returns an error if one of the preceding tasks failed. If the context was created with the CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the GPU context has finished its work.

      • cuCtxSetLimit

        public static int cuCtxSetLimit​(int limit,
                                        long value)
        Set resource limits.

        Setting limit to value is a request by the application to update the current limit maintained by the context. The driver is free to modify the requested value to meet h/w requirements (this could be clamping to minimum or maximum values, rounding up to nearest element size, etc). The application can use CtxGetLimit to find out exactly what the limit has been set to.

        Setting each CUlimit has its own specific restrictions, so each is discussed here.

        • LIMIT_STACK_SIZE controls the stack size in bytes of each GPU thread. The driver automatically increases the per-thread stack size for each kernel launch as needed. This size isn't reset back to the original value after each launch. Setting this value will take effect immediately, and if necessary, the device will block until all preceding requested tasks are complete.
        • LIMIT_PRINTF_FIFO_SIZE controls the size in bytes of the FIFO used by the printf() device system call. Setting LIMIT_PRINTF_FIFO_SIZE must be performed before launching any kernel that uses the printf() device system call, otherwise CUDA_ERROR_INVALID_VALUE will be returned.
        • LIMIT_MALLOC_HEAP_SIZE controls the size in bytes of the heap used by the malloc() and free() device system calls. Setting CU_LIMIT_MALLOC_HEAP_SIZE must be performed before launching any kernel that uses the malloc() or free() device system calls, otherwise CUDA_ERROR_INVALID_VALUE will be returned.
        • LIMIT_DEV_RUNTIME_SYNC_DEPTH controls the maximum nesting depth of a grid at which a thread can safely call cudaDeviceSynchronize(). Setting this limit must be performed before any launch of a kernel that uses the device runtime and calls cudaDeviceSynchronize() above the default sync depth, two levels of grids. Calls to cudaDeviceSynchronize() will fail with error code cudaErrorSyncDepthExceeded if the limitation is violated. This limit can be set smaller than the default or up the maximum launch depth of 24. When setting this limit, keep in mind that additional levels of sync depth require the driver to reserve large amounts of device memory which can no longer be used for user allocations. If these reservations of device memory fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned.
        • LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT controls the maximum number of outstanding device runtime launches that can be made from the current context. A grid is outstanding from the point of launch up until the grid is known to have been completed. Device runtime launches which violate this limitation fail and return cudaErrorLaunchPendingCountExceeded when cudaGetLastError() is called after launch. If more pending launches than the default (2048 launches) are needed for a module using the device runtime, this limit can be increased. Keep in mind that being able to sustain additional pending launches will require the driver to reserve larger amounts of device memory upfront which can no longer be used for allocations. If these reservations fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned.
        • LIMIT_MAX_L2_FETCH_GRANULARITY controls the L2 cache fetch granularity. Values can range from 0B to 128B. This is purely a performence hint and it can be ignored or clamped depending on the platform.
        • LIMIT_PERSISTING_L2_CACHE_SIZE controls size in bytes availabe for persisting L2 cache. This is purely a performance hint and it can be ignored or clamped depending on the platform.
        Parameters:
        limit - limit to set
        value - size of limit
      • ncuCtxGetLimit

        public static int ncuCtxGetLimit​(long pvalue,
                                         int limit)
        Unsafe version of: CtxGetLimit
      • cuCtxGetLimit

        public static int cuCtxGetLimit​(org.lwjgl.PointerBuffer pvalue,
                                        int limit)
        Returns resource limits.

        Returns in *pvalue the current size of limit.

        Parameters:
        pvalue - returned size of limit
        limit - limit to query
      • ncuCtxGetCacheConfig

        public static int ncuCtxGetCacheConfig​(long pconfig)
        Unsafe version of: CtxGetCacheConfig
      • cuCtxGetCacheConfig

        public static int cuCtxGetCacheConfig​(java.nio.IntBuffer pconfig)
        Returns the preferred cache configuration for the current context.

        On devices where the L1 cache and shared memory use the same hardware resources, this function returns through pconfig the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute functions.

        This will return a pconfig of FUNC_CACHE_PREFER_NONE on devices where the size of the L1 cache and shared memory are fixed.

        Parameters:
        pconfig - returned cache configuration
      • cuCtxSetCacheConfig

        public static int cuCtxSetCacheConfig​(int config)
        Sets the preferred cache configuration for the current context.

        On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute the function. Any function preference set via cuFuncSetCacheConfig() will be preferred over this context-wide setting. Setting the context-wide cache configuration to FUNC_CACHE_PREFER_NONE will cause subsequent kernel launches to prefer to not change the cache configuration unless required to launch the kernel.

        This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

        Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

        Parameters:
        config - requested cache configuration
      • ncuCtxGetSharedMemConfig

        public static int ncuCtxGetSharedMemConfig​(long pConfig)
        Unsafe version of: CtxGetSharedMemConfig
      • cuCtxGetSharedMemConfig

        public static int cuCtxGetSharedMemConfig​(java.nio.IntBuffer pConfig)
        Returns the current shared memory configuration for the current context.

        This function will return in pConfig the current size of shared memory banks in the current context. On devices with configurable shared memory banks, CtxSetSharedMemConfig can be used to change this setting, so that all subsequent kernel launches will by default use the new bank size. When cuCtxGetSharedMemConfig is called on devices without configurable shared memory, it will return the fixed bank size of the hardware.

        Parameters:
        pConfig - returned shared memory configuration
      • cuCtxSetSharedMemConfig

        public static int cuCtxSetSharedMemConfig​(int config)
        Sets the shared memory configuration for the current context.

        On devices with configurable shared memory banks, this function will set the context's shared memory bank size which is used for subsequent kernel launches.

        Changed the shared memory configuration between launches may insert a device side synchronization point between those launches.

        Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

        This function will do nothing on devices with fixed shared memory bank size.

        Parameters:
        config - requested shared memory configuration
      • ncuCtxGetApiVersion

        public static int ncuCtxGetApiVersion​(long ctx,
                                              long version)
        Unsafe version of: CtxGetApiVersion
      • cuCtxGetApiVersion

        public static int cuCtxGetApiVersion​(long ctx,
                                             java.nio.IntBuffer version)
        Gets the context's API version.

        Returns a version number in version corresponding to the capabilities of the context (e.g. 3010 or 3020), which library developers can use to direct callers to a specific API version. If ctx is NULL, returns the API version used to create the currently bound context.

        Note that new API versions are only introduced when context capabilities are changed that break binary compatibility, so the API version and driver version may be different. For example, it is valid for the API version to be 3020 while the driver version is 4020.

        Parameters:
        ctx - context to check
        version - pointer to version
      • ncuCtxGetStreamPriorityRange

        public static int ncuCtxGetStreamPriorityRange​(long leastPriority,
                                                       long greatestPriority)
        Unsafe version of: CtxGetStreamPriorityRange
      • cuCtxGetStreamPriorityRange

        public static int cuCtxGetStreamPriorityRange​(@Nullable
                                                      java.nio.IntBuffer leastPriority,
                                                      @Nullable
                                                      java.nio.IntBuffer greatestPriority)
        Returns numerical values that correspond to the least and greatest stream priorities.

        Returns in *leastPriority and *greatestPriority the numerical values that correspond to the least and greatest stream priorities respectively. Stream priorities follow a convention where lower numbers imply greater priorities. The range of meaningful stream priorities is given by [ *greatestPriority, *leastPriority]. If the user attempts to create a stream with a priority value that is outside the meaningful range as specified by this API, the priority is automatically clamped down or up to either *leastPriority or *greatestPriority respectively. See StreamCreateWithPriority for details on creating a priority stream. A NULL may be passed in for *leastPriority or greatestPriority if the value is not desired.

        This function will return 0 in both *leastPriority and *greatestPriority if the current context's device does not support stream priorities (see DeviceGetAttribute).

        Parameters:
        leastPriority - pointer to an int in which the numerical value for least stream priority is returned
        greatestPriority - pointer to an int in which the numerical value for greatest stream priority is returned
      • cuCtxResetPersistingL2Cache

        public static int cuCtxResetPersistingL2Cache()
        Resets all persisting lines in cache to normal status.

        Takes effect on function return.

      • ncuCtxGetExecAffinity

        public static int ncuCtxGetExecAffinity​(long pExecAffinity,
                                                int type)
        Unsafe version of: CtxGetExecAffinity
      • cuCtxGetExecAffinity

        public static int cuCtxGetExecAffinity​(CUexecAffinityParam.Buffer pExecAffinity,
                                               int type)
        Returns the execution affinity setting for the current context.

        Returns in *pExecAffinity the current value of type.

        Parameters:
        pExecAffinity - returned execution affinity
        type - execution affinity type to query
      • ncuCtxAttach

        public static int ncuCtxAttach​(long pctx,
                                       int flags)
        Unsafe version of: CtxAttach
      • cuCtxAttach

        public static int cuCtxAttach​(org.lwjgl.PointerBuffer pctx,
                                      int flags)
        Increment a context's usage-count.

        Deprecated: Note that this function is deprecated and should not be used.

        Increments the usage count of the context and passes back a context handle in *pctx that must be passed to CtxDetach when the application is done with the context. cuCtxAttach() fails if there is no context current to the thread.

        Currently, the flags parameter must be 0.

        Parameters:
        pctx - returned context handle of the current context
        flags - context attach flags (must be 0)
      • cuCtxDetach

        public static int cuCtxDetach​(long ctx)
        Decrement a context's usage-count

        Deprecated: Note that this function is deprecated and should not be used.

        Decrements the usage count of the context ctx, and destroys the context if the usage count goes to 0. The context must be a handle that was passed back by CtxCreate or CtxAttach, and must be current to the calling thread.

        Parameters:
        ctx - context to destroy
      • ncuModuleLoad

        public static int ncuModuleLoad​(long module,
                                        long fname)
        Unsafe version of: ModuleLoad
      • cuModuleLoad

        public static int cuModuleLoad​(org.lwjgl.PointerBuffer module,
                                       java.nio.ByteBuffer fname)
        
        public static int cuModuleLoad​(org.lwjgl.PointerBuffer module,
                                       java.lang.CharSequence fname)
        
        Loads a compute module.

        Takes a filename fname and loads the corresponding module module into the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated, cuModuleLoad() fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.

        Parameters:
        module - returned module
        fname - filename of module to load
      • ncuModuleLoadData

        public static int ncuModuleLoadData​(long module,
                                            long image)
        Unsafe version of: ModuleLoadData
      • cuModuleLoadData

        public static int cuModuleLoadData​(org.lwjgl.PointerBuffer module,
                                           java.nio.ByteBuffer image)
        Load a module's data.

        Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer.

        Parameters:
        module - returned module
        image - module data to load
      • ncuModuleLoadDataEx

        public static int ncuModuleLoadDataEx​(long module,
                                              long image,
                                              int numOptions,
                                              long options,
                                              long optionValues)
        Unsafe version of: ModuleLoadDataEx
        Parameters:
        numOptions - number of options
      • cuModuleLoadDataEx

        public static int cuModuleLoadDataEx​(org.lwjgl.PointerBuffer module,
                                             java.nio.ByteBuffer image,
                                             @Nullable
                                             java.nio.IntBuffer options,
                                             @Nullable
                                             org.lwjgl.PointerBuffer optionValues)
        Load a module's data with options.

        Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer. Options are passed as an array via options and any corresponding parameters are passed in optionValues. The number of total options is supplied via numOptions. Any outputs will be returned via optionValues.

        Parameters:
        module - returned module
        image - module data to load
        options - options for JIT
        optionValues - option values for JIT
      • ncuModuleLoadFatBinary

        public static int ncuModuleLoadFatBinary​(long module,
                                                 long fatCubin)
        Unsafe version of: ModuleLoadFatBinary
      • cuModuleLoadFatBinary

        public static int cuModuleLoadFatBinary​(org.lwjgl.PointerBuffer module,
                                                java.nio.ByteBuffer fatCubin)
        Load a module's data.

        Takes a pointer fatCubin and loads the corresponding module module into the current context. The pointer represents a fat binary object, which is a collection of different cubin and/or PTX files, all representing the same device code, but compiled and optimized for different architectures.

        Prior to CUDA 4.0, there was no documented API for constructing and using fat binary objects by programmers. Starting with CUDA 4.0, fat binary objects can be constructed by providing the -fatbin option to nvcc. More information can be found in the nvcc document.

        Parameters:
        module - returned module
        fatCubin - fat binary to load
      • cuModuleUnload

        public static int cuModuleUnload​(long hmod)
        Unloads a module.

        Unloads a module hmod from the current context.

        Parameters:
        hmod - module to unload
      • ncuModuleGetFunction

        public static int ncuModuleGetFunction​(long hfunc,
                                               long hmod,
                                               long name)
        Unsafe version of: ModuleGetFunction
      • cuModuleGetFunction

        public static int cuModuleGetFunction​(org.lwjgl.PointerBuffer hfunc,
                                              long hmod,
                                              java.nio.ByteBuffer name)
        
        public static int cuModuleGetFunction​(org.lwjgl.PointerBuffer hfunc,
                                              long hmod,
                                              java.lang.CharSequence name)
        
        Returns a function handle.

        Returns in *hfunc the handle of the function of name name located in module hmod. If no function of that name exists, cuModuleGetFunction() returns CUDA_ERROR_NOT_FOUND.

        Parameters:
        hfunc - returned function handle
        hmod - module to retrieve function from
        name - name of function to retrieve
      • ncuModuleGetGlobal

        public static int ncuModuleGetGlobal​(long dptr,
                                             long bytes,
                                             long hmod,
                                             long name)
        Unsafe version of: ModuleGetGlobal
      • cuModuleGetGlobal

        public static int cuModuleGetGlobal​(@Nullable
                                            org.lwjgl.PointerBuffer dptr,
                                            @Nullable
                                            org.lwjgl.PointerBuffer bytes,
                                            long hmod,
                                            java.nio.ByteBuffer name)
        
        public static int cuModuleGetGlobal​(@Nullable
                                            org.lwjgl.PointerBuffer dptr,
                                            @Nullable
                                            org.lwjgl.PointerBuffer bytes,
                                            long hmod,
                                            java.lang.CharSequence name)
        
        Returns a global pointer from a module.

        Returns in *dptr and *bytes the base pointer and size of the global of name name located in module hmod. If no variable of that name exists, cuModuleGetGlobal() returns CUDA_ERROR_NOT_FOUND. Both parameters dptr and bytes are optional. If one of them is NULL, it is ignored.

        Parameters:
        dptr - returned global device pointer
        bytes - returned global size in bytes
        hmod - module to retrieve global from
        name - name of global to retrieve
      • ncuModuleGetTexRef

        public static int ncuModuleGetTexRef​(long pTexRef,
                                             long hmod,
                                             long name)
        Unsafe version of: ModuleGetTexRef
      • cuModuleGetTexRef

        public static int cuModuleGetTexRef​(org.lwjgl.PointerBuffer pTexRef,
                                            long hmod,
                                            java.nio.ByteBuffer name)
        
        public static int cuModuleGetTexRef​(org.lwjgl.PointerBuffer pTexRef,
                                            long hmod,
                                            java.lang.CharSequence name)
        
        Returns a handle to a texture reference.

        Returns in *pTexRef the handle of the texture reference of name name in the module hmod. If no texture reference of that name exists, cuModuleGetTexRef() returns CUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.

        Parameters:
        pTexRef - returned texture reference
        hmod - module to retrieve texture reference from
        name - name of texture reference to retrieve
      • ncuModuleGetSurfRef

        public static int ncuModuleGetSurfRef​(long pSurfRef,
                                              long hmod,
                                              long name)
        Unsafe version of: ModuleGetSurfRef
      • cuModuleGetSurfRef

        public static int cuModuleGetSurfRef​(org.lwjgl.PointerBuffer pSurfRef,
                                             long hmod,
                                             java.nio.ByteBuffer name)
        
        public static int cuModuleGetSurfRef​(org.lwjgl.PointerBuffer pSurfRef,
                                             long hmod,
                                             java.lang.CharSequence name)
        
        Returns a handle to a surface reference.

        Returns in *pSurfRef the handle of the surface reference of name name in the module hmod. If no surface reference of that name exists, cuModuleGetSurfRef() returns CUDA_ERROR_NOT_FOUND.

        Parameters:
        pSurfRef - returned surface reference
        hmod - module to retrieve surface reference from
        name - name of surface reference to retrieve
      • ncuLinkCreate

        public static int ncuLinkCreate​(int numOptions,
                                        long options,
                                        long optionValues,
                                        long stateOut)
        Unsafe version of: LinkCreate
        Parameters:
        numOptions - size of options arrays
      • cuLinkCreate

        public static int cuLinkCreate​(java.nio.IntBuffer options,
                                       org.lwjgl.PointerBuffer optionValues,
                                       org.lwjgl.PointerBuffer stateOut)
        Creates a pending JIT linker invocation.

        If the call is successful, the caller owns the returned CUlinkState, which should eventually be destroyed with LinkDestroy. The device code machine size (32 or 64 bit) will match the calling application.

        Both linker and compiler options may be specified. Compiler options will be applied to inputs to this linker action which must be compiled from PTX. The options JIT_WALL_TIME, JIT_INFO_LOG_BUFFER_SIZE_BYTES, and JIT_ERROR_LOG_BUFFER_SIZE_BYTES will accumulate data until the CUlinkState is destroyed.

        optionValues must remain valid for the life of the CUlinkState if output options are used. No other references to inputs are maintained after this call returns.

        Parameters:
        options - array of linker and compiler options
        optionValues - array of option values, each cast to void *
        stateOut - on success, this will contain a CUlinkState to specify and complete this action
      • ncuLinkAddData

        public static int ncuLinkAddData​(long state,
                                         int type,
                                         long data,
                                         long size,
                                         long name,
                                         int numOptions,
                                         long options,
                                         long optionValues)
        Unsafe version of: LinkAddData
        Parameters:
        size - the length of the input data
        numOptions - size of options
      • cuLinkAddData

        public static int cuLinkAddData​(long state,
                                        int type,
                                        java.nio.ByteBuffer data,
                                        java.nio.ByteBuffer name,
                                        java.nio.IntBuffer options,
                                        org.lwjgl.PointerBuffer optionValues)
        
        public static int cuLinkAddData​(long state,
                                        int type,
                                        java.nio.ByteBuffer data,
                                        java.lang.CharSequence name,
                                        java.nio.IntBuffer options,
                                        org.lwjgl.PointerBuffer optionValues)
        
        Add an input to a pending linker invocation.

        Ownership of data is retained by the caller. No reference is retained to any inputs after this call returns.

        This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

        Parameters:
        state - a pending linker action
        type - the type of the input data
        data - the input data. PTX must be NULL-terminated.
        name - an optional name for this input in log messages
        options - options to be applied only for this input (overrides options from LinkCreate)
        optionValues - array of option values, each cast to void *
      • ncuLinkAddFile

        public static int ncuLinkAddFile​(long state,
                                         int type,
                                         long path,
                                         int numOptions,
                                         long options,
                                         long optionValues)
        Unsafe version of: LinkAddFile
        Parameters:
        numOptions - size of options
      • cuLinkAddFile

        public static int cuLinkAddFile​(long state,
                                        int type,
                                        java.nio.ByteBuffer path,
                                        java.nio.IntBuffer options,
                                        org.lwjgl.PointerBuffer optionValues)
        
        public static int cuLinkAddFile​(long state,
                                        int type,
                                        java.lang.CharSequence path,
                                        java.nio.IntBuffer options,
                                        org.lwjgl.PointerBuffer optionValues)
        
        Add a file input to a pending linker invocation.

        No reference is retained to any inputs after this call returns.

        This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

        This method is equivalent to invoking LinkAddData on the contents of the file.

        Parameters:
        state - a pending linker action
        type - the type of the input data
        path - path to the input file
        options - options to be applied only for this input (overrides options from LinkCreate)
        optionValues - array of option values, each cast to void *
      • ncuLinkComplete

        public static int ncuLinkComplete​(long state,
                                          long cubinOut,
                                          long sizeOut)
        Unsafe version of: LinkComplete
      • cuLinkComplete

        public static int cuLinkComplete​(long state,
                                         org.lwjgl.PointerBuffer cubinOut,
                                         org.lwjgl.PointerBuffer sizeOut)
        Complete a pending linker invocation.

        Completes the pending linker action and returns the cubin image for the linked device code, which can be used with ModuleLoadData. The cubin is owned by state, so it should be loaded before state is destroyed via LinkDestroy. This call does not destroy state.

        Parameters:
        state - a pending linker invocation
        cubinOut - on success, this will point to the output image
        sizeOut - optional parameter to receive the size of the generated image
      • cuLinkDestroy

        public static int cuLinkDestroy​(long state)
        Destroys state for a JIT linker invocation.
        Parameters:
        state - state object for the linker invocation
      • ncuMemGetInfo

        public static int ncuMemGetInfo​(long free,
                                        long total)
        Unsafe version of: MemGetInfo
      • cuMemGetInfo

        public static int cuMemGetInfo​(org.lwjgl.PointerBuffer free,
                                       org.lwjgl.PointerBuffer total)
        Gets free and total memory.

        Returns in *total the total amount of memory available to the the current context. Returns in *free the amount of memory on the device that is free according to the OS. CUDA is not guaranteed to be able to allocate all of the memory that the OS reports as free.

        Parameters:
        free - returned free memory in bytes
        total - returned total memory in bytes
      • ncuMemAlloc

        public static int ncuMemAlloc​(long dptr,
                                      long bytesize)
        Unsafe version of: MemAlloc
      • cuMemAlloc

        public static int cuMemAlloc​(org.lwjgl.PointerBuffer dptr,
                                     long bytesize)
        Allocates device memory.

        Allocates bytesize bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, cuMemAlloc() returns CUDA_ERROR_INVALID_VALUE.

        Parameters:
        dptr - returned device pointer
        bytesize - requested allocation size in bytes
      • ncuMemAllocPitch

        public static int ncuMemAllocPitch​(long dptr,
                                           long pPitch,
                                           long WidthInBytes,
                                           long Height,
                                           int ElementSizeBytes)
        Unsafe version of: MemAllocPitch
      • cuMemAllocPitch

        public static int cuMemAllocPitch​(org.lwjgl.PointerBuffer dptr,
                                          org.lwjgl.PointerBuffer pPitch,
                                          long WidthInBytes,
                                          long Height,
                                          int ElementSizeBytes)
        Allocates pitched device memory.

        Allocates at least WidthInBytes * Height bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The function may pad the allocation to ensure that corresponding pointers in any given row will continue to meet the alignment requirements for coalescing as the address is updated from row to row. ElementSizeBytes specifies the size of the largest reads and writes that will be performed on the memory range. ElementSizeBytes may be 4, 8 or 16 (since coalesced memory transactions are not possible on other data sizes). If ElementSizeBytes is smaller than the actual read/write size of a kernel, the kernel will run correctly, but possibly at reduced speed. The pitch returned in *pPitch by cuMemAllocPitch() is the width in bytes of the allocation. The intended usage of pitch is as a separate parameter of the allocation, used to compute addresses within the 2D array. Given the row and column of an array element of type T, the address is computed as:

        
            T* pElement = (T*)((char*)BaseAddress + Row * Pitch) + Column;

        The pitch returned by cuMemAllocPitch() is guaranteed to work with Memcpy2D under all circumstances. For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations using cuMemAllocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing 2D memory copies between different regions of device memory (whether linear memory or CUDA arrays).

        The byte alignment of the pitch returned by cuMemAllocPitch() is guaranteed to match or exceed the alignment requirement for texture binding with TexRefSetAddress2D.

        Parameters:
        dptr - returned device pointer
        pPitch - returned pitch of allocation in bytes
        WidthInBytes - requested allocation width in bytes
        Height - requested allocation height in rows
        ElementSizeBytes - size of largest reads/writes for range
      • cuMemFree

        public static int cuMemFree​(long dptr)
        Frees device memory.

        Frees the memory space pointed to by dptr, which must have been returned by a previous call to MemAlloc or MemAllocPitch.

        Parameters:
        dptr - pointer to memory to free
      • ncuMemGetAddressRange

        public static int ncuMemGetAddressRange​(long pbase,
                                                long psize,
                                                long dptr)
        Unsafe version of: MemGetAddressRange
      • cuMemGetAddressRange

        public static int cuMemGetAddressRange​(@Nullable
                                               org.lwjgl.PointerBuffer pbase,
                                               @Nullable
                                               org.lwjgl.PointerBuffer psize,
                                               long dptr)
        Get information on memory allocations.

        Returns the base address in *pbase and size in *psize of the allocation by MemAlloc or MemAllocPitch that contains the input pointer dptr. Both parameters pbase and psize are optional. If one of them is NULL, it is ignored.

        Parameters:
        pbase - returned base address
        psize - returned size of device memory allocation
        dptr - device pointer to query
      • ncuMemAllocHost

        public static int ncuMemAllocHost​(long pp,
                                          long bytesize)
        Unsafe version of: MemAllocHost
      • cuMemAllocHost

        public static int cuMemAllocHost​(org.lwjgl.PointerBuffer pp,
                                         long bytesize)
        Allocates page-locked host memory.

        Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as Memcpy. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of memory with cuMemAllocHost() may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

        Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). The device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. See CUDA_UNIFIED for additional details.

        Parameters:
        pp - returned host pointer to page-locked memory
        bytesize - requested allocation size in bytes
      • ncuMemFreeHost

        public static int ncuMemFreeHost​(long p)
        Unsafe version of: MemFreeHost
      • cuMemFreeHost

        public static int cuMemFreeHost​(java.nio.ByteBuffer p)
        Frees page-locked host memory.

        Frees the memory space pointed to by p, which must have been returned by a previous call to MemAllocHost.

        Parameters:
        p - pointer to memory to free
      • ncuMemHostAlloc

        public static int ncuMemHostAlloc​(long pp,
                                          long bytesize,
                                          int Flags)
        Unsafe version of: MemHostAlloc
      • cuMemHostAlloc

        public static int cuMemHostAlloc​(org.lwjgl.PointerBuffer pp,
                                         long bytesize,
                                         int Flags)
        Allocates page-locked host memory.

        Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as MemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of pinned memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

        The Flags parameter enables different options to be specified that affect the allocation, as follows:

        • MEMHOSTALLOC_PORTABLE: The memory returned by this call will be considered as pinned memory by all CUDA contexts, not just the one that performed the allocation.
        • MEMHOSTALLOC_DEVICEMAP: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling MemHostGetDevicePointer.
        • MEMHOSTALLOC_WRITECOMBINED: Allocates the memory as write-combined (WC). WC memory can be transferred across the PCI Express bus more quickly on some system configurations, but cannot be read efficiently by most CPUs. WC memory is a good option for buffers that will be written by the CPU and read by the GPU via mapped pinned memory or host->device transfers.

        All of these flags are orthogonal to one another: a developer may allocate memory that is portable, mapped and/or write-combined with no restrictions.

        The MEMHOSTALLOC_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to MemHostGetDevicePointer because the memory may be mapped into other CUDA contexts via the MEMHOSTALLOC_PORTABLE flag.

        The memory allocated by this function must be freed with MemFreeHost.

        Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). Unless the flag MEMHOSTALLOC_WRITECOMBINED is specified, the device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. If the flag MEMHOSTALLOC_WRITECOMBINED is specified, then the function MemHostGetDevicePointer must be used to query the device pointer, even if the context supports unified addressing. See CUDA_UNIFIED for additional details.

        Parameters:
        pp - returned host pointer to page-locked memory
        bytesize - requested allocation size in bytes
        Flags - flags for allocation request
      • ncuMemHostGetDevicePointer

        public static int ncuMemHostGetDevicePointer​(long pdptr,
                                                     long p,
                                                     int Flags)
        Unsafe version of: MemHostGetDevicePointer
      • cuMemHostGetDevicePointer

        public static int cuMemHostGetDevicePointer​(org.lwjgl.PointerBuffer pdptr,
                                                    java.nio.ByteBuffer p,
                                                    int Flags)
        Passes back device pointer of mapped pinned memory.

        Passes back the device pointer pdptr corresponding to the mapped, pinned host buffer p allocated by MemHostAlloc.

        cuMemHostGetDevicePointer() will fail if the MEMHOSTALLOC_DEVICEMAP flag was not specified at the time the memory was allocated, or if the function is called on a GPU that does not support mapped pinned memory.

        For devices that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer p and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer p. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer p, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.

        Flags provides for future releases. For now, it must be set to 0.

        Parameters:
        pdptr - returned device pointer
        p - host pointer
        Flags - options (must be 0)
      • ncuMemHostGetFlags

        public static int ncuMemHostGetFlags​(long pFlags,
                                             long p)
        Unsafe version of: MemHostGetFlags
      • cuMemHostGetFlags

        public static int cuMemHostGetFlags​(java.nio.IntBuffer pFlags,
                                            java.nio.ByteBuffer p)
        Passes back flags that were used for a pinned allocation

        Passes back the flags pFlags that were specified when allocating the pinned host buffer p allocated by MemHostAlloc.

        cuMemHostGetFlags() will fail if the pointer does not reside in an allocation performed by MemAllocHost or cuMemHostAlloc().

        Parameters:
        pFlags - returned flags word
        p - host pointer
      • ncuMemAllocManaged

        public static int ncuMemAllocManaged​(long dptr,
                                             long bytesize,
                                             int flags)
        Unsafe version of: MemAllocManaged
      • cuMemAllocManaged

        public static int cuMemAllocManaged​(org.lwjgl.PointerBuffer dptr,
                                            long bytesize,
                                            int flags)
        Allocates memory that will be automatically managed by the Unified Memory system.

        Allocates bytesize bytes of managed memory on the device and returns in *dptr a pointer to the allocated memory. If the device doesn't support allocating managed memory, CUDA_ERROR_NOT_SUPPORTED is returned. Support for managed memory can be queried using the device attribute DEVICE_ATTRIBUTE_MANAGED_MEMORY. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, MemAllocManaged returns CUDA_ERROR_INVALID_VALUE. The pointer is valid on the CPU and on all GPUs in the system that support managed memory. All accesses to this pointer must obey the Unified Memory programming model.

        flags specifies the default stream association for this allocation. flags must be one of MEM_ATTACH_GLOBAL or MEM_ATTACH_HOST. If MEM_ATTACH_GLOBAL is specified, then this memory is accessible from any stream on any device. If MEM_ATTACH_HOST is specified, then the allocation should not be accessed from devices that have a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS; an explicit call to StreamAttachMemAsync will be required to enable access on such devices.

        If the association is later changed via StreamAttachMemAsync to a single stream, the default association as specifed during MemAllocManaged is restored when that stream is destroyed. For __managed__ variables, the default association is always MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.

        Memory allocated with MemAllocManaged should be released with MemFree.

        Device memory oversubscription is possible for GPUs that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Managed memory on such GPUs may be evicted from device memory to host memory at any time by the Unified Memory driver in order to make room for other allocations.

        In a multi-GPU system where all GPUs have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, managed memory may not be populated when this API returns and instead may be populated on access. In such systems, managed memory can migrate to any processor's memory at any time. The Unified Memory driver will employ heuristics to maintain data locality and prevent excessive page faults to the extent possible. The application can also guide the driver about memory usage patterns via MemAdvise. The application can also explicitly migrate memory to a desired processor's memory via MemPrefetchAsync.

        In a multi-GPU system where all of the GPUs have a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS and all the GPUs have peer-to-peer support with each other, the physical storage for managed memory is created on the GPU which is active at the time MemAllocManaged is called. All other GPUs will reference the data at reduced bandwidth via peer mappings over the PCIe bus. The Unified Memory driver does not migrate memory among such GPUs.

        In a multi-GPU system where not all GPUs have peer-to-peer support with each other and where the value of the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS is zero for at least one of those GPUs, the location chosen for physical storage of managed memory is system-dependent.

        • On Linux, the location chosen will be device memory as long as the current set of active contexts are on devices that either have peer-to-peer support with each other or have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If there is an active context on a GPU that does not have a non-zero value for that device attribute and it does not have peer-to-peer support with the other devices that have active contexts on them, then the location for physical storage will be 'zero-copy' or host memory. Note that this means that managed memory that is located in device memory is migrated to host memory if a new context is created on a GPU that doesn't have a non-zero value for the device attribute and does not support peer-to-peer with at least one of the other devices that has an active context. This in turn implies that context creation may fail if there is insufficient host memory to migrate all managed allocations.
        • On Windows, the physical storage is always created in 'zero-copy' or host memory. All GPUs will reference the data at reduced bandwidth over the PCIe bus. In these circumstances, use of the environment variable CUDA_VISIBLE_DEVICES is recommended to restrict CUDA to only use those GPUs that have peer-to-peer support. Alternatively, users can also set CUDA_MANAGED_FORCE_DEVICE_ALLOC to a non-zero value to force the driver to always use device memory for physical storage. When this environment variable is set to a non-zero value, all contexts created in that process on devices that support managed memory have to be peer-to-peer compatible with each other. Context creation will fail if a context is created on a device that supports managed memory and is not peer-to-peer compatible with any of the other managed memory supporting devices on which contexts were previously created, even if those contexts have been destroyed. These environment variables are described in the CUDA programming guide under the "CUDA environment variables" section.
        • On ARM, managed memory is not available on discrete gpu with Drive PX-2.
        Parameters:
        dptr - returned device pointer
        bytesize - requested allocation size in bytes
        flags - must be one of MEM_ATTACH_GLOBAL or MEM_ATTACH_HOST
      • ncuDeviceGetByPCIBusId

        public static int ncuDeviceGetByPCIBusId​(long dev,
                                                 long pciBusId)
        Unsafe version of: DeviceGetByPCIBusId
      • cuDeviceGetByPCIBusId

        public static int cuDeviceGetByPCIBusId​(java.nio.IntBuffer dev,
                                                java.nio.ByteBuffer pciBusId)
        
        public static int cuDeviceGetByPCIBusId​(java.nio.IntBuffer dev,
                                                java.lang.CharSequence pciBusId)
        
        Returns a handle to a compute device.

        Returns in *device a device handle given a PCI bus ID string.

        Parameters:
        dev - returned device handle
        pciBusId - string in one of the following forms: [domain]:[bus]:[device].[function] [domain]:[bus]:[device] [bus]:[device].[function] where domain, bus, device, and function are all hexadecimal values
      • ncuDeviceGetPCIBusId

        public static int ncuDeviceGetPCIBusId​(long pciBusId,
                                               int len,
                                               int dev)
        Unsafe version of: DeviceGetPCIBusId
        Parameters:
        len - maximum length of string to store in name
      • cuDeviceGetPCIBusId

        public static int cuDeviceGetPCIBusId​(java.nio.ByteBuffer pciBusId,
                                              int dev)
        Returns a PCI Bus Id string for the device.

        Returns an ASCII string identifying the device dev in the NULL-terminated string pointed to by pciBusId. len specifies the maximum length of the string that may be returned.

        Parameters:
        pciBusId - returned identifier string for the device in the following format [domain]:[bus]:[device].[function] where domain, bus, device, and function are all hexadecimal values. pciBusId should be large enough to store 13 characters including the NULL-terminator.
        dev - device to get identifier string for
      • ncuIpcGetEventHandle

        public static int ncuIpcGetEventHandle​(long pHandle,
                                               long event)
        Unsafe version of: IpcGetEventHandle
      • cuIpcGetEventHandle

        public static int cuIpcGetEventHandle​(CUIPCEventHandle pHandle,
                                              long event)
        Gets an interprocess handle for a previously allocated event.

        Takes as input a previously allocated event. This event must have been created with the EVENT_INTERPROCESS and EVENT_DISABLE_TIMING flags set. This opaque handle may be copied into other processes and opened with IpcOpenEventHandle to allow efficient hardware synchronization between GPU work in different processes.

        After the event has been opened in the importing process, EventRecord, EventSynchronize, StreamWaitEvent and EventQuery may be used in either process. Performing operations on the imported event after the exported event has been freed with EventDestroy will result in undefined behavior.

        IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

        Parameters:
        pHandle - pointer to a user allocated CUipcEventHandle in which to return the opaque event handle
        event - event allocated with EVENT_INTERPROCESS and EVENT_DISABLE_TIMING flags
      • ncuIpcOpenEventHandle

        public static int ncuIpcOpenEventHandle​(long phEvent,
                                                long handle)
        Unsafe version of: IpcOpenEventHandle
      • cuIpcOpenEventHandle

        public static int cuIpcOpenEventHandle​(org.lwjgl.PointerBuffer phEvent,
                                               CUIPCEventHandle handle)
        Opens an interprocess event handle for use in the current process.

        Opens an interprocess event handle exported from another process with IpcGetEventHandle. This function returns a CUevent that behaves like a locally created event with the EVENT_DISABLE_TIMING flag specified. This event must be freed with EventDestroy.

        Performing operations on the imported event after the exported event has been freed with cuEventDestroy will result in undefined behavior.

        IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

        Parameters:
        phEvent - returns the imported event
        handle - interprocess handle to open
      • ncuIpcGetMemHandle

        public static int ncuIpcGetMemHandle​(long pHandle,
                                             long dptr)
        Unsafe version of: IpcGetMemHandle
      • cuIpcGetMemHandle

        public static int cuIpcGetMemHandle​(CUIPCMemHandle pHandle,
                                            long dptr)
        Gets an interprocess memory handle for an existing device memory allocation.

        Takes a pointer to the base of an existing device memory allocation created with MemAlloc and exports it for use in another process. This is a lightweight operation and may be called multiple times on an allocation without adverse effects.

        If a region of memory is freed with MemFree and a subsequent call to MemAlloc returns memory with the same device address, IpcGetMemHandle will return a unique handle for the new memory.

        IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

        Parameters:
        pHandle - pointer to user allocated CUipcMemHandle to return the handle in
        dptr - base pointer to previously allocated device memory
      • ncuIpcOpenMemHandle

        public static int ncuIpcOpenMemHandle​(long pdptr,
                                              long handle,
                                              int Flags)
        Unsafe version of: IpcOpenMemHandle
      • cuIpcOpenMemHandle

        public static int cuIpcOpenMemHandle​(org.lwjgl.PointerBuffer pdptr,
                                             CUIPCMemHandle handle,
                                             int Flags)
        Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.

        Maps memory exported from another process with IpcGetMemHandle into the current device address space. For contexts on different devices cuIpcOpenMemHandle can attempt to enable peer access between the devices as if the user called CtxEnablePeerAccess. This behavior is controlled by the IPC_MEM_LAZY_ENABLE_PEER_ACCESS flag. DeviceCanAccessPeer can determine if a mapping is possible.

        Contexts that may open CUIPCMemHandle are restricted in the following way. CUipcMemHandles from each CUdevice in a given process may only be opened by one CUcontext per CUdevice per other process.

        If the memory handle has already been opened by the current context, the reference count on the handle is incremented by 1 and the existing device pointer is returned.

        Memory returned from cuIpcOpenMemHandle must be freed with IpcCloseMemHandle.

        Calling MemFree on an exported memory region before calling cuIpcCloseMemHandle in the importing context will result in undefined behavior.

        IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

        Note

        No guarantees are made about the address returned in *pdptr. In particular, multiple processes may not receive the same address for the same handle.

        Parameters:
        pdptr - returned device pointer
        handle - CUipcMemHandle to open
        Flags - flags for this operation. Must be specified as IPC_MEM_LAZY_ENABLE_PEER_ACCESS.
      • cuIpcCloseMemHandle

        public static int cuIpcCloseMemHandle​(long dptr)
        Attempts to close memory mapped with IpcOpenMemHandle.

        Decrements the reference count of the memory returned by cuIpcOpenMemHandle() by 1. When the reference count reaches 0, this API unmaps the memory. The original allocation in the exporting process as well as imported mappings in other processes will be unaffected.

        Any resources used to enable peer access will be freed if this is the last mapping using them.

        IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

        Parameters:
        dptr - device pointer returned by cuIpcOpenMemHandle()
      • ncuMemHostRegister

        public static int ncuMemHostRegister​(long p,
                                             long bytesize,
                                             int Flags)
        Unsafe version of: MemHostRegister
        Parameters:
        bytesize - size in bytes of the address range to page-lock
      • cuMemHostRegister

        public static int cuMemHostRegister​(java.nio.ByteBuffer p,
                                            int Flags)
        Registers an existing host memory range for use by CUDA.

        Page-locks the memory range specified by p and bytesize and maps it for the device(s) as specified by Flags. This memory range also is added to the same tracking mechanism as MemHostAlloc to automatically accelerate calls to functions such as MemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory that has not been registered. Page-locking excessive amounts of memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to register staging areas for data exchange between host and device.

        This function has limited support on Mac OS X. OS 10.7 or higher is required.

        All flags are orthogonal to one another: a developer may page-lock memory that is portable or mapped with no restrictions.

        The MEMHOSTREGISTER_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to MemHostGetDevicePointer because the memory may be mapped into other CUDA contexts via the MEMHOSTREGISTER_PORTABLE flag.

        For devices that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer ptr and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer ptr. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer ptr, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.

        The memory page-locked by this function must be unregistered with MemHostUnregister.

        Parameters:
        p - host pointer to memory to page-lock
        Flags - flags for allocation request. One or more of:
        MEMHOSTREGISTER_PORTABLEMEMHOSTREGISTER_DEVICEMAPMEMHOSTREGISTER_IOMEMORY
        MEMHOSTREGISTER_READ_ONLY
      • ncuMemHostUnregister

        public static int ncuMemHostUnregister​(long p)
        Unsafe version of: MemHostUnregister
      • cuMemHostUnregister

        public static int cuMemHostUnregister​(java.nio.ByteBuffer p)
        Unregisters a memory range that was registered with MemHostRegister.

        Unmaps the memory range whose base address is specified by p, and makes it pageable again.

        The base address must be the same one specified to MemHostRegister.

        Parameters:
        p - host pointer to memory to unregister
      • cuMemcpy

        public static int cuMemcpy​(long dst,
                                   long src,
                                   long ByteCount)
        Copies memory.

        Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

        Parameters:
        dst - destination unified virtual address space pointer
        src - source unified virtual address space pointer
        ByteCount - size of memory copy in bytes
      • cuMemcpyPeer

        public static int cuMemcpyPeer​(long dstDevice,
                                       long dstContext,
                                       long srcDevice,
                                       long srcContext,
                                       long ByteCount)
        Copies device memory between two contexts.

        Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        dstContext - destination context
        srcDevice - source device pointer
        srcContext - source context
        ByteCount - size of memory copy in bytes
      • ncuMemcpyHtoD

        public static int ncuMemcpyHtoD​(long dstDevice,
                                        long srcHost,
                                        long ByteCount)
        Unsafe version of: MemcpyHtoD
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyHtoD

        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.ByteBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.ShortBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.IntBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.LongBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.FloatBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       java.nio.DoubleBuffer srcHost)
        
        public static int cuMemcpyHtoD​(long dstDevice,
                                       org.lwjgl.PointerBuffer srcHost)
        
        Copies memory from Host to Device.

        Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        srcHost - source host pointer
      • ncuMemcpyDtoH

        public static int ncuMemcpyDtoH​(long dstHost,
                                        long srcDevice,
                                        long ByteCount)
        Unsafe version of: MemcpyDtoH
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyDtoH

        public static int cuMemcpyDtoH​(java.nio.ByteBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(java.nio.ShortBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(java.nio.IntBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(java.nio.LongBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(java.nio.FloatBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(java.nio.DoubleBuffer dstHost,
                                       long srcDevice)
        
        public static int cuMemcpyDtoH​(org.lwjgl.PointerBuffer dstHost,
                                       long srcDevice)
        
        Copies memory from Device to Host.

        Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstHost - destination host pointer
        srcDevice - source device pointer
      • cuMemcpyDtoD

        public static int cuMemcpyDtoD​(long dstDevice,
                                       long srcDevice,
                                       long ByteCount)
        Copies memory from Device to Device.

        Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        srcDevice - source device pointer
        ByteCount - size of memory copy in bytes
      • cuMemcpyDtoA

        public static int cuMemcpyDtoA​(long dstArray,
                                       long dstOffset,
                                       long srcDevice,
                                       long ByteCount)
        Copies memory from Device to Array.

        Copies from device memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting index of the destination data. srcDevice specifies the base pointer of the source. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstArray - destination array
        dstOffset - offset in bytes of destination array
        srcDevice - source device pointer
        ByteCount - size of memory copy in bytes
      • cuMemcpyAtoD

        public static int cuMemcpyAtoD​(long dstDevice,
                                       long srcArray,
                                       long srcOffset,
                                       long ByteCount)
        Copies memory from Array to Device.

        Copies from one 1D CUDA array to device memory. dstDevice specifies the base pointer of the destination and must be naturally aligned with the CUDA array elements. srcArray and srcOffset specify the CUDA array handle and the offset in bytes into the array where the copy is to begin. ByteCount specifies the number of bytes to copy and must be evenly divisible by the array element size.

        Parameters:
        dstDevice - destination device pointer
        srcArray - source array
        srcOffset - offset in bytes of source array
        ByteCount - size of memory copy in bytes
      • ncuMemcpyHtoA

        public static int ncuMemcpyHtoA​(long dstArray,
                                        long dstOffset,
                                        long srcHost,
                                        long ByteCount)
        Unsafe version of: MemcpyHtoA
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyHtoA

        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.ByteBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.ShortBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.IntBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.LongBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.FloatBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       java.nio.DoubleBuffer srcHost)
        
        public static int cuMemcpyHtoA​(long dstArray,
                                       long dstOffset,
                                       org.lwjgl.PointerBuffer srcHost)
        
        Copies memory from Host to Array.

        Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstArray - destination array
        dstOffset - offset in bytes of destination array
        srcHost - source host pointer
      • ncuMemcpyAtoH

        public static int ncuMemcpyAtoH​(long dstHost,
                                        long srcArray,
                                        long srcOffset,
                                        long ByteCount)
        Unsafe version of: MemcpyAtoH
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyAtoH

        public static int cuMemcpyAtoH​(java.nio.ByteBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(java.nio.ShortBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(java.nio.IntBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(java.nio.LongBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(java.nio.FloatBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(java.nio.DoubleBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        public static int cuMemcpyAtoH​(org.lwjgl.PointerBuffer dstHost,
                                       long srcArray,
                                       long srcOffset)
        
        Copies memory from Array to Host.

        Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstHost - destination device pointer
        srcArray - source array
        srcOffset - offset in bytes of source array
      • cuMemcpyAtoA

        public static int cuMemcpyAtoA​(long dstArray,
                                       long dstOffset,
                                       long srcArray,
                                       long srcOffset,
                                       long ByteCount)
        Copies memory from Array to Array.

        Copies from one 1D CUDA array to another. dstArray and srcArray specify the handles of the destination and source CUDA arrays for the copy, respectively. dstOffset and srcOffset specify the destination and source offsets in bytes into the CUDA arrays. ByteCount is the number of bytes to be copied. The size of the elements in the CUDA arrays need not be the same format, but the elements must be the same size; and count must be evenly divisible by that size.

        Parameters:
        dstArray - destination array
        dstOffset - offset in bytes of destination array
        srcArray - source array
        srcOffset - offset in bytes of source array
        ByteCount - size of memory copy in bytes
      • ncuMemcpy2D

        public static int ncuMemcpy2D​(long pCopy)
        Unsafe version of: Memcpy2D
      • cuMemcpy2D

        public static int cuMemcpy2D​(CUDA_MEMCPY2D pCopy)
        Copies memory for 2D arrays.

        Perform a 2D memory copy according to the parameters specified in pCopy.

        If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

        If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

        srcXInBytes and srcY specify the base address of the source data for the copy.

        For host pointers, the starting address is

        
         voidStart = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

        For device pointers, the starting address is

        
         CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

        For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

        dstXInBytes and dstY specify the base address of the destination data for the copy.

        For host pointers, the base address is

        
         voiddstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

        For device pointers, the starting address is

        
         CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

        For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

        WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        cuMemcpy2D() returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). cuMemAllocPitch() passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by MemAllocPitch. Memcpy2DUnaligned does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

        Parameters:
        pCopy - parameters for the memory copy
      • ncuMemcpy2DUnaligned

        public static int ncuMemcpy2DUnaligned​(long pCopy)
        Unsafe version of: Memcpy2DUnaligned
      • cuMemcpy2DUnaligned

        public static int cuMemcpy2DUnaligned​(CUDA_MEMCPY2D pCopy)
        Copies memory for 2D arrays.

        Perform a 2D memory copy according to the parameters specified in pCopy.

        If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

        If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

        srcXInBytes and srcY specify the base address of the source data for the copy.

        For host pointers, the starting address is

        
           void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

        For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

        dstXInBytes and dstY specify the base address of the destination data for the copy.

        For host pointers, the base address is

        
           void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

        For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

        WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        Memcpy2D returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). MemAllocPitch passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by cuMemAllocPitch(). cuMemcpy2DUnaligned() does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

        Parameters:
        pCopy - parameters for the memory copy
      • ncuMemcpy3D

        public static int ncuMemcpy3D​(long pCopy)
        Unsafe version of: Memcpy3D
      • cuMemcpy3D

        public static int cuMemcpy3D​(CUDA_MEMCPY3D pCopy)
        Copies memory for 3D arrays.

        Perform a 3D memory copy according to the parameters specified in pCopy.

        If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If srcMemoryType is MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

        If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

        srcXInBytes, srcY and srcZ specify the base address of the source data for the copy.

        For host pointers, the starting address is

        
           void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

        For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

        dstXInBytes, dstY and dstZ specify the base address of the destination data for the copy.

        For host pointers, the base address is

        
           void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

        For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

        WidthInBytes, Height and Depth specify the width (in bytes), height and depth of the 3D copy being performed.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

        Memcpy3D returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).

        The srcLOD and dstLOD members of the CUDA_MEMCPY3D structure must be set to 0.

        Note

        _sync

        Parameters:
        pCopy - parameters for the memory copy
      • ncuMemcpy3DPeer

        public static int ncuMemcpy3DPeer​(long pCopy)
        Unsafe version of: Memcpy3DPeer
      • cuMemcpy3DPeer

        public static int cuMemcpy3DPeer​(CUDA_MEMCPY3D_PEER pCopy)
        Copies memory between contexts.

        Perform a 3D memory copy according to the parameters specified in pCopy.

        Parameters:
        pCopy - parameters for the memory copy
      • cuMemcpyAsync

        public static int cuMemcpyAsync​(long dst,
                                        long src,
                                        long ByteCount,
                                        long hStream)
        Copies memory asynchronously.

        Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

        Parameters:
        dst - destination unified virtual address space pointer
        src - source unified virtual address space pointer
        ByteCount - size of memory copy in bytes
        hStream - stream identifier
      • cuMemcpyPeerAsync

        public static int cuMemcpyPeerAsync​(long dstDevice,
                                            long dstContext,
                                            long srcDevice,
                                            long srcContext,
                                            long ByteCount,
                                            long hStream)
        Copies device memory between two contexts asynchronously.

        Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        dstContext - destination context
        srcDevice - source device pointer
        srcContext - source context
        ByteCount - size of memory copy in bytes
        hStream - stream identifier
      • ncuMemcpyHtoDAsync

        public static int ncuMemcpyHtoDAsync​(long dstDevice,
                                             long srcHost,
                                             long ByteCount,
                                             long hStream)
        Unsafe version of: MemcpyHtoDAsync
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyHtoDAsync

        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.ByteBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.ShortBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.IntBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.LongBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.FloatBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            java.nio.DoubleBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoDAsync​(long dstDevice,
                                            org.lwjgl.PointerBuffer srcHost,
                                            long hStream)
        
        Copies memory from Host to Device.

        Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        srcHost - source host pointer
        hStream - stream identifier
      • ncuMemcpyDtoHAsync

        public static int ncuMemcpyDtoHAsync​(long dstHost,
                                             long srcDevice,
                                             long ByteCount,
                                             long hStream)
        Unsafe version of: MemcpyDtoHAsync
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyDtoHAsync

        public static int cuMemcpyDtoHAsync​(java.nio.ByteBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(java.nio.ShortBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(java.nio.IntBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(java.nio.LongBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(java.nio.FloatBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(java.nio.DoubleBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        public static int cuMemcpyDtoHAsync​(org.lwjgl.PointerBuffer dstHost,
                                            long srcDevice,
                                            long hStream)
        
        Copies memory from Device to Host.

        Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstHost - destination host pointer
        srcDevice - source device pointer
        hStream - stream identifier
      • cuMemcpyDtoDAsync

        public static int cuMemcpyDtoDAsync​(long dstDevice,
                                            long srcDevice,
                                            long ByteCount,
                                            long hStream)
        Copies memory from Device to Device.

        Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstDevice - destination device pointer
        srcDevice - source device pointer
        ByteCount - size of memory copy in bytes
        hStream - stream identifier
      • ncuMemcpyHtoAAsync

        public static int ncuMemcpyHtoAAsync​(long dstArray,
                                             long dstOffset,
                                             long srcHost,
                                             long ByteCount,
                                             long hStream)
        Unsafe version of: MemcpyHtoAAsync
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyHtoAAsync

        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.ByteBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.ShortBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.IntBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.LongBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.FloatBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            java.nio.DoubleBuffer srcHost,
                                            long hStream)
        
        public static int cuMemcpyHtoAAsync​(long dstArray,
                                            long dstOffset,
                                            org.lwjgl.PointerBuffer srcHost,
                                            long hStream)
        
        Copies memory from Host to Array.

        Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstArray - destination array
        dstOffset - offset in bytes of destination array
        srcHost - source host pointer
        hStream - stream identifier
      • ncuMemcpyAtoHAsync

        public static int ncuMemcpyAtoHAsync​(long dstHost,
                                             long srcArray,
                                             long srcOffset,
                                             long ByteCount,
                                             long hStream)
        Unsafe version of: MemcpyAtoHAsync
        Parameters:
        ByteCount - size of memory copy in bytes
      • cuMemcpyAtoHAsync

        public static int cuMemcpyAtoHAsync​(java.nio.ByteBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(java.nio.ShortBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(java.nio.IntBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(java.nio.LongBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(java.nio.FloatBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(java.nio.DoubleBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        public static int cuMemcpyAtoHAsync​(org.lwjgl.PointerBuffer dstHost,
                                            long srcArray,
                                            long srcOffset,
                                            long hStream)
        
        Copies memory from Array to Host.

        Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

        Parameters:
        dstHost - destination pointer
        srcArray - source array
        srcOffset - offset in bytes of source array
        hStream - stream identifier
      • ncuMemcpy2DAsync

        public static int ncuMemcpy2DAsync​(long pCopy,
                                           long hStream)
        Unsafe version of: Memcpy2DAsync
      • cuMemcpy2DAsync

        public static int cuMemcpy2DAsync​(CUDA_MEMCPY2D pCopy,
                                          long hStream)
        Copies memory for 2D arrays.

        Perform a 2D memory copy according to the parameters specified in pCopy.

        If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

        If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

        srcXInBytes and srcY specify the base address of the source data for the copy.

        For host pointers, the starting address is

        
           void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

        For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

        dstXInBytes and dstY specify the base address of the destination data for the copy.

        For host pointers, the base address is

        
           void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

        For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

        WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

        cuMemcpy2DAsync() returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). MemAllocPitch passes back pitches that always work with Memcpy2D. On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2DAsync() may fail for pitches not computed by cuMemAllocPitch().

        Parameters:
        pCopy - parameters for the memory copy
        hStream - stream identifier
      • ncuMemcpy3DAsync

        public static int ncuMemcpy3DAsync​(long pCopy,
                                           long hStream)
        Unsafe version of: Memcpy3DAsync
      • cuMemcpy3DAsync

        public static int cuMemcpy3DAsync​(CUDA_MEMCPY3D pCopy,
                                          long hStream)
        Copies memory for 3D arrays.

        Perform a 3D memory copy according to the parameters specified in pCopy.

        If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If srcMemoryType is MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

        If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

        If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

        If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

        If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

        - srcXInBytes, srcY and srcZ specify the base address of the source data for the copy.

        For host pointers, the starting address is

        
           void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

        For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

        dstXInBytes, dstY and dstZ specify the base address of the destination data for the copy.

        For host pointers, the base address is

        
           void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);

        For device pointers, the starting address is

        
           CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

        For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

        WidthInBytes, Height and Depth specify the width (in bytes), height and depth of the 3D copy being performed.

        If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

        If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

        Memcpy3DAsync returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).

        The srcLOD and dstLOD members of the CUDA_MEMCPY3D structure must be set to 0.

        Parameters:
        pCopy - parameters for the memory copy
        hStream - stream identifier
      • ncuMemcpy3DPeerAsync

        public static int ncuMemcpy3DPeerAsync​(long pCopy,
                                               long hStream)
        Unsafe version of: Memcpy3DPeerAsync
      • cuMemcpy3DPeerAsync

        public static int cuMemcpy3DPeerAsync​(CUDA_MEMCPY3D_PEER pCopy,
                                              long hStream)
        Copies memory between contexts asynchronously.

        Perform a 3D memory copy according to the parameters specified in pCopy.

        Parameters:
        pCopy - parameters for the memory copy
        hStream - stream identifier
      • cuMemsetD8

        public static int cuMemsetD8​(long dstDevice,
                                     byte uc,
                                     long N)
        Initializes device memory.

        Sets the memory range of N 8-bit values to the specified value uc.

        Parameters:
        dstDevice - destination device pointer
        uc - value to set
        N - number of elements
      • cuMemsetD16

        public static int cuMemsetD16​(long dstDevice,
                                      short us,
                                      long N)
        Initializes device memory.

        Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

        Parameters:
        dstDevice - destination device pointer
        us - value to set
        N - number of elements
      • cuMemsetD32

        public static int cuMemsetD32​(long dstDevice,
                                      int ui,
                                      long N)
        Initializes device memory

        Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

        Parameters:
        dstDevice - destination device pointer
        ui - value to set
        N - number of elements
      • cuMemsetD2D8

        public static int cuMemsetD2D8​(long dstDevice,
                                       long dstPitch,
                                       byte uc,
                                       long Width,
                                       long Height)
        Initializes device memory.

        Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        uc - value to set
        Width - width of row
        Height - number of rows
      • cuMemsetD2D16

        public static int cuMemsetD2D16​(long dstDevice,
                                        long dstPitch,
                                        short us,
                                        long Width,
                                        long Height)
        Initializes device memory.

        Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        us - value to set
        Width - width of row
        Height - number of rows
      • cuMemsetD2D32

        public static int cuMemsetD2D32​(long dstDevice,
                                        long dstPitch,
                                        int ui,
                                        long Width,
                                        long Height)
        Initializes device memory.

        Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        ui - value to set
        Width - width of row
        Height - number of rows
      • cuMemsetD8Async

        public static int cuMemsetD8Async​(long dstDevice,
                                          byte uc,
                                          long N,
                                          long hStream)
        Sets device memory

        Sets the memory range of N 8-bit values to the specified value uc.

        Parameters:
        dstDevice - destination device pointer
        uc - value to set
        N - number of elements
        hStream - stream identifier
      • cuMemsetD16Async

        public static int cuMemsetD16Async​(long dstDevice,
                                           short us,
                                           long N,
                                           long hStream)
        Sets device memory

        Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

        Parameters:
        dstDevice - destination device pointer
        us - value to set
        N - number of elements
        hStream - stream identifier
      • cuMemsetD32Async

        public static int cuMemsetD32Async​(long dstDevice,
                                           int ui,
                                           long N,
                                           long hStream)
        Sets device memory.

        Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

        Parameters:
        dstDevice - destination device pointer
        ui - value to set
        N - number of elements
        hStream - stream identifier
      • cuMemsetD2D8Async

        public static int cuMemsetD2D8Async​(long dstDevice,
                                            long dstPitch,
                                            byte uc,
                                            long Width,
                                            long Height,
                                            long hStream)
        Sets device memory.

        Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        uc - value to set
        Width - width of row
        Height - number of rows
        hStream - stream identifier
      • cuMemsetD2D16Async

        public static int cuMemsetD2D16Async​(long dstDevice,
                                             long dstPitch,
                                             short us,
                                             long Width,
                                             long Height,
                                             long hStream)
        Sets device memory.

        Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        us - value to set
        Width - width of row
        Height - number of rows
        hStream - stream identifier
      • cuMemsetD2D32Async

        public static int cuMemsetD2D32Async​(long dstDevice,
                                             long dstPitch,
                                             int ui,
                                             long Width,
                                             long Height,
                                             long hStream)
        Sets device memory.

        Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

        Parameters:
        dstDevice - destination device pointer
        dstPitch - pitch of destination device pointer(Unused if Height is 1)
        ui - value to set
        Width - width of row
        Height - number of rows
        hStream - stream identifier
      • ncuArrayCreate

        public static int ncuArrayCreate​(long pHandle,
                                         long pAllocateArray)
        Unsafe version of: ArrayCreate
      • cuArrayCreate

        public static int cuArrayCreate​(org.lwjgl.PointerBuffer pHandle,
                                        CUDA_ARRAY_DESCRIPTOR pAllocateArray)
        Creates a 1D or 2D CUDA array.

        Creates a CUDA array according to the CUDA_ARRAY_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in *pHandle.

        Parameters:
        pHandle - returned array
        pAllocateArray - array descriptor
      • ncuArrayGetDescriptor

        public static int ncuArrayGetDescriptor​(long pArrayDescriptor,
                                                long hArray)
        Unsafe version of: ArrayGetDescriptor
      • cuArrayGetDescriptor

        public static int cuArrayGetDescriptor​(CUDA_ARRAY_DESCRIPTOR pArrayDescriptor,
                                               long hArray)
        Get a 1D or 2D CUDA array descriptor.

        Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

        Parameters:
        pArrayDescriptor - returned array descriptor
        hArray - array to get descriptor of
      • ncuArrayGetSparseProperties

        public static int ncuArrayGetSparseProperties​(long sparseProperties,
                                                      long array)
        Unsafe version of: ArrayGetSparseProperties
      • ncuMipmappedArrayGetSparseProperties

        public static int ncuMipmappedArrayGetSparseProperties​(long sparseProperties,
                                                               long mipmap)
      • cuMipmappedArrayGetSparseProperties

        public static int cuMipmappedArrayGetSparseProperties​(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties,
                                                              long mipmap)
        Returns the layout properties of a sparse CUDA mipmapped array.

        Returns the sparse array layout properties in sparseProperties If the CUDA mipmapped array is not allocated with flag CUDA_ARRAY3D_SPARSE CUDA_ERROR_INVALID_VALUE will be returned.

        For non-layered CUDA mipmapped arrays, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize returns the size of the mip tail region. The mip tail region includes all mip levels whose width, height or depth is less than that of the tile. For layered CUDA mipmapped arrays, if CUDA_ARRAY_SPARSE_PROPERTIES::flags contains ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, then CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies the size of the mip tail of all layers combined. Otherwise, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies mip tail size per layer. The returned value of CUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevel is valid only if CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize is non-zero.

        Parameters:
        sparseProperties - pointer to CUDA_ARRAY_SPARSE_PROPERTIES
        mipmap - CUDA mipmapped array to get the sparse properties of
      • ncuArrayGetPlane

        public static int ncuArrayGetPlane​(long pPlaneArray,
                                           long hArray,
                                           int planeIdx)
        Unsafe version of: ArrayGetPlane
      • cuArrayGetPlane

        public static int cuArrayGetPlane​(org.lwjgl.PointerBuffer pPlaneArray,
                                          long hArray,
                                          int planeIdx)
        Gets a CUDA array plane from a CUDA array.

        Returns in pPlaneArray a CUDA array that represents a single format plane of the CUDA array hArray.

        If planeIdx is greater than the maximum number of planes in this array or if the array does not have a multi-planar format e.g: AD_FORMAT_NV12, then CUDA_ERROR_INVALID_VALUE is returned.

        Note that if the hArray has format AD_FORMAT_NV12, then passing in 0 for planeIdx returns a CUDA array of the same size as hArray but with one channel and AD_FORMAT_UNSIGNED_INT8 as its format. If 1 is passed for planeIdx, then the returned CUDA array has half the height and width of hArray with two channels and AD_FORMAT_UNSIGNED_INT8 as its format.

        Parameters:
        pPlaneArray - returned CUDA array referenced by the planeIdx
        hArray - multiplanar CUDA array
        planeIdx - plane index
      • cuArrayDestroy

        public static int cuArrayDestroy​(long hArray)
        Destroys a CUDA array.

        Destroys the CUDA array hArray.

        Parameters:
        hArray - array to destroy
      • ncuArray3DCreate

        public static int ncuArray3DCreate​(long pHandle,
                                           long pAllocateArray)
        Unsafe version of: Array3DCreate
      • cuArray3DCreate

        public static int cuArray3DCreate​(org.lwjgl.PointerBuffer pHandle,
                                          CUDA_ARRAY3D_DESCRIPTOR pAllocateArray)
        Creates a 3D CUDA array.

        Creates a CUDA array according to the CUDA_ARRAY3D_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in pHandle.

        • Width, Height, and Depth are the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:
          • A 1D array is allocated if Height and Depth extents are both zero.
          • A 2D array is allocated if only Depth extent is zero.
          • A 3D array is allocated if all three extents are non-zero.
          • A 1D layered CUDA array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent.
          • A 2D layered CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent.
          • A cubemap CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face.
          • A cubemap layered CUDA array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
        • Format specifies the format of the elements.
        • NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4;
        • Flags may be set to
          • CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array.
          • CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to the CUDA array. If this flag is not set, SurfRefSetArray will fail when attempting to bind the CUDA array to a surface reference.
          • CUDA_ARRAY3D_CUBEMAP to enable creation of cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six.
          • CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA array will be used for texture gather. Texture gather can only be performed on 2D CUDA arrays.

        Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_WIDTH refers to the device attribute DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH.

        Note that 2D CUDA arrays have different size requirements if the CUDA_ARRAY3D_TEXTURE_GATHER flag is set. Width and Height must not be greater than DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH and DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT respectively, in that case.

        CUDA array type Valid extents that must always be met
        {(width range in elements), (height range), (depth range)}
        Valid extents with CUDA_ARRAY3D_SURFACE_LDST set
        {(width range in elements), (height range), (depth range)}
        1D { (1,TEXTURE1D_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 }
        2D { (1,TEXTURE2D_WIDTH), (1,TEXTURE2D_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 }
        3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
        OR
        { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }
        { (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) }
        1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) }
        2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) }
        Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 }
        Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }
        Parameters:
        pHandle - returned array
        pAllocateArray - 3D array descriptor
      • ncuArray3DGetDescriptor

        public static int ncuArray3DGetDescriptor​(long pArrayDescriptor,
                                                  long hArray)
        Unsafe version of: Array3DGetDescriptor
      • cuArray3DGetDescriptor

        public static int cuArray3DGetDescriptor​(CUDA_ARRAY3D_DESCRIPTOR pArrayDescriptor,
                                                 long hArray)
        Get a 3D CUDA array descriptor.

        Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

        This function may be called on 1D and 2D arrays, in which case the Height and/or Depth members of the descriptor struct will be set to 0.

        Parameters:
        pArrayDescriptor - returned 3D array descriptor
        hArray - 3D array to get descriptor of
      • ncuMipmappedArrayCreate

        public static int ncuMipmappedArrayCreate​(long pHandle,
                                                  long pMipmappedArrayDesc,
                                                  int numMipmapLevels)
        Unsafe version of: MipmappedArrayCreate
      • cuMipmappedArrayCreate

        public static int cuMipmappedArrayCreate​(org.lwjgl.PointerBuffer pHandle,
                                                 CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc,
                                                 int numMipmapLevels)
        Creates a CUDA mipmapped array.

        Creates a CUDA mipmapped array according to the CUDA_ARRAY3D_DESCRIPTOR structure pMipmappedArrayDesc and returns a handle to the new CUDA mipmapped array in *pHandle. numMipmapLevels specifies the number of mipmap levels to be allocated. This value is clamped to the range [1, 1 + floor(log2(max(width, height, depth)))].

        • Width, Height, and Depth are the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:
          • A 1D mipmapped array is allocated if Height and Depth extents are both zero.
          • A 2D mipmapped array is allocated if only Depth extent is zero.
          • A 3D mipmapped array is allocated if all three extents are non-zero.
          • A 1D layered CUDA mipmapped array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent.
          • A 2D layered CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent.
          • A cubemap CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face.
          • A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
        • Format specifies the format of the elements.
        • NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4;
        • Flags may be set to:
          • CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA mipmapped arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array.
          • CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to individual mipmap levels of the CUDA mipmapped array. If this flag is not set, SurfRefSetArray will fail when attempting to bind a mipmap level of the CUDA mipmapped array to a surface reference.
          • CUDA_ARRAY3D_CUBEMAP to enable creation of mipmapped cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six.
          • CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA mipmapped array will be used for texture gather. Texture gather can only be performed on 2D CUDA mipmapped arrays.

        Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_MIPMAPPED_WIDTH refers to the device attribute DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH.

        CUDA array type Valid extents that must always be met
        {(width range in elements), (height range), (depth range)}
        Valid extents with CUDA_ARRAY3D_SURFACE_LDST set
        {(width range in elements), (height range), (depth range)}
        1D { (1,TEXTURE1D_MIPMAPPED_WIDTH), 0, 0 } { (1,SURFACE1D_WIDTH), 0, 0 }
        2D { (1,TEXTURE2D_MIPMAPPED_WIDTH), (1,TEXTURE2D_MIPMAPPED_HEIGHT), 0 } { (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 }
        3D { (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
        OR
        { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }
        { (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) }
        1D Layered { (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) } { (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) }
        2D Layered { (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) } { (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) }
        Cubemap { (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 } { (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 }
        Cubemap Layered { (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) } { (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }
        Parameters:
        pHandle - returned mipmapped array
        pMipmappedArrayDesc - mipmapped array descriptor
        numMipmapLevels - number of mipmap levels
      • ncuMipmappedArrayGetLevel

        public static int ncuMipmappedArrayGetLevel​(long pLevelArray,
                                                    long hMipmappedArray,
                                                    int level)
        Unsafe version of: MipmappedArrayGetLevel
      • cuMipmappedArrayGetLevel

        public static int cuMipmappedArrayGetLevel​(org.lwjgl.PointerBuffer pLevelArray,
                                                   long hMipmappedArray,
                                                   int level)
        Gets a mipmap level of a CUDA mipmapped array.

        Returns in *pLevelArray a CUDA array that represents a single mipmap level of the CUDA mipmapped array hMipmappedArray.

        If level is greater than the maximum number of levels in this mipmapped array, CUDA_ERROR_INVALID_VALUE is returned.

        Parameters:
        pLevelArray - returned mipmap level CUDA array
        hMipmappedArray - CUDA mipmapped array
        level - mipmap level
      • cuMipmappedArrayDestroy

        public static int cuMipmappedArrayDestroy​(long hMipmappedArray)
        Destroys a CUDA mipmapped array.

        Destroys the CUDA mipmapped array hMipmappedArray.

        Parameters:
        hMipmappedArray - mipmapped array to destroy
      • ncuMemAddressReserve

        public static int ncuMemAddressReserve​(long ptr,
                                               long size,
                                               long alignment,
                                               long addr,
                                               long flags)
        Unsafe version of: MemAddressReserve
      • cuMemAddressReserve

        public static int cuMemAddressReserve​(org.lwjgl.PointerBuffer ptr,
                                              long size,
                                              long alignment,
                                              long addr,
                                              long flags)
        Allocate an address range reservation.

        Reserves a virtual address range based on the given parameters, giving the starting address of the range in ptr. This API requires a system that supports UVA. The size and address parameters must be a multiple of the host page size and the alignment must be a power of two or zero for default alignment.

        Parameters:
        ptr - resulting pointer to start of virtual address range allocated
        size - size of the reserved virtual address range requested
        alignment - alignment of the reserved virtual address range requested
        addr - fixed starting address range requested
        flags - currently unused, must be zero
      • cuMemAddressFree

        public static int cuMemAddressFree​(long ptr,
                                           long size)
        Free an address range reservation.

        Frees a virtual address range reserved by MemAddressReserve. The size must match what was given to memAddressReserve and the ptr given must match what was returned from memAddressReserve.

        Parameters:
        ptr - starting address of the virtual address range to free
        size - size of the virtual address region to free
      • ncuMemCreate

        public static int ncuMemCreate​(long handle,
                                       long size,
                                       long prop,
                                       long flags)
        Unsafe version of: MemCreate
      • cuMemCreate

        public static int cuMemCreate​(java.nio.LongBuffer handle,
                                      long size,
                                      CUmemAllocationProp prop,
                                      long flags)
        Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.

        This creates a memory allocation on the target device specified through the prop strcuture. The created allocation will not have any device or host mappings. The generic memory handle for the allocation can be mapped to the address space of calling process via MemMap. This handle cannot be transmitted directly to other processes (see MemExportToShareableHandle). On Windows, the caller must also pass an LPSECURITYATTRIBUTE in prop to be associated with this handle which limits or allows access to this handle for a recepient process (see CUmemAllocationProp::win32HandleMetaData for more). The size of this allocation must be a multiple of the the value given via MemGetAllocationGranularity with the MEM_ALLOC_GRANULARITY_MINIMUM flag. If CUmemAllocationProp::allocFlags::usage contains MEM_CREATE_USAGE_TILE_POOL flag then the memory allocation is intended only to be used as backing tile pool for sparse CUDA arrays and sparse CUDA mipmapped arrays. (see MemMapArrayAsync).

        Parameters:
        handle - value of handle returned. All operations on this allocation are to be performed using this handle.
        size - size of the allocation requested
        prop - properties of the allocation to create
        flags - flags for future use, must be zero now
      • cuMemRelease

        public static int cuMemRelease​(long handle)
        Release a memory handle representing a memory allocation which was previously allocated through MemCreate.

        Frees the memory that was allocated on a device through cuMemCreate.

        The memory allocation will be freed when all outstanding mappings to the memory are unmapped and when all outstanding references to the handle (including it's shareable counterparts) are also released. The generic memory handle can be freed when there are still outstanding mappings made with this handle. Each time a recepient process imports a shareable handle, it needs to pair it with MemRelease for the handle to be freed. If handle is not a valid handle the behavior is undefined.

        Parameters:
        handle - value of handle which was returned previously by cuMemCreate
      • cuMemMap

        public static int cuMemMap​(long ptr,
                                   long size,
                                   long offset,
                                   long handle,
                                   long flags)
        Maps an allocation handle to a reserved virtual address range.

        Maps bytes of memory represented by handle starting from byte offset to size to address range [ addr, addr + size]. This range must be an address reservation previously reserved with MemAddressReserve, and offset + size must be less than the size of the memory allocation. Both ptr, size, and offset must be a multiple of the value given via MemGetAllocationGranularity with the MEM_ALLOC_GRANULARITY_MINIMUM flag.

        Please note calling MemMap does not make the address accessible, the caller needs to update accessibility of a contiguous mapped VA range by calling MemSetAccess.

        Once a recipient process obtains a shareable memory handle from MemImportFromShareableHandle, the process must use MemMap to map the memory into its address ranges before setting accessibility with MemSetAccess.

        MemMap can only create mappings on VA range reservations that are not currently mapped.

        Parameters:
        ptr - address where memory will be mapped
        size - size of the memory mapping
        offset - offset into the memory represented by - handle from which to start mapping - Note: currently must be zero
        handle - handle to a shareable memory
        flags - flags for future use, must be zero now
      • ncuMemMapArrayAsync

        public static int ncuMemMapArrayAsync​(long mapInfoList,
                                              int count,
                                              long hStream)
        Unsafe version of: MemMapArrayAsync
        Parameters:
        count - count of CUarrayMapInfo in mapInfoList
      • cuMemMapArrayAsync

        public static int cuMemMapArrayAsync​(CUarrayMapInfo.Buffer mapInfoList,
                                             long hStream)
        Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.

        Performs map or unmap operations on subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays. Each operation is specified by a CUarrayMapInfo entry in the mapInfoList array of size count.

        where CUarrayMapInfo::resourceType specifies the type of resource to be operated on. If CUarrayMapInfo::resourceType is set to RESOURCE_TYPE_ARRAY then CUarrayMapInfo::resource::array must be set to a valid sparse CUDA array handle. The CUDA array must be either a 2D, 2D layered or 3D CUDA array and must have been allocated using ArrayCreate or Array3DCreate with the flag CUDA_ARRAY3D_SPARSE. For CUDA arrays obtained using MipmappedArrayGetLevel, CUDA_ERROR_INVALID_VALUE will be returned. If CUarrayMapInfo::resourceType is set to RESOURCE_TYPE_MIPMAPPED_ARRAY then CUarrayMapInfo::resource::mipmap must be set to a valid sparse CUDA mipmapped array handle. The CUDA mipmapped array must be either a 2D, 2D layered or 3D CUDA mipmapped array and must have been allocated using MipmappedArrayCreate with the flag CUDA_ARRAY3D_SPARSE.

        CUarrayMapInfo::subresourceType specifies the type of subresource within the resource.

        where ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL indicates a sparse-miplevel which spans at least one tile in every dimension. The remaining miplevels which are too small to span at least one tile in any dimension constitute the mip tail region as indicated by ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL subresource type.

        If CUarrayMapInfo::subresourceType is set to ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL then CUarrayMapInfo::subresource::sparseLevel struct must contain valid array subregion offsets and extents. The CUarrayMapInfo::subresource::sparseLevel::offsetX, CUarrayMapInfo::subresource::sparseLevel::offsetY and CUarrayMapInfo::subresource::sparseLevel::offsetZ must specify valid X, Y and Z offsets respectively. The CUarrayMapInfo::subresource::sparseLevel::extentWidth, CUarrayMapInfo::subresource::sparseLevel::extentHeight and CUarrayMapInfo::subresource::sparseLevel::extentDepth must specify valid width, height and depth extents respectively. These offsets and extents must be aligned to the corresponding tile dimension. For CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::level must specify a valid mip level index. Otherwise, must be zero. For layered CUDA arrays and layered CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::layer must specify a valid layer index. Otherwise, must be zero. CUarrayMapInfo::subresource::sparseLevel::offsetZ must be zero and CUarrayMapInfo::subresource::sparseLevel::extentDepth must be set to 1 for 2D and 2D layered CUDA arrays and CUDA mipmapped arrays. Tile extents can be obtained by calling ArrayGetSparseProperties and MipmappedArrayGetSparseProperties

        If CUarrayMapInfo::subresourceType is set to ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL then CUarrayMapInfo::subresource::miptail struct must contain valid mip tail offset in CUarrayMapInfo::subresource::miptail::offset and size in CUarrayMapInfo::subresource::miptail::size. Both, mip tail offset and mip tail size must be aligned to the tile size. For layered CUDA mipmapped arrays which don't have the flag ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL set in CUDA_ARRAY_SPARSE_PROPERTIES::flags as returned by MipmappedArrayGetSparseProperties, CUarrayMapInfo::subresource::miptail::layer must specify a valid layer index. Otherwise, must be zero.

        CUarrayMapInfo::memOperationType specifies the type of operation.

        If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_MAP then the subresource will be mapped onto the tile pool memory specified by CUarrayMapInfo::memHandle at offset CUarrayMapInfo::offset. The tile pool allocation has to be created by specifying the MEM_CREATE_USAGE_TILE_POOL flag when calling MemCreate. Also, CUarrayMapInfo::memHandleType must be set to MEM_HANDLE_TYPE_GENERIC.

        If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_UNMAP then an unmapping operation is performed. CUarrayMapInfo::memHandle must be NULL.

        CUarrayMapInfo::deviceBitMask specifies the list of devices that must map or unmap physical memory. Currently, this mask must have exactly one bit set, and the corresponding device must match the device associated with the stream. If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_MAP, the device must also match the device associated with the tile pool memory allocation as specified by CUarrayMapInfo::memHandle.

        CUarrayMapInfo::flags and CUarrayMapInfo::reserved[] are unused and must be set to zero.

        Parameters:
        mapInfoList - list of CUarrayMapInfo
        hStream - stream identifier for the stream to use for map or unmap operations
      • cuMemUnmap

        public static int cuMemUnmap​(long ptr,
                                     long size)
        Unmap the backing memory of a given address range.

        The range must be the entire contiguous address range that was mapped to. In other words, MemUnmap cannot unmap a sub-range of an address range mapped by MemCreate / MemMap. Any backing memory allocations will be freed if there are no existing mappings and there are no unreleased memory handles.

        When MemUnmap returns successfully the address range is converted to an address reservation and can be used for a future calls to MemMap. Any new mapping to this virtual address will need to have access granted through MemSetAccess, as all mappings start with no accessibility setup.

        Parameters:
        ptr - starting address for the virtual address range to unmap
        size - size of the virtual address range to unmap
      • ncuMemSetAccess

        public static int ncuMemSetAccess​(long ptr,
                                          long size,
                                          long desc,
                                          long count)
        Unsafe version of: MemSetAccess
        Parameters:
        count - number of CUmemAccessDesc in desc
      • cuMemSetAccess

        public static int cuMemSetAccess​(long ptr,
                                         long size,
                                         CUmemAccessDesc.Buffer desc)
        Set the access flags for each location specified in desc for the given virtual address range.

        Given the virtual address range via ptr and size, and the locations in the array given by desc and count, set the access flags for the target locations. The range must be a fully mapped address range containing all allocations created by MemMap / MemCreate.

        Parameters:
        ptr - starting address for the virtual address range
        size - length of the virtual address range
        desc - array of CUmemAccessDesc that describe how to change the - mapping for each location specified
      • ncuMemGetAccess

        public static int ncuMemGetAccess​(long flags,
                                          long location,
                                          long ptr)
        Unsafe version of: MemGetAccess
      • cuMemGetAccess

        public static int cuMemGetAccess​(java.nio.LongBuffer flags,
                                         CUmemLocation location,
                                         long ptr)
        Get the access flags set for the given location and ptr.
        Parameters:
        flags - flags set for this location
        location - location in which to check the flags for
        ptr - address in which to check the access flags for
      • ncuMemExportToShareableHandle

        public static int ncuMemExportToShareableHandle​(long shareableHandle,
                                                        long handle,
                                                        int handleType,
                                                        long flags)
        Unsafe version of: MemExportToShareableHandle
      • cuMemExportToShareableHandle

        public static int cuMemExportToShareableHandle​(java.nio.ByteBuffer shareableHandle,
                                                       long handle,
                                                       int handleType,
                                                       long flags)
        
        public static int cuMemExportToShareableHandle​(org.lwjgl.PointerBuffer shareableHandle,
                                                       long handle,
                                                       int handleType,
                                                       long flags)
        
        Exports an allocation to a requested shareable handle type.

        Given a CUDA memory handle, create a shareable memory allocation handle that can be used to share the memory with other processes. The recipient process can convert the shareable handle back into a CUDA memory handle using MemImportFromShareableHandle and map it with MemMap. The implementation of what this handle is and how it can be transferred is defined by the requested handle type in handleType.

        Once all shareable handles are closed and the allocation is released, the allocated memory referenced will be released back to the OS and uses of the CUDA handle afterward will lead to undefined behavior.

        This API can also be used in conjunction with other APIs (e.g. Vulkan, OpenGL) that support importing memory from the shareable type

        Parameters:
        shareableHandle - pointer to the location in which to store the requested handle type
        handle - CUDA handle for the memory allocation
        handleType - type of shareable handle requested (defines type and size of the shareableHandle output parameter)
        flags - reserved, must be zero
      • ncuMemImportFromShareableHandle

        public static int ncuMemImportFromShareableHandle​(long handle,
                                                          long osHandle,
                                                          int shHandleType)
        Unsafe version of: MemImportFromShareableHandle
      • cuMemImportFromShareableHandle

        public static int cuMemImportFromShareableHandle​(java.nio.LongBuffer handle,
                                                         long osHandle,
                                                         int shHandleType)
        Imports an allocation from a requested shareable handle type.

        If the current process cannot support the memory described by this shareable handle, this API will error as CUDA_ERROR_NOT_SUPPORTED.

        Note

        Importing shareable handles exported from some graphics APIs(VUlkan, OpenGL, etc) created on devices under an SLI group may not be supported, and thus this API will return CUDA_ERROR_NOT_SUPPORTED. There is no guarantee that the contents of handle will be the same CUDA memory handle for the same given OS shareable handle, or the same underlying allocation.

        Parameters:
        handle - CUDA Memory handle for the memory allocation
        osHandle - shareable Handle representing the memory allocation that is to be imported
        shHandleType - handle type of the exported handle CUmemAllocationHandleType
      • ncuMemGetAllocationGranularity

        public static int ncuMemGetAllocationGranularity​(long granularity,
                                                         long prop,
                                                         int option)
        Unsafe version of: MemGetAllocationGranularity
      • cuMemGetAllocationGranularity

        public static int cuMemGetAllocationGranularity​(org.lwjgl.PointerBuffer granularity,
                                                        CUmemAllocationProp prop,
                                                        int option)
        Calculates either the minimal or recommended granularity.

        Calculates either the minimal or recommended granularity for a given allocation specification and returns it in granularity. This granularity can be used as a multiple for alignment, size, or address mapping.

        Parameters:
        granularity - returned granularity
        prop - property for which to determine the granularity for
        option - determines which granularity to return
      • ncuMemGetAllocationPropertiesFromHandle

        public static int ncuMemGetAllocationPropertiesFromHandle​(long prop,
                                                                  long handle)
      • cuMemGetAllocationPropertiesFromHandle

        public static int cuMemGetAllocationPropertiesFromHandle​(CUmemAllocationProp prop,
                                                                 long handle)
        Retrieve the contents of the property structure defining properties for this handle.
        Parameters:
        prop - pointer to a properties structure which will hold the information about this handle
        handle - handle which to perform the query on
      • ncuMemRetainAllocationHandle

        public static int ncuMemRetainAllocationHandle​(long handle,
                                                       long addr)
        Unsafe version of: MemRetainAllocationHandle
      • cuMemRetainAllocationHandle

        public static int cuMemRetainAllocationHandle​(java.nio.LongBuffer handle,
                                                      java.nio.ByteBuffer addr)
        Given an address addr, returns the allocation handle of the backing memory allocation.

        The handle is guaranteed to be the same handle value used to map the memory. If the address requested is not mapped, the function will fail. The returned handle must be released with corresponding number of calls to MemRelease.

        Note

        The address addr, can be any address in a range previously mapped by MemMap, and not necessarily the start address.

        Parameters:
        handle - CUDA Memory handle for the backing memory allocation
        addr - memory address to query, that has been mapped previously
      • cuMemFreeAsync

        public static int cuMemFreeAsync​(long dptr,
                                         long hStream)
        Frees memory with stream ordered semantics.

        Inserts a free operation into hStream. The allocation must not be accessed after stream execution reaches the free. After this API returns, accessing the memory from any subsequent work launched on the GPU or querying its pointer attributes results in undefined behavior.

        Note

        During stream capture, this function results in the creation of a free node and must therefore be passed the address of a graph allocation.

        Parameters:
        dptr - memory to free
        hStream - the stream establishing the stream ordering contract
      • ncuMemAllocAsync

        public static int ncuMemAllocAsync​(long dptr,
                                           long bytesize,
                                           long hStream)
        Unsafe version of: MemAllocAsync
      • cuMemAllocAsync

        public static int cuMemAllocAsync​(org.lwjgl.PointerBuffer dptr,
                                          long bytesize,
                                          long hStream)
        Allocates memory with stream ordered semantics

        Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the memory pool current to the stream's device.

        Note

        The default memory pool of a device contains device memory from that device.

        Note

        Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.

        Note

        During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.

        Parameters:
        dptr - returned device pointer
        bytesize - number of bytes to allocate
        hStream - the stream establishing the stream ordering contract and the memory pool to allocate from
      • cuMemPoolTrimTo

        public static int cuMemPoolTrimTo​(long pool,
                                          long minBytesToKeep)
        Tries to release memory back to the OS.

        Releases memory back to the OS until the pool contains fewer than minBytesToKeep reserved bytes, or there is no more memory that the allocator can safely release. The allocator cannot release OS allocations that back outstanding asynchronous allocations. The OS allocations may happen at different granularity from the user allocations.

        Note

        Allocations that have not been freed count as outstanding.

        Note

        Allocations that have been asynchronously freed but whose completion has not been observed on the host (eg. by a synchronize) can count as outstanding.

        Parameters:
        pool - the memory pool to trim
        minBytesToKeep - if the pool has less than minBytesToKeep reserved, the TrimTo operation is a no-op. Otherwise the pool will be guaranteed to have at least minBytesToKeep bytes reserved after the operation.
      • ncuMemPoolSetAttribute

        public static int ncuMemPoolSetAttribute​(long pool,
                                                 int attr,
                                                 long value)
        Unsafe version of: MemPoolSetAttribute
      • ncuMemPoolGetAttribute

        public static int ncuMemPoolGetAttribute​(long pool,
                                                 int attr,
                                                 long value)
        Unsafe version of: MemPoolGetAttribute
      • ncuMemPoolSetAccess

        public static int ncuMemPoolSetAccess​(long pool,
                                              long map,
                                              long count)
        Unsafe version of: MemPoolSetAccess
        Parameters:
        count - number of descriptors in the map array
      • cuMemPoolSetAccess

        public static int cuMemPoolSetAccess​(long pool,
                                             CUmemAccessDesc.Buffer map)
        Controls visibility of pools between devices.
        Parameters:
        pool - the pool being modified
        map - array of access descriptors. Each descriptor instructs the access to enable for a single gpu.
      • ncuMemPoolGetAccess

        public static int ncuMemPoolGetAccess​(long flags,
                                              long memPool,
                                              long location)
        Unsafe version of: MemPoolGetAccess
      • cuMemPoolGetAccess

        public static int cuMemPoolGetAccess​(java.nio.IntBuffer flags,
                                             long memPool,
                                             CUmemLocation location)
        Returns the accessibility of a pool from a device.

        Returns the accessibility of the pool's memory from the specified location.

        Parameters:
        flags - the accessibility of the pool from the specified location
        memPool - the pool being queried
        location - the location accessing the pool
      • ncuMemPoolCreate

        public static int ncuMemPoolCreate​(long pool,
                                           long poolProps)
        Unsafe version of: MemPoolCreate
      • cuMemPoolCreate

        public static int cuMemPoolCreate​(org.lwjgl.PointerBuffer pool,
                                          CUmemPoolProps poolProps)
        Creates a memory pool.

        Creates a CUDA memory pool and returns the handle in pool. The poolProps determines the properties of the pool such as the backing device and IPC capabilities.

        By default, the pool's memory will be accessible from the device it is allocated on.

        Note

        Specifying MEM_HANDLE_TYPE_NONE creates a memory pool that will not support IPC.

      • cuMemPoolDestroy

        public static int cuMemPoolDestroy​(long pool)
        Destroys the specified memory pool.

        If any pointers obtained from this pool haven't been freed or the pool has free operations that haven't completed when MemPoolDestroy is invoked, the function will return immediately and the resources associated with the pool will be released automatically once there are no more outstanding allocations.

        Destroying the current mempool of a device sets the default mempool of that device as the current mempool for that device.

        Note

        A device's default memory pool cannot be destroyed.

      • ncuMemAllocFromPoolAsync

        public static int ncuMemAllocFromPoolAsync​(long dptr,
                                                   long bytesize,
                                                   long pool,
                                                   long hStream)
        Unsafe version of: MemAllocFromPoolAsync
      • cuMemAllocFromPoolAsync

        public static int cuMemAllocFromPoolAsync​(org.lwjgl.PointerBuffer dptr,
                                                  long bytesize,
                                                  long pool,
                                                  long hStream)
        Allocates memory from a specified pool with stream ordered semantics.

        Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the specified memory pool.

        Note

        The specified memory pool may be from a device different than that of the specified hStream.

        • Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.
        Note

        During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.

        Parameters:
        dptr - returned device pointer
        bytesize - number of bytes to allocate
        pool - the pool to allocate from
        hStream - the stream establishing the stream ordering semantic
      • ncuMemPoolExportToShareableHandle

        public static int ncuMemPoolExportToShareableHandle​(long handle_out,
                                                            long pool,
                                                            int handleType,
                                                            long flags)
      • cuMemPoolExportToShareableHandle

        public static int cuMemPoolExportToShareableHandle​(java.nio.ByteBuffer handle_out,
                                                           long pool,
                                                           int handleType,
                                                           long flags)
        
        public static int cuMemPoolExportToShareableHandle​(org.lwjgl.PointerBuffer handle_out,
                                                           long pool,
                                                           int handleType,
                                                           long flags)
        
        Exports a memory pool to the requested handle type.

        Given an IPC capable mempool, create an OS handle to share the pool with another process. A recipient process can convert the shareable handle into a mempool with MemPoolImportFromShareableHandle. Individual pointers can then be shared with the MemPoolExportPointer and MemPoolImportPointer APIs. The implementation of what the shareable handle is and how it can be transferred is defined by the requested handle type.

        Note

        To create an IPC capable mempool, create a mempool with a CUmemAllocationHandleType other than MEM_HANDLE_TYPE_NONE.

        Parameters:
        handle_out - returned OS handle
        pool - pool to export
        handleType - the type of handle to create
        flags - must be 0
      • ncuMemPoolImportFromShareableHandle

        public static int ncuMemPoolImportFromShareableHandle​(long pool_out,
                                                              long handle,
                                                              int handleType,
                                                              long flags)
      • cuMemPoolImportFromShareableHandle

        public static int cuMemPoolImportFromShareableHandle​(org.lwjgl.PointerBuffer pool_out,
                                                             java.nio.ByteBuffer handle,
                                                             int handleType,
                                                             long flags)
        
        public static int cuMemPoolImportFromShareableHandle​(org.lwjgl.PointerBuffer pool_out,
                                                             org.lwjgl.PointerBuffer handle,
                                                             int handleType,
                                                             long flags)
        
        Imports a memory pool from a shared handle.

        Specific allocations can be imported from the imported pool with MemPoolImportPointer.

        Note

        Imported memory pools do not support creating new allocations. As such imported memory pools may not be used in DeviceSetMemPool or MemAllocFromPoolAsync calls.

        Parameters:
        pool_out - returned memory pool
        handle - OS handle of the pool to open
        handleType - the type of handle being imported
        flags - must be 0
      • ncuMemPoolExportPointer

        public static int ncuMemPoolExportPointer​(long shareData_out,
                                                  long ptr)
        Unsafe version of: MemPoolExportPointer
      • cuMemPoolExportPointer

        public static int cuMemPoolExportPointer​(CUmemPoolPtrExportData shareData_out,
                                                 long ptr)
        Export data to share a memory pool allocation between processes.

        Constructs shareData_out for sharing a specific allocation from an already shared memory pool. The recipient process can import the allocation with the MemPoolImportPointer api. The data is not a handle and may be shared through any IPC mechanism.

        Parameters:
        shareData_out - returned export data
        ptr - pointer to memory being exported
      • ncuMemPoolImportPointer

        public static int ncuMemPoolImportPointer​(long ptr_out,
                                                  long pool,
                                                  long shareData)
        Unsafe version of: MemPoolImportPointer
      • cuMemPoolImportPointer

        public static int cuMemPoolImportPointer​(org.lwjgl.PointerBuffer ptr_out,
                                                 long pool,
                                                 CUmemPoolPtrExportData shareData)
        Import a memory pool allocation from another process.

        Returns in ptr_out a pointer to the imported memory. The imported memory must not be accessed before the allocation operation completes in the exporting process. The imported memory must be freed from all importing processes before being freed in the exporting process. The pointer may be freed with MemFree or MemFreeAsync. If cuMemFreeAsync is used, the free must be completed on the importing process before the free operation on the exporting process.

        Note

        The cuMemFreeAsync api may be used in the exporting process before the cuMemFreeAsync operation completes in its stream as long as the cuMemFreeAsync in the exporting process specifies a stream with a stream dependency on the importing process's cuMemFreeAsync.

        Parameters:
        ptr_out - pointer to imported memory
        pool - pool from which to import
        shareData - data specifying the memory to import
      • ncuPointerGetAttribute

        public static int ncuPointerGetAttribute​(long data,
                                                 int attribute,
                                                 long ptr)
        Unsafe version of: PointerGetAttribute
      • cuPointerGetAttribute

        public static int cuPointerGetAttribute​(java.nio.ByteBuffer data,
                                                int attribute,
                                                long ptr)
        
        public static int cuPointerGetAttribute​(org.lwjgl.PointerBuffer data,
                                                int attribute,
                                                long ptr)
        
        public static int cuPointerGetAttribute​(java.nio.IntBuffer data,
                                                int attribute,
                                                long ptr)
        
        public static int cuPointerGetAttribute​(java.nio.LongBuffer data,
                                                int attribute,
                                                long ptr)
        
        Returns information about a pointer.

        The supported attributes are:

        • POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in which ptr was allocated or registered. The type of data must be CUcontext *.

          If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

        • POINTER_ATTRIBUTE_MEMORY_TYPE:

          Returns in *data the physical memory type of the memory that ptr addresses as a CUmemorytype enumerated value. The type of data must be unsigned int.

          If ptr addresses device memory then *data is set to MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the POINTER_ATTRIBUTE_CONTEXT attribute of ptr.

          If ptr addresses host memory then *data is set to MEMORYTYPE_HOST.

          If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

          If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned.

        • POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in *data the device pointer value through which ptr may be accessed by kernels running in the current CUcontext. The type of data must be CUdeviceptr *.

          If there exists no device pointer value through which kernels running in the current CUcontext may access ptr then CUDA_ERROR_INVALID_VALUE is returned.

          If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned.

          Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

        • POINTER_ATTRIBUTE_HOST_POINTER: Returns in *data the host pointer value through which ptr may be accessed by by the host program. The type of data must be void **. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned.

          Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

        • POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.

          ptr must be a pointer to memory obtained from MemAlloc. Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to.

        • POINTER_ATTRIBUTE_SYNC_MEMOPS:

          A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.

        • POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long.

          ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.

        • POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not.

          If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned.

        • POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered.
        • POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle().
        • POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from MemAddressReserve).
        • POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from MemAddressReserve). To retrieve the size of the mapped region, see MemGetAddressRange.
        • POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.
        • POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to MemExportToShareableHandle.
        • POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

        Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using MemHostRegister - host memory allocated using MemHostAlloc with the MEMHOSTALLOC_WRITECOMBINED flag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular

        • The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
        • The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).

        For these types of allocations, querying POINTER_ATTRIBUTE_HOST_POINTER and POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host and device addresses from either address.

        Parameters:
        data - returned pointer attribute value
        attribute - pointer attribute to query
        ptr - pointer
      • cuMemPrefetchAsync

        public static int cuMemPrefetchAsync​(long devPtr,
                                             long count,
                                             int dstDevice,
                                             long hStream)
        Prefetches memory to the specified destination device,

        Prefetches memory to the specified destination device. devPtr is the base device pointer of the memory to be prefetched and dstDevice is the destination device. count specifies the number of bytes to copy. hStream is the stream in which the operation is enqueued. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables.

        Passing in DEVICE_CPU for dstDevice will prefetch the data to host memory. If dstDevice is a GPU, then the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. Additionally, hStream must be associated with a device that has a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS.

        The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the prefetch operation is enqueued in the stream.

        If no physical memory has been allocated for this region, then this memory region will be populated and mapped on the destination device. If there's insufficient memory to prefetch the desired region, the Unified Memory driver may evict pages from other MemAllocManaged allocations to host memory in order to make room. Device memory allocated using MemAlloc or ArrayCreate will not be evicted.

        By default, any mappings to the previous location of the migrated pages are removed and mappings for the new location are only setup on dstDevice. The exact behavior however also depends on the settings applied to this memory range via MemAdvise as described below:

        If MEM_ADVISE_SET_READ_MOSTLY was set on any subset of this memory range, then that subset will create a read-only copy of the pages on dstDevice.

        If MEM_ADVISE_SET_PREFERRED_LOCATION was called on any subset of this memory range, then the pages will be migrated to dstDevice even if dstDevice is not the preferred location of any pages in the memory range.

        If MEM_ADVISE_SET_ACCESSED_BY was called on any subset of this memory range, then mappings to those pages from all the appropriate processors are updated to refer to the new location if establishing such a mapping is possible. Otherwise, those mappings are cleared.

        Note that this API is not required for functionality and only serves to improve performance by allowing the application to migrate data to a suitable location before it is accessed. Memory accesses to this range are always coherent and are allowed even when the data is actively being migrated.

        Note that this function is asynchronous with respect to the host and all work on other devices.

        Parameters:
        devPtr - pointer to be prefetched
        count - size in bytes
        dstDevice - destination device to prefetch to
        hStream - stream to enqueue prefetch operation
      • cuMemAdvise

        public static int cuMemAdvise​(long devPtr,
                                      long count,
                                      int advice,
                                      int device)
        Advise about the usage of a given memory range.

        Advise the Unified Memory subsystem about the usage pattern for the memory range starting at devPtr with a size of count bytes. The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the advice is applied. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables. The memory range could also refer to system-allocated pageable memory provided it represents a valid, host-accessible region of memory and all additional constraints imposed by advice as outlined below are also satisfied. Specifying an invalid system-allocated pageable memory range results in an error being returned.

        The advice parameter can take the following values:

        • MEM_ADVISE_SET_READ_MOSTLY: This implies that the data is mostly going to be read from and only occasionally written to. Any read accesses from any processor to this region will create a read-only copy of at least the accessed pages in that processor's memory. Additionally, if MemPrefetchAsync is called on this region, it will create a read-only copy of the data on the destination processor. If any processor writes to this region, all copies of the corresponding page will be invalidated except for the one where the write occurred. The device argument is ignored for this advice. Note that for a page to be read-duplicated, the accessing processor must either be the CPU or a GPU that has a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Also, if a context is created on a device that does not have the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS set, then read-duplication will not occur until all such contexts are destroyed. If the memory region refers to valid system-allocated pageable memory, then the accessing device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS for a read-only copy to be created on that device. Note however that if the accessing device also has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then setting this advice will not create a read-only copy when that device accesses this memory region.
        • MEM_ADVISE_UNSET_READ_MOSTLY: Undoes the effect of MEM_ADVISE_SET_READ_MOSTLY and also prevents the Unified Memory driver from attempting heuristic read-duplication on the memory range. Any read-duplicated copies of the data will be collapsed into a single copy. The location for the collapsed copy will be the preferred location if the page has a preferred location and one of the read-duplicated copies was resident at that location. Otherwise, the location chosen is arbitrary.
        • MEM_ADVISE_SET_PREFERRED_LOCATION: This advice sets the preferred location for the data to be the memory belonging to device. Passing in CU_DEVICE_CPU for device sets the preferred location as host memory. If device is a GPU, then it must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Setting the preferred location does not cause data to migrate to that location immediately. Instead, it guides the migration policy when a fault occurs on that memory region. If the data is already in its preferred location and the faulting processor can establish a mapping without requiring the data to be migrated, then data migration will be avoided. On the other hand, if the data is not in its preferred location or if a direct mapping cannot be established, then it will be migrated to the processor accessing it. It is important to note that setting the preferred location does not prevent data prefetching done using MemPrefetchAsync. Having a preferred location can override the page thrash detection and resolution logic in the Unified Memory driver. Normally, if a page is detected to be constantly thrashing between for example host and device memory, the page may eventually be pinned to host memory by the Unified Memory driver. But if the preferred location is set as device memory, then the page will continue to thrash indefinitely. If MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice, unless read accesses from device will not result in a read-only copy being created on that device as outlined in description for the advice MEM_ADVISE_SET_READ_MOSTLY. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect. Note however that this behavior may change in the future.
        • MEM_ADVISE_UNSET_PREFERRED_LOCATION: Undoes the effect of MEM_ADVISE_SET_PREFERRED_LOCATION and changes the preferred location to none.
        • MEM_ADVISE_SET_ACCESSED_BY: This advice implies that the data will be accessed by device. Passing in DEVICE_CPU for device will set the advice for the CPU. If device is a GPU, then the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. This advice does not cause data migration and has no impact on the location of the data per se. Instead, it causes the data to always be mapped in the specified processor's page tables, as long as the location of the data permits a mapping to be established. If the data gets migrated for any reason, the mappings are updated accordingly. This advice is recommended in scenarios where data locality is not important, but avoiding faults is. Consider for example a system containing multiple GPUs with peer-to-peer access enabled, where the data located on one GPU is occasionally accessed by peer GPUs. In such scenarios, migrating data over to the other GPUs is not as important because the accesses are infrequent and the overhead of migration may be too high. But preventing faults can still help improve performance, and so having a mapping set up in advance is useful. Note that on CPU access of this data, the data may be migrated to host memory because the CPU typically cannot access device memory directly. Any GPU that had the MEM_ADVISE_SET_ACCESSED_BY flag set for this data will now have its mapping updated to point to the page in host memory. If MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice. Additionally, if the preferred location of this memory region or any subset of it is also device, then the policies associated with MEM_ADVISE_SET_PREFERRED_LOCATION will override the policies of this advice. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.
        • MEM_ADVISE_UNSET_ACCESSED_BY: Undoes the effect of MEM_ADVISE_SET_ACCESSED_BY. Any mappings to the data from device may be removed at any time causing accesses to result in non-fatal page faults. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.
        Parameters:
        devPtr - pointer to memory to set the advice for
        count - size in bytes of the memory range
        advice - advice to be applied for the specified memory range
        device - device to apply the advice for
      • ncuMemRangeGetAttribute

        public static int ncuMemRangeGetAttribute​(long data,
                                                  long dataSize,
                                                  int attribute,
                                                  long devPtr,
                                                  long count)
        Unsafe version of: MemRangeGetAttribute
        Parameters:
        dataSize - the size of data
      • cuMemRangeGetAttribute

        public static int cuMemRangeGetAttribute​(java.nio.ByteBuffer data,
                                                 int attribute,
                                                 long devPtr,
                                                 long count)
        Query an attribute of a given memory range.

        Query an attribute about the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables.

        The attribute parameter can take the following values:

        • MEM_RANGE_ATTRIBUTE_READ_MOSTLY: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be 1 if all pages in the given memory range have read-duplication enabled, or 0 otherwise.
        • MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be a GPU device id if all pages in the memory range have that GPU as their preferred location, or it will be CU_DEVICE_CPU if all pages in the memory range have the CPU as their preferred location, or it will be CU_DEVICE_INVALID if either all the pages don't have the same preferred location or some of the pages don't have a preferred location at all. Note that the actual location of the pages in the memory range at the time of the query may be different from the preferred location.
        • MEM_RANGE_ATTRIBUTE_ACCESSED_BY: If this attribute is specified, data will be interpreted as an array of 32-bit integers, and dataSize must be a non-zero multiple of 4. The result returned will be a list of device ids that had MEM_ADVISE_SET_ACCESSED_BY set for that entire memory range. If any device does not have that advice set for the entire memory range, that device will not be included. If data is larger than the number of devices that have that advice set for that memory range, CU_DEVICE_INVALID will be returned in all the extra space provided. For ex., if dataSize is 12 (i.e. data has 3 elements) and only device 0 has the advice set, then the result returned will be { 0, CU_DEVICE_INVALID, CU_DEVICE_INVALID }. If data is smaller than the number of devices that have that advice set, then only as many devices will be returned as can fit in the array. There is no guarantee on which specific devices will be returned, however.
        • MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be the last location to which all pages in the memory range were prefetched explicitly via MemPrefetchAsync. This will either be a GPU id or CU_DEVICE_CPU depending on whether the last location for prefetch was a GPU or the CPU respectively. If any page in the memory range was never explicitly prefetched or if all pages were not prefetched to the same location, CU_DEVICE_INVALID will be returned. Note that this simply returns the last location that the applicaton requested to prefetch the memory range to. It gives no indication as to whether the prefetch operation to that location has completed or even begun.
        Parameters:
        data - a pointers to a memory location where the result of each attribute query will be written to
        attribute - the attribute to query
        devPtr - start of the range to query
        count - size of the range to query
      • ncuMemRangeGetAttributes

        public static int ncuMemRangeGetAttributes​(long data,
                                                   long dataSizes,
                                                   long attributes,
                                                   long numAttributes,
                                                   long devPtr,
                                                   long count)
        Unsafe version of: MemRangeGetAttributes
        Parameters:
        numAttributes - number of attributes to query
      • ncuPointerSetAttribute

        public static int ncuPointerSetAttribute​(long value,
                                                 int attribute,
                                                 long ptr)
        Unsafe version of: PointerSetAttribute
      • cuPointerSetAttribute

        public static int cuPointerSetAttribute​(java.nio.ByteBuffer value,
                                                int attribute,
                                                long ptr)
        Set attributes on a previously allocated memory region.

        The supported attributes are:

        • POINTER_ATTRIBUTE_SYNC_MEMOPS: A boolean attribute that can either be set (1) or unset (0).

          When set, the region of memory that ptr points to is guaranteed to always synchronize memory operations that are synchronous. If there are some previously initiated synchronous memory operations that are pending when this attribute is set, the function does not return until those memory operations are complete. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior. value will be considered as a pointer to an unsigned integer to which this attribute is to be set.

        Parameters:
        value - pointer to memory containing the value to be set
        attribute - pointer attribute to set
        ptr - pointer to a memory region allocated using CUDA memory allocation APIs
      • ncuPointerGetAttributes

        public static int ncuPointerGetAttributes​(int numAttributes,
                                                  long attributes,
                                                  long data,
                                                  long ptr)
        Unsafe version of: PointerGetAttributes
        Parameters:
        numAttributes - number of attributes to query
      • ncuStreamCreate

        public static int ncuStreamCreate​(long phStream,
                                          int Flags)
        Unsafe version of: StreamCreate
      • cuStreamCreate

        public static int cuStreamCreate​(org.lwjgl.PointerBuffer phStream,
                                         int Flags)
        Create a stream.

        Creates a stream and returns a handle in phStream. The Flags argument determines behaviors of the stream.

        Valid values for Flags are:

        • STREAM_DEFAULT: Default stream creation flag.
        • STREAM_NON_BLOCKING: Specifies that work running in the created stream may run concurrently with work in stream 0 (the NULL stream), and that the created stream should perform no implicit synchronization with stream 0.
        Parameters:
        phStream - returned newly created stream
        Flags - parameters for stream creation
      • ncuStreamCreateWithPriority

        public static int ncuStreamCreateWithPriority​(long phStream,
                                                      int flags,
                                                      int priority)
        Unsafe version of: StreamCreateWithPriority
      • cuStreamCreateWithPriority

        public static int cuStreamCreateWithPriority​(org.lwjgl.PointerBuffer phStream,
                                                     int flags,
                                                     int priority)
        Create a stream with the given priority.

        Creates a stream with the specified priority and returns a handle in phStream. This API alters the scheduler priority of work in the stream. Work in a higher priority stream may preempt work already executing in a low priority stream.

        priority follows a convention where lower numbers represent higher priorities. 0 represents default priority. The range of meaningful numerical priorities can be queried using CtxGetStreamPriorityRange. If the specified priority is outside the numerical range returned by CtxGetStreamPriorityRange, it will automatically be clamped to the lowest or the highest number in the range.

        Note

        Stream priorities are supported only on GPUs with compute capability 3.5 or higher.

        Note

        In the current implementation, only compute kernels launched in priority streams are affected by the stream's priority. Stream priorities have no effect on host-to-device and device-to-host memory operations.

        Parameters:
        phStream - returned newly created stream
        flags - flags for stream creation. See StreamCreate for a list of valid flags
        priority - stream priority. Lower numbers represent higher priorities. See CtxGetStreamPriorityRange for more information about meaningful stream priorities that can be passed.
      • ncuStreamGetPriority

        public static int ncuStreamGetPriority​(long hStream,
                                               long priority)
        Unsafe version of: StreamGetPriority
      • cuStreamGetPriority

        public static int cuStreamGetPriority​(long hStream,
                                              java.nio.IntBuffer priority)
        Query the priority of a given stream.

        Query the priority of a stream created using StreamCreate or StreamCreateWithPriority and return the priority in priority. Note that if the stream was created with a priority outside the numerical range returned by CtxGetStreamPriorityRange, this function returns the clamped priority. See StreamCreateWithPriority for details about priority clamping.

        Parameters:
        hStream - handle to the stream to be queried
        priority - pointer to a signed integer in which the stream's priority is returned
      • ncuStreamGetFlags

        public static int ncuStreamGetFlags​(long hStream,
                                            long flags)
        Unsafe version of: StreamGetFlags
      • cuStreamGetFlags

        public static int cuStreamGetFlags​(long hStream,
                                           java.nio.IntBuffer flags)
        Query the flags of a given stream.

        Query the flags of a stream created using StreamCreate or StreamCreateWithPriority and return the flags in flags.

        Parameters:
        hStream - handle to the stream to be queried
        flags - pointer to an unsigned integer in which the stream's flags are returned The value returned in flags is a logical 'OR' of all flags that were used while creating this stream. See StreamCreate for the list of valid flags.
      • ncuStreamGetCtx

        public static int ncuStreamGetCtx​(long hStream,
                                          long pctx)
        Unsafe version of: StreamGetCtx
      • cuStreamGetCtx

        public static int cuStreamGetCtx​(long hStream,
                                         org.lwjgl.PointerBuffer pctx)
        Query the context associated with a stream.

        Returns the CUDA context that the stream is associated with.

        The stream handle hStream can refer to any of the following:

        • a stream created via any of the CUDA driver APIs such as StreamCreate and StreamCreateWithPriority, or their runtime API equivalents such as cudaStreamCreate(), cudaStreamCreateWithFlags() and cudaStreamCreateWithPriority(). The returned context is the context that was active in the calling thread when the stream was created. Passing an invalid handle will result in undefined behavior.
        • any of the special streams such as the NULL stream, STREAM_LEGACY and STREAM_PER_THREAD. The runtime API equivalents of these are also accepted, which are NULL, cudaStreamLegacy() and cudaStreamPerThread() respectively. Specifying any of the special handles will return the context current to the calling thread. If no context is current to the calling thread, CUDA_ERROR_INVALID_CONTEXT is returned.
        Parameters:
        hStream - handle to the stream to be queried
        pctx - returned context associated with the stream
      • cuStreamWaitEvent

        public static int cuStreamWaitEvent​(long hStream,
                                            long hEvent,
                                            int Flags)
        Make a compute stream wait on an event.

        Makes all future work submitted to hStream wait for all work captured in hEvent. See EventRecord for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. hEvent may be from a different context or device than hStream.

        Parameters:
        hStream - stream to wait
        hEvent - event to wait on (may not be NULL). One of:
        EVENT_WAIT_DEFAULTEVENT_WAIT_EXTERNAL
        Flags - see CUevent_capture_flags
      • ncuStreamAddCallback

        public static int ncuStreamAddCallback​(long hStream,
                                               long callback,
                                               long userData,
                                               int flags)
        Unsafe version of: StreamAddCallback
      • cuStreamAddCallback

        public static int cuStreamAddCallback​(long hStream,
                                              CUstreamCallbackI callback,
                                              long userData,
                                              int flags)
        Add a callback to a compute stream.
        Note

        This function is slated for eventual deprecation and removal. If you do not require the callback to execute in case of a device error, consider using LaunchHostFunc. Additionally, this function is not supported with StreamBeginCapture and StreamEndCapture, unlike LaunchHostFunc.

        Adds a callback to be called on the host after all currently enqueued items in the stream have completed. For each cuStreamAddCallback call, the callback will be executed exactly once. The callback will block later work in the stream until it is finished.

        The callback may be passed CUDA_SUCCESS or an error code. In the event of a device error, all subsequently executed callbacks will receive an appropriate CUresult.

        Callbacks must not make any CUDA API calls. Attempting to use a CUDA API will result in CUDA_ERROR_NOT_PERMITTED. Callbacks must not perform any synchronization that may depend on outstanding device work or other callbacks that are not mandated to run earlier. Callbacks without a mandated order (in independent streams) execute in undefined order and may be serialized.

        For the purposes of Unified Memory, callback execution makes a number of guarantees:

        • The callback stream is considered idle for the duration of the callback. Thus, for example, a callback may always use memory attached to the callback stream.
        • The start of execution of a callback has the same effect as synchronizing an event recorded in the same stream immediately prior to the callback. It thus synchronizes streams which have been "joined" prior to the callback.
        • Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a callback might use global attached memory even if work has been added to another stream, if the work has been ordered behind the callback with an event.
        • Completion of a callback does not cause a stream to become active except as described above. The callback stream will remain idle if no device work follows the callback, and will remain idle across consecutive callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a callback at the end of the stream.
        Parameters:
        hStream - stream to add callback to
        callback - the function to call once preceding stream operations are complete
        userData - user specified data to be passed to the callback function
        flags - reserved for future use, must be 0
      • cuStreamBeginCapture

        public static int cuStreamBeginCapture​(long hStream)
        Begins graph capture on a stream.

        Begin graph capture on hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned via StreamEndCapture. Capture may not be initiated if stream is STREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried via StreamIsCapturing. A unique id representing the capture sequence may be queried via StreamGetCaptureInfo.

        Note

        Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

        Parameters:
        hStream - stream in which to initiate capture
      • cuStreamBeginCapture_v2

        public static int cuStreamBeginCapture_v2​(long hStream,
                                                  int mode)
        Begins graph capture on a stream.

        Begin graph capture on hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned via StreamEndCapture. Capture may not be initiated if stream is STREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried via StreamIsCapturing. A unique id representing the capture sequence may be queried via StreamGetCaptureInfo.

        If mode is not STREAM_CAPTURE_MODE_RELAXED, StreamEndCapture must be called on this stream from the same thread.

        Note

        Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

        Parameters:
        hStream - stream in which to initiate capture
        mode - controls the interaction of this capture sequence with other API calls that are potentially unsafe. For more details see ThreadExchangeStreamCaptureMode.
      • ncuThreadExchangeStreamCaptureMode

        public static int ncuThreadExchangeStreamCaptureMode​(long mode)
      • cuThreadExchangeStreamCaptureMode

        public static int cuThreadExchangeStreamCaptureMode​(java.nio.IntBuffer mode)
        Swaps the stream capture interaction mode for a thread.

        Sets the calling thread's stream capture interaction mode to the value contained in *mode, and overwrites *mode with the previous mode for the thread. To facilitate deterministic behavior across function or module boundaries, callers are encouraged to use this API in a push-pop fashion:

        
         CUstreamCaptureMode mode = desiredMode
         cuThreadExchangeStreamCaptureMode(&mode);
         ...
         cuThreadExchangeStreamCaptureMode(&mode); // restore previous mode

        During stream capture (see StreamBeginCapture), some actions, such as a call to cudaMalloc, may be unsafe. In the case of cudaMalloc, the operation is not enqueued asynchronously to a stream, and is not observed by stream capture. Therefore, if the sequence of operations captured via StreamBeginCapture depended on the allocation being replayed whenever the graph is launched, the captured graph would be invalid.

        Therefore, stream capture places restrictions on API calls that can be made within or concurrently to a StreamBeginCapture-StreamEndCapture sequence. This behavior can be controlled via this API and flags to cuStreamBeginCapture.

        A thread's mode is one of the following:

        • STREAM_CAPTURE_MODE_GLOBAL: This is the default mode.

          If the local thread has an ongoing capture sequence that was not initiated with STREAM_CAPTURE_MODE_RELAXED at StreamBeginCapture, or if any other thread has a concurrent capture sequence initiated with STREAM_CAPTURE_MODE_GLOBAL, this thread is prohibited from potentially unsafe API calls.

        • STREAM_CAPTURE_MODE_THREAD_LOCAL: If the local thread has an ongoing capture sequence not initiated with CU_STREAM_CAPTURE_MODE_RELAXED, it is prohibited from potentially unsafe API calls. Concurrent capture sequences in other threads are ignored.
        • STREAM_CAPTURE_MODE_RELAXED: The local thread is not prohibited from potentially unsafe API calls. Note that the thread is still prohibited from API calls which necessarily conflict with stream capture, for example, attempting EventQuery on an event that was last recorded inside a capture sequence.
        Parameters:
        mode - pointer to mode value to swap with the current mode
      • ncuStreamEndCapture

        public static int ncuStreamEndCapture​(long hStream,
                                              long phGraph)
        Unsafe version of: StreamEndCapture
      • cuStreamEndCapture

        public static int cuStreamEndCapture​(long hStream,
                                             org.lwjgl.PointerBuffer phGraph)
        Ends capture on a stream, returning the captured graph.

        End capture on hStream, returning the captured graph via phGraph. Capture must have been initiated on hStream via a call to StreamBeginCapture. If capture was invalidated, due to a violation of the rules of stream capture, then a NULL graph will be returned.

        If the mode argument to StreamBeginCapture was not STREAM_CAPTURE_MODE_RELAXED, this call must be from the same thread as StreamBeginCapture.

        Parameters:
        hStream - stream to query
        phGraph - the captured graph
      • ncuStreamIsCapturing

        public static int ncuStreamIsCapturing​(long hStream,
                                               long captureStatus)
        Unsafe version of: StreamIsCapturing
      • cuStreamIsCapturing

        public static int cuStreamIsCapturing​(long hStream,
                                              java.nio.IntBuffer captureStatus)
        Returns a stream's capture status.

        Return the capture status of hStream via captureStatus. After a successful call, *captureStatus will contain one of the following:

        Note that, if this is called on STREAM_LEGACY (the "null stream") while a blocking stream in the same context is capturing, it will return CUDA_ERROR_STREAM_CAPTURE_IMPLICIT and *captureStatus is unspecified after the call. The blocking stream capture is not invalidated.

        When a blocking stream is capturing, the legacy stream is in an unusable state until the blocking stream capture is terminated. The legacy stream is not supported for stream capture, but attempted use would have an implicit dependency on the capturing stream(s).

        Parameters:
        hStream - stream to query
        captureStatus - returns the stream's capture status
      • ncuStreamGetCaptureInfo

        public static int ncuStreamGetCaptureInfo​(long hStream,
                                                  long captureStatus,
                                                  long id)
        Unsafe version of: StreamGetCaptureInfo
      • cuStreamGetCaptureInfo

        public static int cuStreamGetCaptureInfo​(long hStream,
                                                 java.nio.IntBuffer captureStatus,
                                                 java.nio.LongBuffer id)
        Query capture status of a stream.

        Query the capture status of a stream and and get an id for the capture sequence, which is unique over the lifetime of the process.

        If called on STREAM_LEGACY (the "null stream") while a stream not created with STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

        A valid id is returned only if both of the following are true:

      • ncuStreamGetCaptureInfo_v2

        public static int ncuStreamGetCaptureInfo_v2​(long hStream,
                                                     long captureStatus_out,
                                                     long id_out,
                                                     long graph_out,
                                                     long dependencies_out,
                                                     long numDependencies_out)
        Unsafe version of: StreamGetCaptureInfo_v2
      • cuStreamGetCaptureInfo_v2

        public static int cuStreamGetCaptureInfo_v2​(long hStream,
                                                    java.nio.IntBuffer captureStatus_out,
                                                    @Nullable
                                                    java.nio.LongBuffer id_out,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer graph_out,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer dependencies_out,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer numDependencies_out)
        Query a stream's capture state (11.3+).

        Query stream state related to stream capture.

        If called on STREAM_LEGACY (the "null stream") while a stream not created with STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

        Valid data (other than capture status) is returned only if both of the following are true:

        This version of cuStreamGetCaptureInfo is introduced in CUDA 11.3 and will supplant the previous version in 12.0. Developers requiring compatibility across minor versions to CUDA 11.0 (driver version 445) should use StreamGetCaptureInfo or include a fallback path.

        Parameters:
        hStream - the stream to query
        captureStatus_out - location to return the capture status of the stream; required
        id_out - optional location to return an id for the capture sequence, which is unique over the lifetime of the process
        graph_out - optional location to return the graph being captured into.

        All operations other than destroy and node removal are permitted on the graph while the capture sequence is in progress. This API does not transfer ownership of the graph, which is transferred or destroyed at StreamEndCapture. Note that the graph handle may be invalidated before end of capture for certain errors. Nodes that are or become unreachable from the original stream at StreamEndCapture due to direct actions on the graph do not trigger CUDA_ERROR_STREAM_CAPTURE_UNJOINED.

        dependencies_out - optional location to store a pointer to an array of nodes.

        The next node to be captured in the stream will depend on this set of nodes, absent operations such as event wait which modify this set. The array pointer is valid until the next API call which operates on the stream or until end of capture. The node handles may be copied out and are valid until they or the graph is destroyed. The driver-owned array may also be passed directly to APIs that operate on the graph (not the stream) without copying.

        numDependencies_out - optional location to store the size of the array returned in dependencies_out
      • ncuStreamUpdateCaptureDependencies

        public static int ncuStreamUpdateCaptureDependencies​(long hStream,
                                                             long dependencies,
                                                             long numDependencies,
                                                             int flags)
      • cuStreamUpdateCaptureDependencies

        public static int cuStreamUpdateCaptureDependencies​(long hStream,
                                                            org.lwjgl.PointerBuffer dependencies,
                                                            int flags)
        Update the set of dependencies in a capturing stream (11.3+).

        Modifies the dependency set of a capturing stream. The dependency set is the set of nodes that the next captured node in the stream will depend on.

        Valid flags are STREAM_ADD_CAPTURE_DEPENDENCIES and STREAM_SET_CAPTURE_DEPENDENCIES. These control whether the set passed to the API is added to the existing set or replaces it. A flags value of 0 defaults to STREAM_ADD_CAPTURE_DEPENDENCIES.

        Nodes that are removed from the dependency set via this API do not result in CUDA_ERROR_STREAM_CAPTURE_UNJOINED if they are unreachable from the stream at StreamEndCapture.

        Returns CUDA_ERROR_ILLEGAL_STATE if the stream is not capturing.

        This API is new in CUDA 11.3. Developers requiring compatibility across minor versions to CUDA 11.0 should not use this API or provide a fallback.

      • cuStreamAttachMemAsync

        public static int cuStreamAttachMemAsync​(long hStream,
                                                 long dptr,
                                                 long length,
                                                 int flags)
        Attach memory to a stream asynchronously.

        Enqueues an operation in hStream to specify stream association of length bytes of memory starting from dptr. This function is a stream-ordered operation, meaning that it is dependent on, and will only take effect when, previous work in stream has completed. Any previous association is automatically replaced.

        dptr must point to one of the following types of memories:

        • managed memory declared using the __managed__ keyword or allocated with MemAllocManaged.
        • a valid host-accessible region of system-allocated pageable memory. This type of memory may only be specified if the device associated with the stream reports a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS.

        For managed allocations, length must be either zero or the entire allocation's size. Both indicate that the entire allocation's stream association is being changed. Currently, it is not possible to change stream association for a portion of a managed allocation.

        For pageable host allocations, length must be non-zero.

        The stream association is specified using flags which must be one of CUmemAttach_flags. If the MEM_ATTACH_GLOBAL flag is specified, the memory can be accessed by any stream on any device. If the MEM_ATTACH_HOST flag is specified, the program makes a guarantee that it won't access the memory on the device from any stream on a device that has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If the MEM_ATTACH_SINGLE flag is specified and hStream is associated with a device that has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, the program makes a guarantee that it will only access the memory on the device from hStream. It is illegal to attach singly to the NULL stream, because the NULL stream is a virtual global stream and not a specific stream. An error will be returned in this case.

        When memory is associated with a single stream, the Unified Memory system will allow CPU access to this memory region so long as all operations in hStream have completed, regardless of whether other streams are active. In effect, this constrains exclusive ownership of the managed memory region by an active GPU to per-stream activity instead of whole-GPU activity.

        Accessing memory on the device from streams that are not associated with it will produce undefined results. No error checking is performed by the Unified Memory system to ensure that kernels launched into other streams do not access this region.

        It is a program's responsibility to order calls to StreamAttachMemAsync via events, synchronization or other means to ensure legal access to memory at all times. Data visibility and coherency will be changed appropriately for all kernels which follow a stream-association change.

        If hStream is destroyed while data is associated with it, the association is removed and the association reverts to the default visibility of the allocation as specified at MemAllocManaged. For __managed__ variables, the default association is always MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.

        Parameters:
        hStream - stream in which to enqueue the attach operation
        dptr - pointer to memory (must be a pointer to managed memory or to a valid host-accessible region of system-allocated pageable memory)
        length - length of memory
        flags - must be one of CUmemAttach_flags
      • cuStreamQuery

        public static int cuStreamQuery​(long hStream)
        Determine status of a compute stream.

        Returns CUDA_SUCCESS if all operations in the stream specified by hStream have completed, or CUDA_ERROR_NOT_READY if not.

        For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called StreamSynchronize.

        Parameters:
        hStream - stream to query status of
      • cuStreamSynchronize

        public static int cuStreamSynchronize​(long hStream)
        Wait until a stream's tasks are completed.

        Waits until the device has completed all operations in the stream specified by hStream. If the context was created with the CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the stream is finished with all of its tasks.

        Parameters:
        hStream - stream to wait for
      • cuStreamDestroy

        public static int cuStreamDestroy​(long hStream)
        Destroys a stream.

        Destroys the stream specified by hStream.

        In case the device is still doing work in the stream hStream when StreamDestroy is called, the function will return immediately and the resources associated with hStream will be released automatically once the device has completed all work in hStream.

        Parameters:
        hStream - stream to destroy
      • cuStreamCopyAttributes

        public static int cuStreamCopyAttributes​(long dst,
                                                 long src)
        Copies attributes from source stream to destination stream.

        Copies attributes from source stream src to destination stream dst. Both streams must have the same context.

        Parameters:
        dst - destination stream
        src - source stream For list of attributes see CUstreamAttrID
      • ncuStreamGetAttribute

        public static int ncuStreamGetAttribute​(long hStream,
                                                int attr,
                                                long value_out)
        Unsafe version of: StreamGetAttribute
      • cuStreamGetAttribute

        public static int cuStreamGetAttribute​(long hStream,
                                               int attr,
                                               CUstreamAttrValue value_out)
        Queries stream attribute.

        Queries attribute attr from hStream and stores it in corresponding member of value_out.

      • ncuStreamSetAttribute

        public static int ncuStreamSetAttribute​(long hStream,
                                                int attr,
                                                long value)
        Unsafe version of: StreamSetAttribute
      • cuStreamSetAttribute

        public static int cuStreamSetAttribute​(long hStream,
                                               int attr,
                                               CUstreamAttrValue value)
        Sets stream attribute.

        Sets attribute attr on hStream from corresponding attribute of value. The updated attribute will be applied to subsequent work submitted to the stream. It will not affect previously submitted work.

      • ncuEventCreate

        public static int ncuEventCreate​(long phEvent,
                                         int Flags)
        Unsafe version of: EventCreate
      • cuEventCreate

        public static int cuEventCreate​(org.lwjgl.PointerBuffer phEvent,
                                        int Flags)
        Creates an event.

        Creates an event *phEvent for the current context with the flags specified via Flags. Valid flags include:

        Parameters:
        phEvent - returns newly created event
        Flags - event creation flags
      • cuEventRecord

        public static int cuEventRecord​(long hEvent,
                                        long hStream)
        Records an event.

        Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as EventQuery or StreamWaitEvent will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

        EventRecord can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as StreamWaitEvent use the most recently captured state at the time of the API call, and are not affected by later calls to EventRecord. Before the first call to EventRecord, an event represents an empty set of work, so for example EventQuery would return CUDA_SUCCESS.

        Parameters:
        hEvent - event to record
        hStream - stream to record event for
      • cuEventRecordWithFlags

        public static int cuEventRecordWithFlags​(long hEvent,
                                                 long hStream,
                                                 int flags)
        Records an event.

        Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as EventQuery or StreamWaitEvent will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

        EventRecordWithFlags can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as StreamWaitEvent use the most recently captured state at the time of the API call, and are not affected by later calls to EventRecordWithFlags. Before the first call to EventRecordWithFlags, an event represents an empty set of work, so for example EventQuery would return CUDA_SUCCESS.

        flags include:

        • EVENT_RECORD_DEFAULT: Default event creation flag.
        • EVENT_RECORD_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.
        Parameters:
        hEvent - event to record
        hStream - stream to record event for
        flags - see CUevent_capture_flags
      • cuEventQuery

        public static int cuEventQuery​(long hEvent)
        Queries an event's status.

        Queries the status of all work currently captured by hEvent. See EventRecord for details on what is captured by an event.

        Returns CUDA_SUCCESS if all captured work has been completed, or CUDA_ERROR_NOT_READY if any captured work is incomplete.

        For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called EventSynchronize.

        Parameters:
        hEvent - event to query
      • cuEventSynchronize

        public static int cuEventSynchronize​(long hEvent)
        Waits for an event to complete.

        Waits until the completion of all work currently captured in hEvent. See EventRecord for details on what is captured by an event.

        Waiting for an event that was created with the EVENT_BLOCKING_SYNC flag will cause the calling CPU thread to block until the event has been completed by the device. If the EVENT_BLOCKING_SYNC flag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.

        Parameters:
        hEvent - event to wait for
      • cuEventDestroy

        public static int cuEventDestroy​(long hEvent)
        Destroys an event.

        Destroys the event specified by hEvent.

        An event may be destroyed before it is complete (i.e., while EventQuery would return CUDA_ERROR_NOT_READY). In this case, the call does not block on completion of the event, and any associated resources will automatically be released asynchronously at completion.

        Parameters:
        hEvent - event to destroy
      • ncuEventElapsedTime

        public static int ncuEventElapsedTime​(long pMilliseconds,
                                              long hStart,
                                              long hEnd)
        Unsafe version of: EventElapsedTime
      • cuEventElapsedTime

        public static int cuEventElapsedTime​(java.nio.FloatBuffer pMilliseconds,
                                             long hStart,
                                             long hEnd)
        Computes the elapsed time between two events.

        Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds).

        If either event was last recorded in a non-NULL stream, the resulting time may be greater than expected (even if both used the same stream handle). This happens because the EventRecord operation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.

        If EventRecord has not been called on either event then CUDA_ERROR_INVALID_HANDLE is returned. If EventRecord has been called on both events but one or both of them has not yet been completed (that is, EventQuery would return CUDA_ERROR_NOT_READY on at least one of the events), CUDA_ERROR_NOT_READY is returned. If either event was created with the EVENT_DISABLE_TIMING flag, then this function will return CUDA_ERROR_INVALID_HANDLE.

        Parameters:
        pMilliseconds - time between hStart and hEnd in ms
        hStart - starting event
        hEnd - ending event
      • ncuImportExternalMemory

        public static int ncuImportExternalMemory​(long extMem_out,
                                                  long memHandleDesc)
        Unsafe version of: ImportExternalMemory
      • cuImportExternalMemory

        public static int cuImportExternalMemory​(org.lwjgl.PointerBuffer extMem_out,
                                                 CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc)
        Imports an external memory object.

        Imports an externally allocated memory object and returns a handle to that in extMem_out.

        The properties of the handle being imported must be described in memHandleDesc.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD, then ::handle::fd must be a valid file descriptor referencing a memory object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a memory object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a memory object.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT, then ::handle::win32::handle must be non-NULL and ::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the memory object are destroyed.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Heap object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Heap object.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Resource object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Resource object.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE, then ::handle::win32::handle must represent a valid shared NT handle that is\ returned by IDXGIResource1::CreateSharedHandle when referring to a ID3D11Resource object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D11Resource object.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT, then ::handle::win32::handle must represent a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a ID3D11Resource object and ::handle::win32::name must be NULL.

        If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then ::handle::nvSciBufObject must be non-NULL and reference a valid NvSciBuf object. If the NvSciBuf object imported into CUDA is also mapped by other drivers, then the application must use WaitExternalSemaphoresAsync or SignalExternalSemaphoresAsync as appropriate barriers to maintain coherence between CUDA and the other drivers. See CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC and CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC for memory synchronization.

        The size of the memory object must be specified in ::size.

        Specifying the flag CUDA_EXTERNAL_MEMORY_DEDICATED in ::flags indicates that the resource is a dedicated resource. The definition of what a dedicated resource is outside the scope of this extension. This flag must be set if ::type is one of the following:

        Note

        If the Vulkan memory imported into CUDA is mapped on the CPU then the application must use vkInvalidateMappedMemoryRanges/vkFlushMappedMemoryRanges as well as appropriate Vulkan pipeline barriers to maintain coherence between CPU and GPU. For more information on these APIs, please refer to "Synchronization and Cache Control" chapter from Vulkan specification.

        Parameters:
        extMem_out - returned handle to an external memory object
        memHandleDesc - memory import handle descriptor
      • ncuExternalMemoryGetMappedBuffer

        public static int ncuExternalMemoryGetMappedBuffer​(long devPtr,
                                                           long extMem,
                                                           long bufferDesc)
      • cuExternalMemoryGetMappedBuffer

        public static int cuExternalMemoryGetMappedBuffer​(org.lwjgl.PointerBuffer devPtr,
                                                          long extMem,
                                                          CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc)
        Maps a buffer onto an imported memory object.

        Maps a buffer onto an imported memory object and returns a device pointer in devPtr.

        The properties of the buffer being mapped must be described in bufferDesc.

        The offset and size have to be suitably aligned to match the requirements of the external API. Mapping two buffers whose ranges overlap may or may not result in the same virtual address being returned for the overlapped portion. In such cases, the application must ensure that all accesses to that region from the GPU are volatile. Otherwise writes made via one address are not guaranteed to be visible via the other address, even if they're issued by the same thread. It is recommended that applications map the combined range instead of mapping separate buffers and then apply the appropriate offsets to the returned pointer to derive the individual buffers.

        The returned pointer devPtr must be freed using MemFree.

        Parameters:
        devPtr - returned device pointer to buffer
        extMem - handle to external memory object
        bufferDesc - buffer descriptor
      • ncuExternalMemoryGetMappedMipmappedArray

        public static int ncuExternalMemoryGetMappedMipmappedArray​(long mipmap,
                                                                   long extMem,
                                                                   long mipmapDesc)
      • cuExternalMemoryGetMappedMipmappedArray

        public static int cuExternalMemoryGetMappedMipmappedArray​(org.lwjgl.PointerBuffer mipmap,
                                                                  long extMem,
                                                                  CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc)
        Maps a CUDA mipmapped array onto an external memory object.

        Maps a CUDA mipmapped array onto an external object and returns a handle to it in mipmap.

        The properties of the CUDA mipmapped array being mapped must be described in mipmapDesc.

        ::offset is the offset in the memory object where the base level of the mipmap chain is. ::arrayDesc describes the format, dimensions and type of the base level of the mipmap chain. For further details on these parameters, please refer to the documentation for MipmappedArrayCreate. Note that if the mipmapped array is bound as a color target in the graphics API, then the flag CUDA_ARRAY3D_COLOR_ATTACHMENT must be specified in ::arrayDesc::Flags. ::numLevels specifies the total number of levels in the mipmap chain.

        If extMem was imported from a handle of type EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then ::numLevels must be equal to 1.

        The returned CUDA mipmapped array must be freed using MipmappedArrayDestroy.

        Parameters:
        mipmap - returned CUDA mipmapped array
        extMem - handle to external memory object
        mipmapDesc - CUDA array descriptor
      • cuDestroyExternalMemory

        public static int cuDestroyExternalMemory​(long extMem)
        Destroys an external memory object.

        Destroys the specified external memory object. Any existing buffers and CUDA mipmapped arrays mapped onto this object must no longer be used and must be explicitly freed using MemFree and MipmappedArrayDestroy respectively.

        Parameters:
        extMem - external memory object to be destroyed
      • ncuImportExternalSemaphore

        public static int ncuImportExternalSemaphore​(long extSem_out,
                                                     long semHandleDesc)
        Unsafe version of: ImportExternalSemaphore
      • cuImportExternalSemaphore

        public static int cuImportExternalSemaphore​(org.lwjgl.PointerBuffer extSem_out,
                                                    CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc)
        Imports an external semaphore.

        Imports an externally allocated synchronization object and returns a handle to that in extSem_out.

        The properties of the handle being imported must be described in semHandleDesc.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, then ::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must name a valid synchronization object.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT, then ::handle::win32::handle must be non-NULL and ::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the synchronization object are destroyed.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Fence object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D12Fence object.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, then ::handle::win32::handle represents a valid shared NT handle that is returned by ID3D11Fence::CreateSharedHandle. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D11Fence object.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, then ::handle::nvSciSyncObj represents a valid NvSciSyncObj.

        EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, then ::handle::win32::handle represents a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a IDXGIKeyedMutex object. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid IDXGIKeyedMutex object.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT, then ::handle::win32::handle represents a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a IDXGIKeyedMutex object and ::handle::win32::name must be NULL.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, then ::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

        If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must name a valid synchronization object.

        Parameters:
        extSem_out - returned handle to an external semaphore
        semHandleDesc - semaphore import handle descriptor
      • ncuSignalExternalSemaphoresAsync

        public static int ncuSignalExternalSemaphoresAsync​(long extSemArray,
                                                           long paramsArray,
                                                           int numExtSems,
                                                           long stream)
        Parameters:
        numExtSems - number of semaphores to signal
      • ncuWaitExternalSemaphoresAsync

        public static int ncuWaitExternalSemaphoresAsync​(long extSemArray,
                                                         long paramsArray,
                                                         int numExtSems,
                                                         long stream)
        Unsafe version of: WaitExternalSemaphoresAsync
        Parameters:
        numExtSems - number of semaphores to wait on
      • cuDestroyExternalSemaphore

        public static int cuDestroyExternalSemaphore​(long extSem)
        Destroys an external semaphore.

        Destroys an external semaphore object and releases any references to the underlying resource. Any outstanding signals or waits must have completed before the semaphore is destroyed.

        Parameters:
        extSem - external semaphore to be destroyed
      • cuStreamWaitValue32

        public static int cuStreamWaitValue32​(long stream,
                                              long addr,
                                              int value,
                                              int flags)
        Wait on a memory location.

        Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int32_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

        If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).

        Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

        Support for STREAM_WAIT_VALUE_NOR can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.

        Parameters:
        stream - the stream to synchronize on the memory location
        addr - the memory location to wait on
        value - the value to compare with the memory location
        flags - see CUstreamWaitValue_flags
      • cuStreamWaitValue64

        public static int cuStreamWaitValue64​(long stream,
                                              long addr,
                                              long value,
                                              int flags)
        Wait on a memory location.

        Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int64_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

        If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer.

        Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

        Parameters:
        stream - the stream to synchronize on the memory location
        addr - the memory location to wait on
        value - the value to compare with the memory location
        flags - see CUstreamWaitValue_flags
      • cuStreamWriteValue32

        public static int cuStreamWriteValue32​(long stream,
                                               long addr,
                                               int value,
                                               int flags)
        Write a value to memory.

        Write a value to memory. Unless the STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

        If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).

        Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

        Parameters:
        stream - the stream to do the write in
        addr - the device address to write to
        value - the value to write
        flags - see CUstreamWriteValue_flags
      • cuStreamWriteValue64

        public static int cuStreamWriteValue64​(long stream,
                                               long addr,
                                               long value,
                                               int flags)
        Write a value to memory.

        Write a value to memory. Unless the STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

        If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer.

        Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

        Parameters:
        stream - the stream to do the write in
        addr - the device address to write to
        value - the value to write
        flags - see CUstreamWriteValue_flags
      • ncuStreamBatchMemOp

        public static int ncuStreamBatchMemOp​(long stream,
                                              int count,
                                              long paramArray,
                                              int flags)
        Unsafe version of: StreamBatchMemOp
        Parameters:
        count - the number of operations in the array. Must be less than 256.
      • cuStreamBatchMemOp

        public static int cuStreamBatchMemOp​(long stream,
                                             CUstreamBatchMemOpParams.Buffer paramArray,
                                             int flags)
        Batch operations to synchronize the stream via memory operations.

        This is a batch version of StreamWaitValue32 and StreamWriteValue32. Batching operations may avoid some performance overhead in both the API call and the device execution versus adding them to the stream in separate API calls. The operations are enqueued in the order they appear in the array.

        See CUstreamBatchMemOpType for the full set of supported operations, and StreamWaitValue32, StreamWaitValue64, StreamWriteValue32, and StreamWriteValue64 for details of specific operations.

        Basic support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS. See related APIs for details on querying support for specific operations.

        Parameters:
        stream - the stream to enqueue the operations in
        paramArray - the types and parameters of the individual operations
        flags - reserved for future expansion; must be 0
      • ncuFuncGetAttribute

        public static int ncuFuncGetAttribute​(long pi,
                                              int attrib,
                                              long hfunc)
        Unsafe version of: FuncGetAttribute
      • cuFuncGetAttribute

        public static int cuFuncGetAttribute​(java.nio.IntBuffer pi,
                                             int attrib,
                                             long hfunc)
        Returns information about a function.

        Returns in *pi the integer value of the attribute attrib on the kernel given by hfunc. The supported attributes are:

        • FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK: The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
        • FUNC_ATTRIBUTE_SHARED_SIZE_BYTES: The size in bytes of statically-allocated shared memory per block required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
        • FUNC_ATTRIBUTE_CONST_SIZE_BYTES: The size in bytes of user-allocated constant memory required by this function.
        • FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES: The size in bytes of local memory used by each thread of this function.
        • FUNC_ATTRIBUTE_NUM_REGS: The number of registers used by each thread of this function.
        • FUNC_ATTRIBUTE_PTX_VERSION: The PTX virtual architecture version for which the function was compiled. This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.
        • FUNC_ATTRIBUTE_BINARY_VERSION: The binary architecture version for which the function was compiled. This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.
        • FUNC_ATTRIBUTE_CACHE_MODE_CA: The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
        • FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: The maximum size in bytes of dynamically-allocated shared memory.
        • FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: Preferred shared memory-L1 cache split ratio in percent of total shared memory.
        Parameters:
        pi - returned attribute value
        attrib - attribute requested
        hfunc - function to query attribute of
      • cuFuncSetAttribute

        public static int cuFuncSetAttribute​(long hfunc,
                                             int attrib,
                                             int value)
        Sets information about a function.

        This call sets the value of a specified attribute attrib on the kernel given by hfunc to an integer value specified by val This function returns CUDA_SUCCESS if the new value of the attribute could be successfully set. If the set fails, this call will return an error. Not all attributes can have values set. Attempting to set a value on a read-only attribute will result in an error (CUDA_ERROR_INVALID_VALUE).

        Supported attributes for the cuFuncSetAttribute call are:

        Parameters:
        hfunc - function to query attribute of
        attrib - attribute requested
        value - the value to set
      • cuFuncSetCacheConfig

        public static int cuFuncSetCacheConfig​(long hfunc,
                                               int config)
        Sets the preferred cache configuration for a device function.

        On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the device function hfunc. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute hfunc. Any context-wide preference set via CtxSetCacheConfig will be overridden by this per-function setting unless the per-function setting is FUNC_CACHE_PREFER_NONE. In that case, the current context-wide setting will be used.

        This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

        Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

        The supported cache configurations are:

        Parameters:
        hfunc - kernel to configure cache for
        config - requested cache configuration
      • cuFuncSetSharedMemConfig

        public static int cuFuncSetSharedMemConfig​(long hfunc,
                                                   int config)
        Sets the shared memory configuration for a device function.

        On devices with configurable shared memory banks, this function will force all subsequent launches of the specified device function to have the given shared memory bank size configuration. On any given launch of the function, the shared memory configuration of the device will be temporarily changed if needed to suit the function's preferred configuration. Changes in shared memory configuration between subsequent launches of functions, may introduce a device side synchronization point.

        Any per-function setting of shared memory bank size set via FuncSetSharedMemConfig will override the context wide setting set with CtxSetSharedMemConfig.

        Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

        This function will do nothing on devices with fixed shared memory bank size.

        The supported bank configurations are:

        Parameters:
        hfunc - kernel to be given a shared memory config
        config - requested shared memory configuration
      • ncuFuncGetModule

        public static int ncuFuncGetModule​(long hmod,
                                           long hfunc)
        Unsafe version of: FuncGetModule
      • cuFuncGetModule

        public static int cuFuncGetModule​(org.lwjgl.PointerBuffer hmod,
                                          long hfunc)
        Returns a module handle.

        Returns in *hmod the handle of the module that function hfunc is located in. The lifetime of the module corresponds to the lifetime of the context it was loaded in or until the module is explicitly unloaded.

        The CUDA runtime manages its own modules loaded into the primary context. If the handle returned by this API refers to a module loaded by the CUDA runtime, calling ModuleUnload on that module will result in undefined behavior.

        Parameters:
        hmod - returned module handle
        hfunc - function to retrieve module for
      • ncuLaunchKernel

        public static int ncuLaunchKernel​(long f,
                                          int gridDimX,
                                          int gridDimY,
                                          int gridDimZ,
                                          int blockDimX,
                                          int blockDimY,
                                          int blockDimZ,
                                          int sharedMemBytes,
                                          long hStream,
                                          long kernelParams,
                                          long extra)
        Unsafe version of: LaunchKernel
      • cuLaunchKernel

        public static int cuLaunchKernel​(long f,
                                         int gridDimX,
                                         int gridDimY,
                                         int gridDimZ,
                                         int blockDimX,
                                         int blockDimY,
                                         int blockDimZ,
                                         int sharedMemBytes,
                                         long hStream,
                                         @Nullable
                                         org.lwjgl.PointerBuffer kernelParams,
                                         @Nullable
                                         org.lwjgl.PointerBuffer extra)
        Launches a CUDA function.

        Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

        sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

        Kernel parameters to f can be specified in one of two ways:

        1. Kernel parameters can be specified via kernelParams.

          If f has N parameters, then kernelParams needs to be an array of N pointers. Each of kernelParams[0] through kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

        2. Kernel parameters can also be packaged by the application into a single buffer that is passed in via the extra parameter.

          This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. Here is an example of using the extra parameter in this manner:

          
           size_t argBufferSize;
           char argBuffer[256];
           
           // populate argBuffer and argBufferSize
           
           void *config[] = {
               CU_LAUNCH_PARAM_BUFFER_POINTER, argBuffer,
               CU_LAUNCH_PARAM_BUFFER_SIZE,    &argBufferSize,
               CU_LAUNCH_PARAM_END
           };
           status = cuLaunchKernel(f, gx, gy, gz, bx, by, bz, sh, s, NULL, config);

        The extra parameter exists to allow cuLaunchKernel() to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or LAUNCH_PARAM_END.

        The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL).

        Calling cuLaunchKernel() invalidates the persistent function state set through the following deprecated APIs: FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, ParamSetv.

        Note that to use LaunchKernel, the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchKernel will return CUDA_ERROR_INVALID_IMAGE.

        Parameters:
        f - kernel to launch
        gridDimX - width of grid in blocks
        gridDimY - height of grid in blocks
        gridDimZ - depth of grid in blocks
        blockDimX - x dimension of each thread block
        blockDimY - y dimension of each thread block
        blockDimZ - z dimension of each thread block
        sharedMemBytes - dynamic shared-memory size per thread block in bytes
        hStream - stream identifier
        kernelParams - array of pointers to kernel parameters
        extra - extra options
      • ncuLaunchCooperativeKernel

        public static int ncuLaunchCooperativeKernel​(long f,
                                                     int gridDimX,
                                                     int gridDimY,
                                                     int gridDimZ,
                                                     int blockDimX,
                                                     int blockDimY,
                                                     int blockDimZ,
                                                     int sharedMemBytes,
                                                     long hStream,
                                                     long kernelParams)
        Unsafe version of: LaunchCooperativeKernel
      • cuLaunchCooperativeKernel

        public static int cuLaunchCooperativeKernel​(long f,
                                                    int gridDimX,
                                                    int gridDimY,
                                                    int gridDimZ,
                                                    int blockDimX,
                                                    int blockDimY,
                                                    int blockDimZ,
                                                    int sharedMemBytes,
                                                    long hStream,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer kernelParams)
        Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.

        Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

        sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

        The device on which this kernel is invoked must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH.

        The total number of blocks launched cannot exceed the maximum number of blocks per multiprocessor as returned by OccupancyMaxActiveBlocksPerMultiprocessor (or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.

        The kernel cannot make use of CUDA dynamic parallelism.

        Kernel parameters must be specified via kernelParams. If f has N parameters, then kernelParams needs to be an array of N pointers. Each of kernelParams[0] through kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

        Calling LaunchCooperativeKernel sets persistent function state that is the same as function state set through LaunchKernel API

        When the kernel f is launched via LaunchCooperativeKernel, the previous block shape, shared size and parameter info associated with f is overwritten.

        Note that to use LaunchCooperativeKernel, the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchCooperativeKernel will return CUDA_ERROR_INVALID_IMAGE.

        Parameters:
        f - kernel to launch
        gridDimX - width of grid in blocks
        gridDimY - height of grid in blocks
        gridDimZ - depth of grid in blocks
        blockDimX - x dimension of each thread block
        blockDimY - y dimension of each thread block
        blockDimZ - z dimension of each thread block
        sharedMemBytes - dynamic shared-memory size per thread block in bytes
        hStream - stream identifier
        kernelParams - array of pointers to kernel parameters
      • ncuLaunchCooperativeKernelMultiDevice

        public static int ncuLaunchCooperativeKernelMultiDevice​(long launchParamsList,
                                                                int numDevices,
                                                                int flags)
        Parameters:
        numDevices - size of the launchParamsList array
      • cuLaunchCooperativeKernelMultiDevice

        public static int cuLaunchCooperativeKernelMultiDevice​(CUDA_LAUNCH_PARAMS.Buffer launchParamsList,
                                                               int flags)
        Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they executeDeprecated: This function is deprecated as of CUDA 11.3.

        Invokes kernels as specified in the launchParamsList array where each element of the array specifies all the parameters required to perform a single kernel launch. These kernels can cooperate and synchronize as they execute. The size of the array is specified by numDevices.

        No two kernels can be launched on the same device. All the devices targeted by this multi-device launch must be identical. All devices must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH.

        All kernels launched must be identical with respect to the compiled code. Note that any __device__ __constant__ or __managed__ variables present in the module that owns the kernel launched on each device, are independently instantiated on every device. It is the application's responsibility to ensure these variables are initialized and used appropriately.

        The size of the grids as specified in blocks, the size of the blocks themselves and the amount of shared memory used by each thread block must also match across all launched kernels.

        The streams used to launch these kernels must have been created via either StreamCreate or StreamCreateWithPriority. The NULL stream or STREAM_LEGACY or STREAM_PER_THREAD cannot be used.

        The total number of blocks launched per kernel cannot exceed the maximum number of blocks per multiprocessor as returned by OccupancyMaxActiveBlocksPerMultiprocessor (or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT. Since the total number of blocks launched per device has to match across all devices, the maximum number of blocks that can be launched per device will be limited by the device with the least number of multiprocessors.

        The kernels cannot make use of CUDA dynamic parallelism.

        • CUDA_LAUNCH_PARAMS::function specifies the kernel to be launched. All functions must be identical with respect to the compiled code.
        • CUDA_LAUNCH_PARAMS::gridDimX is the width of the grid in blocks. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::gridDimY is the height of the grid in blocks. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::gridDimZ is the depth of the grid in blocks. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::blockDimX is the X dimension of each thread block. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::blockDimX is the Y dimension of each thread block. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::blockDimZ is the Z dimension of each thread block. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::sharedMemBytes is the dynamic shared-memory size per thread block in bytes. This must match across all kernels launched.
        • CUDA_LAUNCH_PARAMS::hStream is the handle to the stream to perform the launch in. This cannot be the NULL stream or STREAM_LEGACY or STREAM_PER_THREAD. The CUDA context associated with this stream must match that associated with CUDA_LAUNCH_PARAMS::function.
        • CUDA_LAUNCH_PARAMS::kernelParams is an array of pointers to kernel parameters. If ::function has N parameters, then ::kernelParams needs to be an array of N pointers. Each of ::kernelParams[0] through ::kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

        By default, the kernel won't begin execution on any GPU until all prior work in all the specified streams has completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC. When this flag is specified, each kernel will only wait for prior work in the stream corresponding to that GPU to complete before it begins execution.

        Similarly, by default, any subsequent work pushed in any of the specified streams will not begin execution until the kernels on all GPUs have completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC. When this flag is specified, any subsequent work pushed in any of the specified streams will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

        Calling LaunchCooperativeKernelMultiDevice sets persistent function state that is the same as function state set through LaunchKernel API when called individually for each element in launchParamsList.

        When kernels are launched via LaunchCooperativeKernelMultiDevice, the previous block shape, shared size and parameter info associated with each CUDA_LAUNCH_PARAMS::function in launchParamsList is overwritten.

        Note that to use LaunchCooperativeKernelMultiDevice, the kernels must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchCooperativeKernelMultiDevice will return CUDA_ERROR_INVALID_IMAGE.

        Parameters:
        launchParamsList - list of launch parameters, one per device
        flags - flags to control launch behavior
      • ncuLaunchHostFunc

        public static int ncuLaunchHostFunc​(long hStream,
                                            long fn,
                                            long userData)
        Unsafe version of: LaunchHostFunc
      • cuLaunchHostFunc

        public static int cuLaunchHostFunc​(long hStream,
                                           CUhostFnI fn,
                                           long userData)
        Enqueues a host function call in a stream.

        Enqueues a host function to run in a stream. The function will be called after currently enqueued work and will block work added after it.

        The host function must not make any CUDA API calls. Attempting to use a CUDA API may result in CUDA_ERROR_NOT_PERMITTED, but this is not required. The host function must not perform any synchronization that may depend on outstanding CUDA work not mandated to run earlier. Host functions without a mandated order (such as in independent streams) execute in undefined order and may be serialized.

        For the purposes of Unified Memory, execution makes a number of guarantees:

        • The stream is considered idle for the duration of the function's execution. Thus, for example, the function may always use memory attached to the stream it was enqueued in.
        • The start of execution of the function has the same effect as synchronizing an event recorded in the same stream immediately prior to the function. It thus synchronizes streams which have been "joined" prior to the function.
        • Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a function might use global attached memory even if work has been added to another stream, if the work has been ordered behind the function call with an event.
        • Completion of the function does not cause a stream to become active except as described above. The stream will remain idle if no device work follows the function, and will remain idle across consecutive host functions or stream callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a host function at the end of the stream.

        Note that, in contrast to StreamAddCallback, the function will not be called in the event of an error in the CUDA context.

        Parameters:
        hStream - stream to enqueue function call in
        fn - the function to call once preceding stream operations are complete
        userData - user-specified data to be passed to the function
      • cuFuncSetBlockShape

        public static int cuFuncSetBlockShape​(long hfunc,
                                              int x,
                                              int y,
                                              int z)
        Sets the block-dimensions for the function. (Deprecated)

        Specifies the x, y, and z dimensions of the thread blocks that are created when the kernel given by hfunc is launched.

        Parameters:
        hfunc - kernel to specify dimensions of
        x - x dimension
        y - y dimension
        z - z dimension
      • cuFuncSetSharedSize

        public static int cuFuncSetSharedSize​(long hfunc,
                                              int bytes)
        Sets the dynamic shared-memory size for the function. (Deprecated)

        Sets through bytes the amount of dynamic shared memory that will be available to each thread block when the kernel given by hfunc is launched.

        Parameters:
        hfunc - kernel to specify dynamic shared-memory size for
        bytes - dynamic shared-memory size per thread in bytes
      • cuParamSetSize

        public static int cuParamSetSize​(long hfunc,
                                         int numbytes)
        Sets the parameter size for the function. (Deprecated)

        Sets through numbytes the total size in bytes needed by the function parameters of the kernel corresponding to hfunc.

        Parameters:
        hfunc - kernel to set parameter size for
        numbytes - size of parameter list in bytes
      • cuParamSeti

        public static int cuParamSeti​(long hfunc,
                                      int offset,
                                      int value)
        Adds an integer parameter to the function's argument listDeprecated:

        Sets an integer parameter that will be specified the next time the kernel corresponding to hfunc will be invoked. offset is a byte offset.

        Parameters:
        hfunc - kernel to add parameter to
        offset - offset to add parameter to argument list
        value - value of parameter
      • cuParamSetf

        public static int cuParamSetf​(long hfunc,
                                      int offset,
                                      float value)
        Adds a floating-point parameter to the function's argument list. (Deprecated)

        Sets a floating-point parameter that will be specified the next time the kernel corresponding to hfunc will be invoked. offset is a byte offset.

        Parameters:
        hfunc - kernel to add parameter to
        offset - offset to add parameter to argument list
        value - value of parameter
      • ncuParamSetv

        public static int ncuParamSetv​(long hfunc,
                                       int offset,
                                       long ptr,
                                       int numbytes)
        Unsafe version of: ParamSetv
        Parameters:
        numbytes - size of data to copy in bytes
      • cuParamSetv

        public static int cuParamSetv​(long hfunc,
                                      int offset,
                                      java.nio.ByteBuffer ptr)
        Adds arbitrary data to the function's argument list. (Deprecated)

        Copies an arbitrary amount of data (specified in numbytes) from ptr into the parameter space of the kernel corresponding to hfunc. offset is a byte offset.

        Parameters:
        hfunc - kernel to add data to
        offset - offset to add data to argument list
        ptr - pointer to arbitrary data
      • cuLaunch

        public static int cuLaunch​(long f)
        Launches a CUDA function. (Deprecated)

        Invokes the kernel f on a 1 x 1 x 1 grid of blocks. The block contains the number of threads specified by a previous call to FuncSetBlockShape.

        The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

        Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

        Parameters:
        f - kernel to launch
      • cuLaunchGrid

        public static int cuLaunchGrid​(long f,
                                       int grid_width,
                                       int grid_height)
        Launches a CUDA function. (Deprecated)

        Invokes the kernel f on a grid_width x grid_height grid of blocks. Each block contains the number of threads specified by a previous call to FuncSetBlockShape.

        The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

        Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

        Parameters:
        f - kernel to launch
        grid_width - width of grid in blocks
        grid_height - height of grid in blocks
      • cuLaunchGridAsync

        public static int cuLaunchGridAsync​(long f,
                                            int grid_width,
                                            int grid_height,
                                            long hStream)
        Launches a CUDA function. (Deprecated)

        Invokes the kernel f on a grid_width x grid_height grid of blocks. Each block contains the number of threads specified by a previous call to FuncSetBlockShape.

        The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

        Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

        Note

        In certain cases where cubins are created with no ABI (i.e., using ptxas --abi-compile no), this function may serialize kernel launches. The CUDA driver retains asynchronous behavior by growing the per-thread stack as needed per launch and not shrinking it afterwards.

        Parameters:
        f - kernel to launch
        grid_width - width of grid in blocks
        grid_height - height of grid in blocks
        hStream - stream identifier
      • cuParamSetTexRef

        public static int cuParamSetTexRef​(long hfunc,
                                           int texunit,
                                           long hTexRef)
        Adds a texture-reference to the function's argument list. (Deprecated)

        Makes the CUDA array or linear memory bound to the texture reference hTexRef available to a device program as a texture. In this version of CUDA, the texture-reference must be obtained via ModuleGetTexRef and the texunit parameter must be set to PARAM_TR_DEFAULT.

        Parameters:
        hfunc - kernel to add texture-reference to
        texunit - texture unit (must be PARAM_TR_DEFAULT)
        hTexRef - texture-reference to add to argument list
      • ncuGraphCreate

        public static int ncuGraphCreate​(long phGraph,
                                         int flags)
        Unsafe version of: GraphCreate
      • cuGraphCreate

        public static int cuGraphCreate​(org.lwjgl.PointerBuffer phGraph,
                                        int flags)
        Creates a graph.

        Creates an empty graph, which is returned via phGraph.

        Parameters:
        phGraph - returns newly created graph
        flags - graph creation flags, must be 0
      • ncuGraphAddKernelNode

        public static int ncuGraphAddKernelNode​(long phGraphNode,
                                                long hGraph,
                                                long dependencies,
                                                long numDependencies,
                                                long nodeParams)
        Unsafe version of: GraphAddKernelNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddKernelNode

        public static int cuGraphAddKernelNode​(org.lwjgl.PointerBuffer phGraphNode,
                                               long hGraph,
                                               @Nullable
                                               org.lwjgl.PointerBuffer dependencies,
                                               CUDA_KERNEL_NODE_PARAMS nodeParams)
        Creates a kernel execution node and adds it to a graph.

        Creates a new kernel execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        When the graph is launched, the node will invoke kernel func on a (gridDimX x gridDimY x gridDimZ) grid of blocks. Each block contains (blockDimX x blockDimY x blockDimZ) threads.

        sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

        Kernel parameters to func can be specified in one of two ways:

        1. Kernel parameters can be specified via kernelParams. If the kernel has N parameters, then kernelParams needs to be an array of N pointers. Each pointer, from kernelParams[0] to kernelParams[N-1], points to the region of memory from which the actual parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.
        2. Kernel parameters for non-cooperative kernels can also be packaged by the application into a single buffer that is passed in via extra. This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. The extra parameter exists to allow this function to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or LAUNCH_PARAM_END.

        The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL). CUDA_ERROR_INVALID_VALUE will be returned if extra is used for a cooperative kernel.

        The kernelParams or extra array, as well as the argument values it points to, are copied during this call.

        Note

        Kernels launched using graphs must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        nodeParams - parameters for the GPU execution node
      • ncuGraphKernelNodeGetParams

        public static int ncuGraphKernelNodeGetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphKernelNodeGetParams
      • cuGraphKernelNodeGetParams

        public static int cuGraphKernelNodeGetParams​(long hNode,
                                                     CUDA_KERNEL_NODE_PARAMS nodeParams)
        Returns a kernel node's parameters.

        Returns the parameters of kernel node hNode in nodeParams. The kernelParams or extra array returned in nodeParams, as well as the argument values it points to, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphKernelNodeSetParams to update the parameters of this node.

        The params will contain either kernelParams or extra, according to which of these was most recently set on the node.

        Parameters:
        hNode - node to get the parameters for
        nodeParams - pointer to return the parameters
      • ncuGraphKernelNodeSetParams

        public static int ncuGraphKernelNodeSetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphKernelNodeSetParams
      • cuGraphKernelNodeSetParams

        public static int cuGraphKernelNodeSetParams​(long hNode,
                                                     CUDA_KERNEL_NODE_PARAMS nodeParams)
        Sets a kernel node's parameters.

        Sets the parameters of kernel node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddMemcpyNode

        public static int ncuGraphAddMemcpyNode​(long phGraphNode,
                                                long hGraph,
                                                long dependencies,
                                                long numDependencies,
                                                long copyParams,
                                                long ctx)
        Unsafe version of: GraphAddMemcpyNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddMemcpyNode

        public static int cuGraphAddMemcpyNode​(org.lwjgl.PointerBuffer phGraphNode,
                                               long hGraph,
                                               @Nullable
                                               org.lwjgl.PointerBuffer dependencies,
                                               CUDA_MEMCPY3D copyParams,
                                               long ctx)
        Creates a memcpy node and adds it to a graph.

        Creates a new memcpy node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        When the graph is launched, the node will perform the memcpy described by copyParams. See Memcpy3D for a description of the structure and its restrictions.

        Memcpy nodes have some additional restrictions with regards to managed memory, if the system contains at least one device which has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If one or more of the operands refer to managed memory, then using the memory type MEMORYTYPE_UNIFIED is disallowed for those operand(s). The managed memory will be treated as residing on either the host or the device, depending on which memory type is specified.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        copyParams - parameters for the memory copy
        ctx - context on which to run the node
      • ncuGraphMemcpyNodeGetParams

        public static int ncuGraphMemcpyNodeGetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphMemcpyNodeGetParams
      • cuGraphMemcpyNodeGetParams

        public static int cuGraphMemcpyNodeGetParams​(long hNode,
                                                     CUDA_MEMCPY3D nodeParams)
        Returns a memcpy node's parameters.

        Returns the parameters of memcpy node hNode in nodeParams.

        Parameters:
        hNode - node to get the parameters for
        nodeParams - pointer to return the parameters
      • ncuGraphMemcpyNodeSetParams

        public static int ncuGraphMemcpyNodeSetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphMemcpyNodeSetParams
      • cuGraphMemcpyNodeSetParams

        public static int cuGraphMemcpyNodeSetParams​(long hNode,
                                                     CUDA_MEMCPY3D nodeParams)
        Sets a memcpy node's parameters.

        Sets the parameters of memcpy node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddMemsetNode

        public static int ncuGraphAddMemsetNode​(long phGraphNode,
                                                long hGraph,
                                                long dependencies,
                                                long numDependencies,
                                                long memsetParams,
                                                long ctx)
        Unsafe version of: GraphAddMemsetNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddMemsetNode

        public static int cuGraphAddMemsetNode​(org.lwjgl.PointerBuffer phGraphNode,
                                               long hGraph,
                                               @Nullable
                                               org.lwjgl.PointerBuffer dependencies,
                                               CUDA_MEMSET_NODE_PARAMS memsetParams,
                                               long ctx)
        Creates a memset node and adds it to a graph.

        Creates a new memset node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by memsetParams.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        memsetParams - parameters for the memory set
        ctx - context on which to run the node
      • ncuGraphMemsetNodeGetParams

        public static int ncuGraphMemsetNodeGetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphMemsetNodeGetParams
      • cuGraphMemsetNodeGetParams

        public static int cuGraphMemsetNodeGetParams​(long hNode,
                                                     CUDA_MEMSET_NODE_PARAMS nodeParams)
        Returns a memset node's parameters.

        Returns the parameters of memset node hNode in nodeParams.

        Parameters:
        hNode - node to get the parameters for
        nodeParams - pointer to return the parameters
      • ncuGraphMemsetNodeSetParams

        public static int ncuGraphMemsetNodeSetParams​(long hNode,
                                                      long nodeParams)
        Unsafe version of: GraphMemsetNodeSetParams
      • cuGraphMemsetNodeSetParams

        public static int cuGraphMemsetNodeSetParams​(long hNode,
                                                     CUDA_MEMSET_NODE_PARAMS nodeParams)
        Sets a memset node's parameters.

        Sets the parameters of memset node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddHostNode

        public static int ncuGraphAddHostNode​(long phGraphNode,
                                              long hGraph,
                                              long dependencies,
                                              long numDependencies,
                                              long nodeParams)
        Unsafe version of: GraphAddHostNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddHostNode

        public static int cuGraphAddHostNode​(org.lwjgl.PointerBuffer phGraphNode,
                                             long hGraph,
                                             @Nullable
                                             org.lwjgl.PointerBuffer dependencies,
                                             CUDA_HOST_NODE_PARAMS nodeParams)
        Creates a host execution node and adds it to a graph.

        Creates a new CPU execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        When the graph is launched, the node will invoke the specified CPU function. Host nodes are not supported under MPS with pre-Volta GPUs.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        nodeParams - parameters for the host node
      • ncuGraphHostNodeGetParams

        public static int ncuGraphHostNodeGetParams​(long hNode,
                                                    long nodeParams)
        Unsafe version of: GraphHostNodeGetParams
      • cuGraphHostNodeGetParams

        public static int cuGraphHostNodeGetParams​(long hNode,
                                                   CUDA_HOST_NODE_PARAMS nodeParams)
        Returns a host node's parameters.

        Returns the parameters of host node hNode in nodeParams.

        Parameters:
        hNode - node to get the parameters for
        nodeParams - pointer to return the parameters
      • ncuGraphHostNodeSetParams

        public static int ncuGraphHostNodeSetParams​(long hNode,
                                                    long nodeParams)
        Unsafe version of: GraphHostNodeSetParams
      • cuGraphHostNodeSetParams

        public static int cuGraphHostNodeSetParams​(long hNode,
                                                   CUDA_HOST_NODE_PARAMS nodeParams)
        Sets a host node's parameters.

        Sets the parameters of host node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddChildGraphNode

        public static int ncuGraphAddChildGraphNode​(long phGraphNode,
                                                    long hGraph,
                                                    long dependencies,
                                                    long numDependencies,
                                                    long childGraph)
        Unsafe version of: GraphAddChildGraphNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddChildGraphNode

        public static int cuGraphAddChildGraphNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                   long hGraph,
                                                   @Nullable
                                                   org.lwjgl.PointerBuffer dependencies,
                                                   long childGraph)
        Creates a child graph node and adds it to a graph.

        Creates a new node which executes an embedded graph, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        If hGraph contains allocation or free nodes, this call will return an error.

        The node executes an embedded child graph. The child graph is cloned in this call.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        childGraph - the graph to clone into this node
      • ncuGraphChildGraphNodeGetGraph

        public static int ncuGraphChildGraphNodeGetGraph​(long hNode,
                                                         long phGraph)
        Unsafe version of: GraphChildGraphNodeGetGraph
      • cuGraphChildGraphNodeGetGraph

        public static int cuGraphChildGraphNodeGetGraph​(long hNode,
                                                        org.lwjgl.PointerBuffer phGraph)
        Gets a handle to the embedded graph of a child graph node.

        Gets a handle to the embedded graph in a child graph node. This call does not clone the graph. Changes to the graph will be reflected in the node, and the node retains ownership of the graph.

        Allocation and free nodes cannot be added to the returned graph. Attempting to do so will return an error.

        Parameters:
        hNode - node to get the embedded graph for
        phGraph - location to store a handle to the graph
      • ncuGraphAddEmptyNode

        public static int ncuGraphAddEmptyNode​(long phGraphNode,
                                               long hGraph,
                                               long dependencies,
                                               long numDependencies)
        Unsafe version of: GraphAddEmptyNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddEmptyNode

        public static int cuGraphAddEmptyNode​(org.lwjgl.PointerBuffer phGraphNode,
                                              long hGraph,
                                              @Nullable
                                              org.lwjgl.PointerBuffer dependencies)
        Creates an empty node and adds it to a graph.

        Creates a new node which performs no operation, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        An empty node performs no operation during execution, but can be used for transitive ordering. For example, a phased execution graph with 2 groups of n nodes with a barrier between them can be represented using an empty node and 2*n dependency edges, rather than no empty node and n^2 dependency edges.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
      • ncuGraphAddEventRecordNode

        public static int ncuGraphAddEventRecordNode​(long phGraphNode,
                                                     long hGraph,
                                                     long dependencies,
                                                     long numDependencies,
                                                     long event)
        Unsafe version of: GraphAddEventRecordNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddEventRecordNode

        public static int cuGraphAddEventRecordNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                    long hGraph,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer dependencies,
                                                    long event)
        Creates an event record node and adds it to a graph.

        Creates a new event record node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        Each launch of the graph will record event to capture execution of the node's dependencies.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        event - event for the node
      • ncuGraphEventRecordNodeGetEvent

        public static int ncuGraphEventRecordNodeGetEvent​(long hNode,
                                                          long event_out)
        Unsafe version of: GraphEventRecordNodeGetEvent
      • cuGraphEventRecordNodeGetEvent

        public static int cuGraphEventRecordNodeGetEvent​(long hNode,
                                                         org.lwjgl.PointerBuffer event_out)
        Returns the event associated with an event record node.

        Returns the event of event record node hNode in event_out.

        Parameters:
        hNode - node to get the event for
        event_out - pointer to return the event
      • cuGraphEventRecordNodeSetEvent

        public static int cuGraphEventRecordNodeSetEvent​(long hNode,
                                                         long event)
        Sets an event record node's event.

        Sets the event of event record node hNode to event.

        Parameters:
        hNode - node to set the event for
        event - event to use
      • ncuGraphAddEventWaitNode

        public static int ncuGraphAddEventWaitNode​(long phGraphNode,
                                                   long hGraph,
                                                   long dependencies,
                                                   long numDependencies,
                                                   long event)
        Unsafe version of: GraphAddEventWaitNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddEventWaitNode

        public static int cuGraphAddEventWaitNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                  long hGraph,
                                                  @Nullable
                                                  org.lwjgl.PointerBuffer dependencies,
                                                  long event)
        Creates an event wait node and adds it to a graph.

        Creates a new event wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        The graph node will wait for all work captured in event. See EventRecord for details on what is captured by an event. event may be from a different context or device than the launch stream.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        event - event for the node
      • ncuGraphEventWaitNodeGetEvent

        public static int ncuGraphEventWaitNodeGetEvent​(long hNode,
                                                        long event_out)
        Unsafe version of: GraphEventWaitNodeGetEvent
      • cuGraphEventWaitNodeGetEvent

        public static int cuGraphEventWaitNodeGetEvent​(long hNode,
                                                       org.lwjgl.PointerBuffer event_out)
        Returns the event associated with an event wait node.

        Returns the event of event wait node hNode in event_out.

        Parameters:
        hNode - node to get the event for
        event_out - pointer to return the event
      • cuGraphEventWaitNodeSetEvent

        public static int cuGraphEventWaitNodeSetEvent​(long hNode,
                                                       long event)
        Sets an event wait node's event.

        Sets the event of event wait node hNode to event.

        Parameters:
        hNode - node to set the event for
        event - event to use
      • ncuGraphAddExternalSemaphoresSignalNode

        public static int ncuGraphAddExternalSemaphoresSignalNode​(long phGraphNode,
                                                                  long hGraph,
                                                                  long dependencies,
                                                                  long numDependencies,
                                                                  long nodeParams)
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddExternalSemaphoresSignalNode

        public static int cuGraphAddExternalSemaphoresSignalNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                                 long hGraph,
                                                                 @Nullable
                                                                 org.lwjgl.PointerBuffer dependencies,
                                                                 CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)
        Creates an external semaphore signal node and adds it to a graph.

        Creates a new external semaphore signal node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        Performs a signal operation on a set of externally allocated semaphore objects when the node is launched. The operation(s) will occur after all of the node's dependencies have completed.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        nodeParams - parameters for the node
      • cuGraphExternalSemaphoresSignalNodeGetParams

        public static int cuGraphExternalSemaphoresSignalNodeGetParams​(long hNode,
                                                                       CUDA_EXT_SEM_SIGNAL_NODE_PARAMS params_out)
        Returns an external semaphore signal node's parameters.

        Returns the parameters of an external semaphore signal node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

        Parameters:
        hNode - node to get the parameters for
        params_out - pointer to return the parameters
      • cuGraphExternalSemaphoresSignalNodeSetParams

        public static int cuGraphExternalSemaphoresSignalNodeSetParams​(long hNode,
                                                                       CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)
        Sets an external semaphore signal node's parameters.

        Sets the parameters of an external semaphore signal node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddExternalSemaphoresWaitNode

        public static int ncuGraphAddExternalSemaphoresWaitNode​(long phGraphNode,
                                                                long hGraph,
                                                                long dependencies,
                                                                long numDependencies,
                                                                long nodeParams)
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddExternalSemaphoresWaitNode

        public static int cuGraphAddExternalSemaphoresWaitNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                               long hGraph,
                                                               @Nullable
                                                               org.lwjgl.PointerBuffer dependencies,
                                                               CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)
        Creates an external semaphore wait node and adds it to a graph.

        Creates a new external semaphore wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        Performs a wait operation on a set of externally allocated semaphore objects when the node is launched. The node's dependencies will not be launched until the wait operation has completed.

        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        nodeParams - parameters for the node
      • ncuGraphExternalSemaphoresWaitNodeGetParams

        public static int ncuGraphExternalSemaphoresWaitNodeGetParams​(long hNode,
                                                                      long params_out)
      • cuGraphExternalSemaphoresWaitNodeGetParams

        public static int cuGraphExternalSemaphoresWaitNodeGetParams​(long hNode,
                                                                     CUDA_EXT_SEM_WAIT_NODE_PARAMS params_out)
        Returns an external semaphore wait node's parameters.

        Returns the parameters of an external semaphore wait node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

        Parameters:
        hNode - node to get the parameters for
        params_out - pointer to return the parameters
      • ncuGraphExternalSemaphoresWaitNodeSetParams

        public static int ncuGraphExternalSemaphoresWaitNodeSetParams​(long hNode,
                                                                      long nodeParams)
      • cuGraphExternalSemaphoresWaitNodeSetParams

        public static int cuGraphExternalSemaphoresWaitNodeSetParams​(long hNode,
                                                                     CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)
        Sets an external semaphore wait node's parameters.

        Sets the parameters of an external semaphore wait node hNode to nodeParams.

        Parameters:
        hNode - node to set the parameters for
        nodeParams - parameters to copy
      • ncuGraphAddMemAllocNode

        public static int ncuGraphAddMemAllocNode​(long phGraphNode,
                                                  long hGraph,
                                                  long dependencies,
                                                  long numDependencies,
                                                  long nodeParams)
        Unsafe version of: GraphAddMemAllocNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddMemAllocNode

        public static int cuGraphAddMemAllocNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                 long hGraph,
                                                 @Nullable
                                                 org.lwjgl.PointerBuffer dependencies,
                                                 CUDA_MEM_ALLOC_NODE_PARAMS nodeParams)
        Creates an allocation node and adds it to a graph.

        Creates a new allocation node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        When GraphAddMemAllocNode creates an allocation node, it returns the address of the allocation in nodeParams.dptr. The allocation's address remains fixed across instantiations and launches.

        If the allocation is freed in the same graph, by creating a free node using GraphAddMemFreeNode, the allocation can be accessed by nodes ordered after the allocation node but before the free node. These allocations cannot be freed outside the owning graph, and they can only be freed once in the owning graph.

        If the allocation is not freed in the same graph, then it can be accessed not only by nodes in the graph which are ordered after the allocation node, but also by stream operations ordered after the graph's execution but before the allocation is freed.

        Allocations which are not freed in the same graph can be freed by:

        It is not possible to free an allocation in both the owning graph and another graph. If the allocation is freed in the same graph, a free node cannot be added to another graph. If the allocation is freed in another graph, a free node can no longer be added to the owning graph.

        The following restrictions apply to graphs which contain allocation and/or memory free nodes:

        • Nodes and edges of the graph cannot be deleted.
        • The graph cannot be used in a child node.
        • Only one instantiation of the graph may exist at any point in time.
        • The graph cannot be cloned.
        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        nodeParams - parameters for the node
      • ncuGraphMemAllocNodeGetParams

        public static int ncuGraphMemAllocNodeGetParams​(long hNode,
                                                        long params_out)
        Unsafe version of: GraphMemAllocNodeGetParams
      • cuGraphMemAllocNodeGetParams

        public static int cuGraphMemAllocNodeGetParams​(long hNode,
                                                       CUDA_MEM_ALLOC_NODE_PARAMS params_out)
        Returns a memory alloc node's parameters.

        Returns the parameters of a memory alloc node hNode in params_out. The poolProps and accessDescs returned in params_out, are owned by the node. This memory remains valid until the node is destroyed. The returned parameters must not be modified.

        Parameters:
        hNode - node to get the parameters for
        params_out - pointer to return the parameters
      • ncuGraphAddMemFreeNode

        public static int ncuGraphAddMemFreeNode​(long phGraphNode,
                                                 long hGraph,
                                                 long dependencies,
                                                 long numDependencies,
                                                 long dptr)
        Unsafe version of: GraphAddMemFreeNode
        Parameters:
        numDependencies - number of dependencies
      • cuGraphAddMemFreeNode

        public static int cuGraphAddMemFreeNode​(org.lwjgl.PointerBuffer phGraphNode,
                                                long hGraph,
                                                @Nullable
                                                org.lwjgl.PointerBuffer dependencies,
                                                long dptr)
        Creates a memory free node and adds it to a graph.

        Creates a new memory free node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

        GraphAddMemFreeNode will return CUDA_ERROR_INVALID_VALUE if the user attempts to free:

        • an allocation twice in the same graph.
        • an address that was not returned by an allocation node.
        • an invalid address.

        The following restrictions apply to graphs which contain allocation and/or memory free nodes:

        • Nodes and edges of the graph cannot be deleted.
        • The graph cannot be used in a child node.
        • Only one instantiation of the graph may exist at any point in time.
        • The graph cannot be cloned.
        Parameters:
        phGraphNode - returns newly created node
        hGraph - graph to which to add the node
        dependencies - dependencies of the node
        dptr - address of memory to free
      • ncuGraphMemFreeNodeGetParams

        public static int ncuGraphMemFreeNodeGetParams​(long hNode,
                                                       long dptr_out)
        Unsafe version of: GraphMemFreeNodeGetParams
      • cuGraphMemFreeNodeGetParams

        public static int cuGraphMemFreeNodeGetParams​(long hNode,
                                                      org.lwjgl.PointerBuffer dptr_out)
        Returns a memory free node's parameters.

        Returns the address of a memory free node hNode in dptr_out.

        Parameters:
        hNode - node to get the parameters for
        dptr_out - pointer to return the device address
      • cuDeviceGraphMemTrim

        public static int cuDeviceGraphMemTrim​(int device)
        Free unused memory that was cached on the specified device for use with graphs back to the OS.

        Blocks which are not in use by a graph that is either currently executing or scheduled to execute are freed back to the operating system.

        Parameters:
        device - the device for which cached memory should be freed
      • ncuDeviceGetGraphMemAttribute

        public static int ncuDeviceGetGraphMemAttribute​(int device,
                                                        int attr,
                                                        long value)
        Unsafe version of: DeviceGetGraphMemAttribute
      • cuDeviceGetGraphMemAttribute

        public static int cuDeviceGetGraphMemAttribute​(int device,
                                                       int attr,
                                                       java.nio.ByteBuffer value)
        
        public static int cuDeviceGetGraphMemAttribute​(int device,
                                                       int attr,
                                                       java.nio.LongBuffer value)
        
        Query asynchronous allocation attributes related to graphs.

        Valid attributes are:

        Parameters:
        device - specifies the scope of the query
        attr - attribute to get
        value - retrieved value
      • ncuDeviceSetGraphMemAttribute

        public static int ncuDeviceSetGraphMemAttribute​(int device,
                                                        int attr,
                                                        long value)
        Unsafe version of: DeviceSetGraphMemAttribute
      • cuDeviceSetGraphMemAttribute

        public static int cuDeviceSetGraphMemAttribute​(int device,
                                                       int attr,
                                                       java.nio.ByteBuffer value)
        
        public static int cuDeviceSetGraphMemAttribute​(int device,
                                                       int attr,
                                                       java.nio.LongBuffer value)
        
        Set asynchronous allocation attributes related to graphs.

        Valid attributes are:

        • GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.
        • GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
        Parameters:
        device - specifies the scope of the query
        attr - attribute to get
        value - pointer to value to set
      • ncuGraphClone

        public static int ncuGraphClone​(long phGraphClone,
                                        long originalGraph)
        Unsafe version of: GraphClone
      • cuGraphClone

        public static int cuGraphClone​(org.lwjgl.PointerBuffer phGraphClone,
                                       long originalGraph)
        Clones a graph.

        This function creates a copy of originalGraph and returns it in phGraphClone. All parameters are copied into the cloned graph. The original graph may be modified after this call without affecting the clone.

        Child graph nodes in the original graph are recursively copied into the clone.

        Parameters:
        phGraphClone - returns newly created cloned graph
        originalGraph - graph to clone
      • ncuGraphNodeFindInClone

        public static int ncuGraphNodeFindInClone​(long phNode,
                                                  long hOriginalNode,
                                                  long hClonedGraph)
        Unsafe version of: GraphNodeFindInClone
      • cuGraphNodeFindInClone

        public static int cuGraphNodeFindInClone​(org.lwjgl.PointerBuffer phNode,
                                                 long hOriginalNode,
                                                 long hClonedGraph)
        Finds a cloned version of a node.

        This function returns the node in hClonedGraph corresponding to hOriginalNode in the original graph.

        hClonedGraph must have been cloned from hOriginalGraph via GraphClone. hOriginalNode must have been in hOriginalGraph at the time of the call to GraphClone, and the corresponding cloned node in hClonedGraph must not have been removed. The cloned node is then returned via phClonedNode.

        Parameters:
        phNode - returns handle to the cloned node
        hOriginalNode - handle to the original node
        hClonedGraph - cloned graph to query
      • ncuGraphNodeGetType

        public static int ncuGraphNodeGetType​(long hNode,
                                              long type)
        Unsafe version of: GraphNodeGetType
      • cuGraphNodeGetType

        public static int cuGraphNodeGetType​(long hNode,
                                             java.nio.IntBuffer type)
        Returns a node's type.

        Returns the node type of hNode in type.

        Parameters:
        hNode - node to query
        type - pointer to return the node type
      • ncuGraphGetNodes

        public static int ncuGraphGetNodes​(long hGraph,
                                           long nodes,
                                           long numNodes)
        Unsafe version of: GraphGetNodes
        Parameters:
        numNodes - see description
      • cuGraphGetNodes

        public static int cuGraphGetNodes​(long hGraph,
                                          @Nullable
                                          org.lwjgl.PointerBuffer nodes,
                                          org.lwjgl.PointerBuffer numNodes)
        Returns a graph's nodes.

        Returns a list of hGraph's nodes. nodes may be NULL, in which case this function will return the number of nodes in numNodes. Otherwise, numNodes entries will be filled in. If numNodes is higher than the actual number of nodes, the remaining entries in nodes will be set to NULL, and the number of nodes actually obtained will be returned in numNodes.

        Parameters:
        hGraph - graph to query
        nodes - pointer to return the nodes
        numNodes - see description
      • ncuGraphGetRootNodes

        public static int ncuGraphGetRootNodes​(long hGraph,
                                               long rootNodes,
                                               long numRootNodes)
        Unsafe version of: GraphGetRootNodes
        Parameters:
        numRootNodes - see description
      • cuGraphGetRootNodes

        public static int cuGraphGetRootNodes​(long hGraph,
                                              @Nullable
                                              org.lwjgl.PointerBuffer rootNodes,
                                              org.lwjgl.PointerBuffer numRootNodes)
        Returns a graph's root nodes.

        Returns a list of hGraph's root nodes. rootNodes may be NULL, in which case this function will return the number of root nodes in numRootNodes. Otherwise, numRootNodes entries will be filled in. If numRootNodes is higher than the actual number of root nodes, the remaining entries in rootNodes will be set to NULL, and the number of nodes actually obtained will be returned in numRootNodes.

        Parameters:
        hGraph - graph to query
        rootNodes - pointer to return the root nodes
        numRootNodes - see description
      • ncuGraphGetEdges

        public static int ncuGraphGetEdges​(long hGraph,
                                           long from,
                                           long to,
                                           long numEdges)
        Unsafe version of: GraphGetEdges
        Parameters:
        numEdges - see description
      • cuGraphGetEdges

        public static int cuGraphGetEdges​(long hGraph,
                                          @Nullable
                                          org.lwjgl.PointerBuffer from,
                                          @Nullable
                                          org.lwjgl.PointerBuffer to,
                                          org.lwjgl.PointerBuffer numEdges)
        Returns a graph's dependency edges.

        Returns a list of hGraph's dependency edges. Edges are returned via corresponding indices in from and to; that is, the node in to[i] has a dependency on the node in from[i]. from and to may both be NULL, in which case this function only returns the number of edges in numEdges. Otherwise, numEdges entries will be filled in. If numEdges is higher than the actual number of edges, the remaining entries in from and to will be set to NULL, and the number of edges actually returned will be written to numEdges.

        Parameters:
        hGraph - graph to get the edges from
        from - location to return edge endpoints
        to - location to return edge endpoints
        numEdges - see description
      • ncuGraphNodeGetDependencies

        public static int ncuGraphNodeGetDependencies​(long hNode,
                                                      long dependencies,
                                                      long numDependencies)
        Unsafe version of: GraphNodeGetDependencies
        Parameters:
        numDependencies - see description
      • cuGraphNodeGetDependencies

        public static int cuGraphNodeGetDependencies​(long hNode,
                                                     @Nullable
                                                     org.lwjgl.PointerBuffer dependencies,
                                                     org.lwjgl.PointerBuffer numDependencies)
        Returns a node's dependencies.

        Returns a list of node's dependencies. dependencies may be NULL, in which case this function will return the number of dependencies in numDependencies. Otherwise, numDependencies entries will be filled in. If numDependencies is higher than the actual number of dependencies, the remaining entries in dependencies will be set to NULL, and the number of nodes actually obtained will be returned in numDependencies.

        Parameters:
        hNode - node to query
        dependencies - pointer to return the dependencies
        numDependencies - see description
      • ncuGraphNodeGetDependentNodes

        public static int ncuGraphNodeGetDependentNodes​(long hNode,
                                                        long dependentNodes,
                                                        long numDependentNodes)
        Unsafe version of: GraphNodeGetDependentNodes
        Parameters:
        numDependentNodes - see description
      • cuGraphNodeGetDependentNodes

        public static int cuGraphNodeGetDependentNodes​(long hNode,
                                                       @Nullable
                                                       org.lwjgl.PointerBuffer dependentNodes,
                                                       org.lwjgl.PointerBuffer numDependentNodes)
        Returns a node's dependent nodes.

        Returns a list of node's dependent nodes. dependentNodes may be NULL, in which case this function will return the number of dependent nodes in numDependentNodes. Otherwise, numDependentNodes entries will be filled in. If numDependentNodes is higher than the actual number of dependent nodes, the remaining entries in dependentNodes will be set to NULL, and the number of nodes actually obtained will be returned in numDependentNodes.

        Parameters:
        hNode - node to query
        dependentNodes - pointer to return the dependent nodes
        numDependentNodes - see description
      • ncuGraphAddDependencies

        public static int ncuGraphAddDependencies​(long hGraph,
                                                  long from,
                                                  long to,
                                                  long numDependencies)
        Unsafe version of: GraphAddDependencies
        Parameters:
        numDependencies - number of dependencies to be added
      • cuGraphAddDependencies

        public static int cuGraphAddDependencies​(long hGraph,
                                                 @Nullable
                                                 org.lwjgl.PointerBuffer from,
                                                 @Nullable
                                                 org.lwjgl.PointerBuffer to)
        Adds dependency edges to a graph.

        The number of dependencies to be added is defined by numDependencies Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

        If numDependencies is 0, elements in from and to will be ignored. Specifying an existing dependency will return an error.

        Parameters:
        hGraph - graph to which dependencies are added
        from - array of nodes that provide the dependencies
        to - array of dependent nodes
      • ncuGraphRemoveDependencies

        public static int ncuGraphRemoveDependencies​(long hGraph,
                                                     long from,
                                                     long to,
                                                     long numDependencies)
        Unsafe version of: GraphRemoveDependencies
        Parameters:
        numDependencies - number of dependencies to be removed
      • cuGraphRemoveDependencies

        public static int cuGraphRemoveDependencies​(long hGraph,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer from,
                                                    @Nullable
                                                    org.lwjgl.PointerBuffer to)
        Removes dependency edges from a graph.

        The number of dependencies to be removed is defined by numDependencies. Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

        If numDependencies is 0, elements in from and to will be ignored. Specifying a non-existing dependency will return an error.

        Dependencies cannot be removed from graphs which contain allocation or free nodes. Any attempt to do so will return an error.

        Parameters:
        hGraph - graph from which to remove dependencies
        from - array of nodes that provide the dependencies
        to - array of dependent nodes
      • cuGraphDestroyNode

        public static int cuGraphDestroyNode​(long hNode)
        Remove a node from the graph.

        Removes hNode from its graph. This operation also severs any dependencies of other nodes on hNode and vice versa.

        Nodes which belong to a graph which contains allocation or free nodes cannot be destroyed. Any attempt to do so will return an error.

        Parameters:
        hNode - node to remove
      • ncuGraphInstantiate

        public static int ncuGraphInstantiate​(long phGraphExec,
                                              long hGraph,
                                              long phErrorNode,
                                              long logBuffer,
                                              long bufferSize)
        Unsafe version of: GraphInstantiate
        Parameters:
        bufferSize - size of the log buffer in bytes
      • cuGraphInstantiate

        public static int cuGraphInstantiate​(org.lwjgl.PointerBuffer phGraphExec,
                                             long hGraph,
                                             org.lwjgl.PointerBuffer phErrorNode,
                                             java.nio.ByteBuffer logBuffer)
        Creates an executable graph from a graph.

        Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

        If there are any errors, diagnostic information may be returned in errorNode and logBuffer. This is the primary way to inspect instantiation errors. The output will be null terminated unless the diagnostics overflow the buffer. In this case, they will be truncated, and the last byte can be inspected to determine if truncation occurred.

        Parameters:
        phGraphExec - returns instantiated graph
        hGraph - graph to instantiate
        phErrorNode - in case of an instantiation error, this may be modified to indicate a node contributing to the error
        logBuffer - a character buffer to store diagnostic messages
      • ncuGraphInstantiateWithFlags

        public static int ncuGraphInstantiateWithFlags​(long phGraphExec,
                                                       long hGraph,
                                                       long flags)
        Unsafe version of: GraphInstantiateWithFlags
      • cuGraphInstantiateWithFlags

        public static int cuGraphInstantiateWithFlags​(org.lwjgl.PointerBuffer phGraphExec,
                                                      long hGraph,
                                                      long flags)
        Creates an executable graph from a graph.

        Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

        The flags parameter controls the behavior of instantiation and subsequent graph launches. Valid flags are:

        If hGraph contains any allocation or free nodes, there can be at most one executable graph in existence for that graph at a time.

        An attempt to instantiate a second executable graph before destroying the first with GraphExecDestroy will result in an error.

        Parameters:
        phGraphExec - returns instantiated graph
        hGraph - graph to instantiate
        flags - flags to control instantiation. See CUgraphInstantiate_flags.
      • ncuGraphExecKernelNodeSetParams

        public static int ncuGraphExecKernelNodeSetParams​(long hGraphExec,
                                                          long hNode,
                                                          long nodeParams)
        Unsafe version of: GraphExecKernelNodeSetParams
      • cuGraphExecKernelNodeSetParams

        public static int cuGraphExecKernelNodeSetParams​(long hGraphExec,
                                                         long hNode,
                                                         CUDA_KERNEL_NODE_PARAMS nodeParams)
        Sets the parameters for a kernel node in the given graphExec.

        Sets the parameters of a kernel node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

        hNode must not have been removed from the original graph. The func field of nodeParams cannot be modified and must match the original value. All other values can be modified.

        The modifications take effect at the next launch of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - kernel node from the graph from which graphExec was instantiated
        nodeParams - updated parameters to set
      • ncuGraphExecMemcpyNodeSetParams

        public static int ncuGraphExecMemcpyNodeSetParams​(long hGraphExec,
                                                          long hNode,
                                                          long copyParams,
                                                          long ctx)
        Unsafe version of: GraphExecMemcpyNodeSetParams
      • cuGraphExecMemcpyNodeSetParams

        public static int cuGraphExecMemcpyNodeSetParams​(long hGraphExec,
                                                         long hNode,
                                                         CUDA_MEMCPY3D copyParams,
                                                         long ctx)
        Sets the parameters for a memcpy node in the given graphExec.

        Updates the work represented by hNode in hGraphExec as though hNode had contained copyParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

        The source and destination memory in copyParams must be allocated from the same contexts as the original source and destination memory. Both the instantiation-time memory operands and the memory operands in copyParams must be 1-dimensional. Zero-length operations are not supported.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Returns CUDA_ERROR_INVALID_VALUE if the memory operands' mappings changed or either the original or new memory operands are multidimensional.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - memcpy node from the graph which was used to instantiate graphExec
        copyParams - the updated parameters to set
        ctx - context on which to run the node
      • ncuGraphExecMemsetNodeSetParams

        public static int ncuGraphExecMemsetNodeSetParams​(long hGraphExec,
                                                          long hNode,
                                                          long memsetParams,
                                                          long ctx)
        Unsafe version of: GraphExecMemsetNodeSetParams
      • cuGraphExecMemsetNodeSetParams

        public static int cuGraphExecMemsetNodeSetParams​(long hGraphExec,
                                                         long hNode,
                                                         CUDA_MEMSET_NODE_PARAMS memsetParams,
                                                         long ctx)
        Sets the parameters for a memset node in the given graphExec.

        Updates the work represented by hNode in hGraphExec as though hNode had contained memsetParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

        The destination memory in memsetParams must be allocated from the same contexts as the original destination memory. Both the instantiation-time memory operand and the memory operand in memsetParams must be 1-dimensional. Zero-length operations are not supported.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Returns CUDA_ERROR_INVALID_VALUE if the memory operand's mappings changed or either the original or new memory operand are multidimensional.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - memset node from the graph which was used to instantiate graphExec
        memsetParams - the updated parameters to set
        ctx - context on which to run the node
      • ncuGraphExecHostNodeSetParams

        public static int ncuGraphExecHostNodeSetParams​(long hGraphExec,
                                                        long hNode,
                                                        long nodeParams)
        Unsafe version of: GraphExecHostNodeSetParams
      • cuGraphExecHostNodeSetParams

        public static int cuGraphExecHostNodeSetParams​(long hGraphExec,
                                                       long hNode,
                                                       CUDA_HOST_NODE_PARAMS nodeParams)
        Sets the parameters for a host node in the given graphExec.

        Updates the work represented by hNode in hGraphExec as though hNode had contained nodeParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - host node from the graph which was used to instantiate graphExec
        nodeParams - the updated parameters to set
      • cuGraphExecChildGraphNodeSetParams

        public static int cuGraphExecChildGraphNodeSetParams​(long hGraphExec,
                                                             long hNode,
                                                             long childGraph)
        Updates node parameters in the child graph node in the given graphExec.

        Updates the work represented by hNode in hGraphExec as though the nodes contained in hNode's graph had the parameters contained in childGraph's nodes at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        The topology of childGraph, as well as the node insertion order, must match that of the graph contained in hNode. See GraphExecUpdate for a list of restrictions on what can be updated in an instantiated graph. The update is recursive, so child graph nodes contained within the top level child graph will also be updated.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - host node from the graph which was used to instantiate graphExec
        childGraph - the graph supplying the updated parameters
      • cuGraphExecEventRecordNodeSetEvent

        public static int cuGraphExecEventRecordNodeSetEvent​(long hGraphExec,
                                                             long hNode,
                                                             long event)
        Sets the event for an event record node in the given graphExec.

        Sets the event of an event record node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - event record node from the graph from which graphExec was instantiated
        event - updated event to use
      • cuGraphExecEventWaitNodeSetEvent

        public static int cuGraphExecEventWaitNodeSetEvent​(long hGraphExec,
                                                           long hNode,
                                                           long event)
        Sets the event for an event wait node in the given graphExec.

        Sets the event of an event wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - event wait node from the graph from which graphExec was instantiated
        event - updated event to use
      • ncuGraphExecExternalSemaphoresSignalNodeSetParams

        public static int ncuGraphExecExternalSemaphoresSignalNodeSetParams​(long hGraphExec,
                                                                            long hNode,
                                                                            long nodeParams)
      • cuGraphExecExternalSemaphoresSignalNodeSetParams

        public static int cuGraphExecExternalSemaphoresSignalNodeSetParams​(long hGraphExec,
                                                                           long hNode,
                                                                           CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)
        Sets the parameters for an external semaphore signal node in the given graphExec.

        Sets the parameters of an external semaphore signal node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

        hNode must not have been removed from the original graph.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Changing nodeParams->numExtSems is not supported.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - semaphore signal node from the graph from which graphExec was instantiated
        nodeParams - updated Parameters to set
      • ncuGraphExecExternalSemaphoresWaitNodeSetParams

        public static int ncuGraphExecExternalSemaphoresWaitNodeSetParams​(long hGraphExec,
                                                                          long hNode,
                                                                          long nodeParams)
      • cuGraphExecExternalSemaphoresWaitNodeSetParams

        public static int cuGraphExecExternalSemaphoresWaitNodeSetParams​(long hGraphExec,
                                                                         long hNode,
                                                                         CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)
        Sets the parameters for an external semaphore wait node in the given graphExec.

        Sets the parameters of an external semaphore wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

        hNode must not have been removed from the original graph.

        The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

        Changing nodeParams->numExtSems is not supported.

        Parameters:
        hGraphExec - the executable graph in which to set the specified node
        hNode - semaphore wait node from the graph from which graphExec was instantiated
        nodeParams - updated Parameters to set
      • cuGraphUpload

        public static int cuGraphUpload​(long hGraphExec,
                                        long hStream)
        Uploads an executable graph in a stream.

        Uploads hGraphExec to the device in hStream without executing it. Uploads of the same hGraphExec will be serialized. Each upload is ordered behind both any previous work in hStream and any previous launches of hGraphExec. Uses memory cached by stream to back the allocations owned by hGraphExec.

        Parameters:
        hGraphExec - executable graph to upload
        hStream - stream in which to upload the graph
      • cuGraphLaunch

        public static int cuGraphLaunch​(long hGraphExec,
                                        long hStream)
        Launches an executable graph in a stream.

        Executes hGraphExec in hStream. Only one instance of hGraphExec may be executing at a time. Each launch is ordered behind both any previous work in hStream and any previous launches of hGraphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.

        If any allocations created by hGraphExec remain unfreed (from a previous launch) and hGraphExec was not instantiated with CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, the launch will fail with CUDA_ERROR_INVALID_VALUE.

        Parameters:
        hGraphExec - executable graph to launch
        hStream - stream in which to launch the graph
      • cuGraphExecDestroy

        public static int cuGraphExecDestroy​(long hGraphExec)
        Destroys an executable graph.

        Destroys the executable graph specified by hGraphExec, as well as all of its executable nodes. If the executable graph is in-flight, it will not be terminated, but rather freed asynchronously on completion.

        Parameters:
        hGraphExec - executable graph to destroy
      • cuGraphDestroy

        public static int cuGraphDestroy​(long hGraph)
        Destroys a graph.

        Destroys the graph specified by hGraph, as well as all of its nodes.

        Parameters:
        hGraph - graph to destroy
      • ncuGraphExecUpdate

        public static int ncuGraphExecUpdate​(long hGraphExec,
                                             long hGraph,
                                             long hErrorNode_out,
                                             long updateResult_out)
        Unsafe version of: GraphExecUpdate
      • cuGraphExecUpdate

        public static int cuGraphExecUpdate​(long hGraphExec,
                                            long hGraph,
                                            org.lwjgl.PointerBuffer hErrorNode_out,
                                            java.nio.IntBuffer updateResult_out)
        Check whether an executable graph can be updated with a graph and perform the update if possible.

        Updates the node parameters in the instantiated graph specified by hGraphExec with the node parameters in a topologically identical graph specified by hGraph.

        Limitations:

        • Kernel nodes:
          • The owning context of the function cannot change.
          • A node whose function originally did not use CUDA dynamic parallelism cannot be updated to a function which uses CDP
        • Memset and memcpy nodes:
          • The CUDA device(s) to which the operand(s) was allocated/mapped cannot change.
          • The source/destination memory must be allocated from the same contexts as the original source/destination memory.
          • Only 1D memsets can be changed.
        • Additional memcpy node restrictions:
          • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.
        • External semaphore wait nodes and record nodes:
          • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.

        Note: The API may add further restrictions in future releases. The return code should always be checked.

        cuGraphExecUpdate sets updateResult_out to GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED under the following conditions:

        • The count of nodes directly in hGraphExec and hGraph differ, in which case hErrorNode_out is NULL.
        • A node is deleted in hGraph but not not its pair from hGraphExec, in which case hErrorNode_out is NULL.
        • A node is deleted in hGraphExec but not its pair from hGraph, in which case hErrorNode_out is the pairless node from hGraph.
        • The dependent nodes of a pair differ, in which case hErrorNode_out is the node from hGraph.

        cuGraphExecUpdate sets updateResult_out to:

        If updateResult_out isn't set in one of the situations described above, the update check passes and cuGraphExecUpdate updates hGraphExec to match the contents of hGraph. If an error happens during the update, updateResult_out will be set to GRAPH_EXEC_UPDATE_ERROR; otherwise, updateResult_out is set to GRAPH_EXEC_UPDATE_SUCCESS.

        cuGraphExecUpdate returns CUDA_SUCCESS when the updated was performed successfully. It returns CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

        Parameters:
        hGraphExec - the instantiated graph to be updated
        hGraph - the graph containing the updated parameters
        hErrorNode_out - the node which caused the permissibility check to forbid the update, if any
        updateResult_out - whether the graph update was permitted. If was forbidden, the reason why.
      • cuGraphKernelNodeCopyAttributes

        public static int cuGraphKernelNodeCopyAttributes​(long dst,
                                                          long src)
        Copies attributes from source node to destination node.

        Copies attributes from source node src to destination node dst. Both node must have the same context.

        Parameters:
        dst - destination node
        src - source node. For list of attributes see CUkernelNodeAttrID.
      • ncuGraphKernelNodeGetAttribute

        public static int ncuGraphKernelNodeGetAttribute​(long hNode,
                                                         int attr,
                                                         long value_out)
        Unsafe version of: GraphKernelNodeGetAttribute
      • cuGraphKernelNodeGetAttribute

        public static int cuGraphKernelNodeGetAttribute​(long hNode,
                                                        int attr,
                                                        CUkernelNodeAttrValue value_out)
        Queries node attribute.

        Queries attribute attr from node hNode and stores it in corresponding member of value_out.

      • ncuGraphKernelNodeSetAttribute

        public static int ncuGraphKernelNodeSetAttribute​(long hNode,
                                                         int attr,
                                                         long value)
        Unsafe version of: GraphKernelNodeSetAttribute
      • cuGraphKernelNodeSetAttribute

        public static int cuGraphKernelNodeSetAttribute​(long hNode,
                                                        int attr,
                                                        CUkernelNodeAttrValue value)
        Sets node attribute.

        Sets attribute attr on node hNode from corresponding attribute of value.

      • ncuGraphDebugDotPrint

        public static int ncuGraphDebugDotPrint​(long hGraph,
                                                long path,
                                                int flags)
        Unsafe version of: GraphDebugDotPrint
      • cuGraphDebugDotPrint

        public static int cuGraphDebugDotPrint​(long hGraph,
                                               java.nio.ByteBuffer path,
                                               int flags)
        
        public static int cuGraphDebugDotPrint​(long hGraph,
                                               java.lang.CharSequence path,
                                               int flags)
        
        Write a DOT file describing graph structure.

        Using the provided hGraph, write to path a DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction. flags can be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.

        Parameters:
        hGraph - the graph to create a DOT file from
        path - the path to write the DOT file to
        flags - flags from CUgraphDebugDot_flags for specifying which additional node information to write
      • ncuUserObjectCreate

        public static int ncuUserObjectCreate​(long object_out,
                                              long ptr,
                                              long destroy,
                                              int initialRefcount,
                                              int flags)
        Unsafe version of: UserObjectCreate
      • cuUserObjectCreate

        public static int cuUserObjectCreate​(org.lwjgl.PointerBuffer object_out,
                                             long ptr,
                                             CUhostFnI destroy,
                                             int initialRefcount,
                                             int flags)
        Create a user object.

        Create a user object with the specified destructor callback and initial reference count. The initial references are owned by the caller.

        Destructor callbacks cannot make CUDA API calls and should avoid blocking behavior, as they are executed by a shared internal thread. Another thread may be signaled to perform such actions, if it does not block forward progress of tasks scheduled through CUDA.

        See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

        Parameters:
        object_out - location to return the user object handle
        ptr - the pointer to pass to the destroy function
        destroy - callback to free the user object when it is no longer in use
        initialRefcount - the initial refcount to create the object with, typically 1. The initial references are owned by the calling thread.
        flags - currently it is required to pass USER_OBJECT_NO_DESTRUCTOR_SYNC, which is the only defined flag. This indicates that the destroy callback cannot be waited on by any CUDA API. Users requiring synchronization of the callback should signal its completion manually.
      • cuUserObjectRetain

        public static int cuUserObjectRetain​(long object,
                                             int count)
        Retain a reference to a user object.

        Retains new references to a user object. The new references are owned by the caller.

        See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

        Parameters:
        object - the object to retain
        count - the number of references to retain, typically 1. Must be nonzero and not larger than INT_MAX.
      • cuUserObjectRelease

        public static int cuUserObjectRelease​(long object,
                                              int count)
        Release a reference to a user object.

        Releases user object references owned by the caller. The object's destructor is invoked if the reference count reaches zero.

        It is undefined behavior to release references not owned by the caller, or to use a user object handle after all references are released.

        See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

        Parameters:
        object - the object to release
        count - the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
      • cuGraphRetainUserObject

        public static int cuGraphRetainUserObject​(long graph,
                                                  long object,
                                                  int count,
                                                  int flags)
        Retain a reference to a user object from a graph.

        Creates or moves user object references that will be owned by a CUDA graph.

        See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

        Parameters:
        graph - the graph to associate the reference with
        object - the user object to retain a reference for
        count - the number of references to add to the graph, typically 1. Must be nonzero and not larger than INT_MAX.
        flags - the optional flag GRAPH_USER_OBJECT_MOVE transfers references from the calling thread, rather than create new references. Pass 0 to create new references.
      • cuGraphReleaseUserObject

        public static int cuGraphReleaseUserObject​(long graph,
                                                   long object,
                                                   int count)
        Release a user object reference from a graph.

        Releases user object references owned by a graph.

        See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

        Parameters:
        graph - the graph that will release the reference
        object - the user object to release a reference for
        count - the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
      • ncuOccupancyMaxActiveBlocksPerMultiprocessor

        public static int ncuOccupancyMaxActiveBlocksPerMultiprocessor​(long numBlocks,
                                                                       long func,
                                                                       int blockSize,
                                                                       long dynamicSMemSize)
      • cuOccupancyMaxActiveBlocksPerMultiprocessor

        public static int cuOccupancyMaxActiveBlocksPerMultiprocessor​(java.nio.IntBuffer numBlocks,
                                                                      long func,
                                                                      int blockSize,
                                                                      long dynamicSMemSize)
        Returns occupancy of a function.

        Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

        Parameters:
        numBlocks - returned occupancy
        func - kernel for which occupancy is calculated
        blockSize - block size the kernel is intended to be launched with
        dynamicSMemSize - per-block dynamic shared memory usage intended, in bytes
      • ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags

        public static int ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags​(long numBlocks,
                                                                                long func,
                                                                                int blockSize,
                                                                                long dynamicSMemSize,
                                                                                int flags)
      • cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags

        public static int cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags​(java.nio.IntBuffer numBlocks,
                                                                               long func,
                                                                               int blockSize,
                                                                               long dynamicSMemSize,
                                                                               int flags)
        Returns occupancy of a function.

        Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

        The Flags parameter controls how special cases are handled. The valid flags are:

        • OCCUPANCY_DEFAULT, which maintains the default behavior as OccupancyMaxActiveBlocksPerMultiprocessor;
        • OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is disabled. Setting OCCUPANCY_DISABLE_CACHING_OVERRIDE makes the occupancy calculator to return 0 in such cases. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.
        Parameters:
        numBlocks - returned occupancy
        func - kernel for which occupancy is calculated
        blockSize - block size the kernel is intended to be launched with
        dynamicSMemSize - per-block dynamic shared memory usage intended, in bytes
        flags - requested behavior for the occupancy calculator
      • ncuOccupancyMaxPotentialBlockSize

        public static int ncuOccupancyMaxPotentialBlockSize​(long minGridSize,
                                                            long blockSize,
                                                            long func,
                                                            long blockSizeToDynamicSMemSize,
                                                            long dynamicSMemSize,
                                                            int blockSizeLimit)
      • cuOccupancyMaxPotentialBlockSize

        public static int cuOccupancyMaxPotentialBlockSize​(java.nio.IntBuffer minGridSize,
                                                           java.nio.IntBuffer blockSize,
                                                           long func,
                                                           @Nullable
                                                           CUoccupancyB2DSizeI blockSizeToDynamicSMemSize,
                                                           long dynamicSMemSize,
                                                           int blockSizeLimit)
        Suggest a launch configuration with reasonable occupancy.

        Returns in *blockSize a reasonable block size that can achieve the maximum occupancy (or, the maximum number of active warps with the fewest blocks per multiprocessor), and in *minGridSize the minimum grid size to achieve the maximum occupancy.

        If blockSizeLimit is 0, the configurator will use the maximum block size permitted by the device / function instead.

        If per-block dynamic shared memory allocation is not needed, the user should leave both blockSizeToDynamicSMemSize and dynamicSMemSize as 0.

        If per-block dynamic shared memory allocation is needed, then if the dynamic shared memory size is constant regardless of block size, the size should be passed through dynamicSMemSize, and blockSizeToDynamicSMemSize should be NULL.

        Otherwise, if the per-block dynamic shared memory size varies with different block sizes, the user needs to provide a unary function through blockSizeToDynamicSMemSize that computes the dynamic shared memory needed by func for any given block size. dynamicSMemSize is ignored. An example signature is:

        
         // Take block size, returns dynamic shared memory needed
         size_t blockToSmem(int blockSize);
        Parameters:
        minGridSize - returned minimum grid size needed to achieve the maximum occupancy
        blockSize - returned maximum block size that can achieve the maximum occupancy
        func - kernel for which launch configuration is calculated
        blockSizeToDynamicSMemSize - a function that calculates how much per-block dynamic shared memory func uses based on the block size
        dynamicSMemSize - dynamic shared memory usage intended, in bytes
        blockSizeLimit - the maximum block size func is designed to handle
      • ncuOccupancyMaxPotentialBlockSizeWithFlags

        public static int ncuOccupancyMaxPotentialBlockSizeWithFlags​(long minGridSize,
                                                                     long blockSize,
                                                                     long func,
                                                                     long blockSizeToDynamicSMemSize,
                                                                     long dynamicSMemSize,
                                                                     int blockSizeLimit,
                                                                     int flags)
      • cuOccupancyMaxPotentialBlockSizeWithFlags

        public static int cuOccupancyMaxPotentialBlockSizeWithFlags​(java.nio.IntBuffer minGridSize,
                                                                    java.nio.IntBuffer blockSize,
                                                                    long func,
                                                                    @Nullable
                                                                    CUoccupancyB2DSizeI blockSizeToDynamicSMemSize,
                                                                    long dynamicSMemSize,
                                                                    int blockSizeLimit,
                                                                    int flags)
        Suggest a launch configuration with reasonable occupancy.

        An extended version of OccupancyMaxPotentialBlockSize. In addition to arguments passed to OccupancyMaxPotentialBlockSize, OccupancyMaxPotentialBlockSizeWithFlags also takes a Flags parameter.

        The Flags parameter controls how special cases are handled. The valid flags are:

        • OCCUPANCY_DEFAULT, which maintains the default behavior as OccupancyMaxPotentialBlockSize;
        • OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, the launch configurations that produces maximal occupancy might not support global caching. Setting OCCUPANCY_DISABLE_CACHING_OVERRIDE guarantees that the the produced launch configuration is global caching compatible at a potential cost of occupancy. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.
        Parameters:
        minGridSize - returned minimum grid size needed to achieve the maximum occupancy
        blockSize - returned maximum block size that can achieve the maximum occupancy
        func - kernel for which launch configuration is calculated
        blockSizeToDynamicSMemSize - a function that calculates how much per-block dynamic shared memory func uses based on the block size
        dynamicSMemSize - dynamic shared memory usage intended, in bytes
        blockSizeLimit - the maximum block size func is designed to handle
        flags - options
      • ncuOccupancyAvailableDynamicSMemPerBlock

        public static int ncuOccupancyAvailableDynamicSMemPerBlock​(long dynamicSmemSize,
                                                                   long func,
                                                                   int numBlocks,
                                                                   int blockSize)
      • cuOccupancyAvailableDynamicSMemPerBlock

        public static int cuOccupancyAvailableDynamicSMemPerBlock​(org.lwjgl.PointerBuffer dynamicSmemSize,
                                                                  long func,
                                                                  int numBlocks,
                                                                  int blockSize)
        Returns dynamic shared memory available per block when launching numBlocks blocks on SM.

        Returns in *dynamicSmemSize the maximum size of dynamic shared memory to allow numBlocks blocks per SM.

        Parameters:
        dynamicSmemSize - returned maximum dynamic shared memory
        func - kernel function for which occupancy is calculated
        numBlocks - number of blocks to fit on SM
        blockSize - size of the blocks
      • cuTexRefSetArray

        public static int cuTexRefSetArray​(long hTexRef,
                                           long hArray,
                                           int Flags)
        Binds an array as a texture reference. (Deprecated)

        Binds the CUDA array hArray to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Flags must be set to TRSA_OVERRIDE_FORMAT. Any CUDA array previously bound to hTexRef is unbound.

        Parameters:
        hTexRef - texture reference to bind
        hArray - array to bind
        Flags - options (must be TRSA_OVERRIDE_FORMAT)
      • cuTexRefSetMipmappedArray

        public static int cuTexRefSetMipmappedArray​(long hTexRef,
                                                    long hMipmappedArray,
                                                    int Flags)
        Binds a mipmapped array to a texture reference. (Deprecated)

        Binds the CUDA mipmapped array hMipmappedArray to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Flags must be set to TRSA_OVERRIDE_FORMAT. Any CUDA array previously bound to hTexRef is unbound.

        Parameters:
        hTexRef - texture reference to bind
        hMipmappedArray - mipmapped array to bind
        Flags - options (must be TRSA_OVERRIDE_FORMAT)
      • ncuTexRefSetAddress

        public static int ncuTexRefSetAddress​(long ByteOffset,
                                              long hTexRef,
                                              long dptr,
                                              long bytes)
        Unsafe version of: TexRefSetAddress
      • cuTexRefSetAddress

        public static int cuTexRefSetAddress​(org.lwjgl.PointerBuffer ByteOffset,
                                             long hTexRef,
                                             long dptr,
                                             long bytes)
        Binds an address as a texture reference. (Deprecated)

        Binds a linear address range to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Any memory previously bound to hTexRef is unbound.

        Since the hardware enforces an alignment requirement on texture base addresses, TexRefSetAddress passes back a byte offset in *ByteOffset that must be applied to texture fetches in order to read from the desired memory. This offset must be divided by the texel size and passed to kernels that read from the texture so they can be applied to the tex1Dfetch() function.

        If the device memory pointer was returned from MemAlloc, the offset is guaranteed to be 0 and NULL may be passed as the ByteOffset parameter.

        The total number of elements (or texels) in the linear address range cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (bytes / bytesPerElement), where bytesPerElement is determined from the data format and number of components set using TexRefSetFormat.

        Parameters:
        ByteOffset - returned byte offset
        hTexRef - texture reference to bind
        dptr - device pointer to bind
        bytes - size of memory to bind in bytes
      • ncuTexRefSetAddress2D

        public static int ncuTexRefSetAddress2D​(long hTexRef,
                                                long desc,
                                                long dptr,
                                                long Pitch)
        Unsafe version of: TexRefSetAddress2D
      • cuTexRefSetFormat

        public static int cuTexRefSetFormat​(long hTexRef,
                                            int fmt,
                                            int NumPackedComponents)
        Sets the format for a texture reference. (Deprecated)

        Specifies the format of the data to be read by the texture reference hTexRef. fmt and NumPackedComponents are exactly analogous to the Format and NumChannels members of the CUDA_ARRAY_DESCRIPTOR structure: They specify the format of each component and the number of components per array element.

        Parameters:
        hTexRef - texture reference
        fmt - format to set
        NumPackedComponents - number of components per array element
      • cuTexRefSetAddressMode

        public static int cuTexRefSetAddressMode​(long hTexRef,
                                                 int dim,
                                                 int am)
        Sets the addressing mode for a texture reference. (Deprecated)

        Specifies the addressing mode am for the given dimension dim of the texture reference hTexRef. If dim is zero, the addressing mode is applied to the first parameter of the functions used to fetch from the texture; if dim is 1, the second, and so on.

        Note that this call has no effect if hTexRef is bound to linear memory. Also, if the flag, TRSF_NORMALIZED_COORDINATES, is not set, the only supported address mode is TR_ADDRESS_MODE_CLAMP.

        Parameters:
        hTexRef - texture reference
        dim - dimension
        am - addressing mode to set
      • cuTexRefSetFilterMode

        public static int cuTexRefSetFilterMode​(long hTexRef,
                                                int fm)
        Sets the filtering mode for a texture reference. (Deprecated)

        Specifies the filtering mode fm to be used when reading memory through the texture reference hTexRef.

        Note that this call has no effect if hTexRef is bound to linear memory.

        Parameters:
        hTexRef - texture reference
        fm - filtering mode to set
      • cuTexRefSetMipmapFilterMode

        public static int cuTexRefSetMipmapFilterMode​(long hTexRef,
                                                      int fm)
        Sets the mipmap filtering mode for a texture reference (Deprecated)

        Specifies the mipmap filtering mode fm to be used when reading memory through the texture reference hTexRef.

        Note that this call has no effect if hTexRef is not bound to a mipmapped array.

        Parameters:
        hTexRef - texture reference
        fm - filtering mode to set
      • cuTexRefSetMipmapLevelBias

        public static int cuTexRefSetMipmapLevelBias​(long hTexRef,
                                                     float bias)
        Sets the mipmap level bias for a texture reference. (Deprecated)

        Specifies the mipmap level bias bias to be added to the specified mipmap level when reading memory through the texture reference hTexRef.

        Note that this call has no effect if hTexRef is not bound to a mipmapped array.

        Parameters:
        hTexRef - texture reference
        bias - mipmap level bias
      • cuTexRefSetMipmapLevelClamp

        public static int cuTexRefSetMipmapLevelClamp​(long hTexRef,
                                                      float minMipmapLevelClamp,
                                                      float maxMipmapLevelClamp)
        Sets the mipmap min/max mipmap level clamps for a texture reference. (Deprecated)

        Specifies the min/max mipmap level clamps, minMipmapLevelClamp and maxMipmapLevelClamp respectively, to be used when reading memory through the texture reference hTexRef.

        Note that this call has no effect if hTexRef is not bound to a mipmapped array.

        Parameters:
        hTexRef - texture reference
        minMipmapLevelClamp - mipmap min level clamp
        maxMipmapLevelClamp - mipmap max level clamp
      • cuTexRefSetMaxAnisotropy

        public static int cuTexRefSetMaxAnisotropy​(long hTexRef,
                                                   int maxAniso)
        Sets the maximum anisotropy for a texture reference. (Deprecated)

        Specifies the maximum anisotropy maxAniso to be used when reading memory through the texture reference hTexRef.

        Note that this call has no effect if hTexRef is bound to linear memory.

        Parameters:
        hTexRef - texture reference
        maxAniso - maximum anisotropy
      • ncuTexRefSetBorderColor

        public static int ncuTexRefSetBorderColor​(long hTexRef,
                                                  long pBorderColor)
        Unsafe version of: TexRefSetBorderColor
      • cuTexRefSetBorderColor

        public static int cuTexRefSetBorderColor​(long hTexRef,
                                                 java.nio.FloatBuffer pBorderColor)
        Sets the border color for a texture reference. (Deprecated)

        Specifies the value of the RGBA color via the pBorderColor to the texture reference hTexRef. The color value supports only float type and holds color components in the following sequence: pBorderColor[0] holds 'R' component pBorderColor[1] holds 'G' component pBorderColor[2] holds 'B' component pBorderColor[3] holds 'A' component.

        Note that the color values can be set only when the Address mode is set to TR_ADDRESS_MODE_BORDER using TexRefSetAddressMode. Applications using integer border color values have to "reinterpret_cast" their values to float.

        Parameters:
        hTexRef - texture reference
        pBorderColor - RGBA color
      • cuTexRefSetFlags

        public static int cuTexRefSetFlags​(long hTexRef,
                                           int Flags)
        Sets the flags for a texture reference. (Deprecated)

        Specifies optional flags via Flags to specify the behavior of data returned through the texture reference hTexRef. The valid flags are:

        • TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified;
        • TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension;
        • TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.
        Parameters:
        hTexRef - texture reference
        Flags - optional flags to set
      • ncuTexRefGetAddress

        public static int ncuTexRefGetAddress​(long pdptr,
                                              long hTexRef)
        Unsafe version of: TexRefGetAddress
      • cuTexRefGetAddress

        public static int cuTexRefGetAddress​(org.lwjgl.PointerBuffer pdptr,
                                             long hTexRef)
        Gets the address associated with a texture reference. (Deprecated)

        Returns in *pdptr the base address bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any device memory range.

        Parameters:
        pdptr - returned device address
        hTexRef - texture reference
      • ncuTexRefGetArray

        public static int ncuTexRefGetArray​(long phArray,
                                            long hTexRef)
        Unsafe version of: TexRefGetArray
      • cuTexRefGetArray

        public static int cuTexRefGetArray​(org.lwjgl.PointerBuffer phArray,
                                           long hTexRef)
        Gets the array bound to a texture reference. (Deprecated)

        Returns in *phArray the CUDA array bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any CUDA array.

        Parameters:
        phArray - returned array
        hTexRef - texture reference
      • ncuTexRefGetMipmappedArray

        public static int ncuTexRefGetMipmappedArray​(long phMipmappedArray,
                                                     long hTexRef)
        Unsafe version of: TexRefGetMipmappedArray
      • cuTexRefGetMipmappedArray

        public static int cuTexRefGetMipmappedArray​(org.lwjgl.PointerBuffer phMipmappedArray,
                                                    long hTexRef)
        Gets the mipmapped array bound to a texture reference. (Deprecated)

        Returns in *phMipmappedArray the CUDA mipmapped array bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any CUDA mipmapped array.

        Parameters:
        phMipmappedArray - returned mipmapped array
        hTexRef - texture reference
      • ncuTexRefGetAddressMode

        public static int ncuTexRefGetAddressMode​(long pam,
                                                  long hTexRef,
                                                  int dim)
        Unsafe version of: TexRefGetAddressMode
      • cuTexRefGetAddressMode

        public static int cuTexRefGetAddressMode​(java.nio.IntBuffer pam,
                                                 long hTexRef,
                                                 int dim)
        Gets the addressing mode used by a texture reference. (Deprecated)

        Returns in *pam the addressing mode corresponding to the dimension dim of the texture reference hTexRef. Currently, the only valid value for dim are 0 and 1.

        Parameters:
        pam - returned addressing mode
        hTexRef - texture reference
        dim - dimension
      • ncuTexRefGetFilterMode

        public static int ncuTexRefGetFilterMode​(long pfm,
                                                 long hTexRef)
        Unsafe version of: TexRefGetFilterMode
      • cuTexRefGetFilterMode

        public static int cuTexRefGetFilterMode​(java.nio.IntBuffer pfm,
                                                long hTexRef)
        Gets the filter-mode used by a texture reference. (Deprecated)

        Returns in *pfm the filtering mode of the texture reference hTexRef.

        Parameters:
        pfm - returned filtering mode
        hTexRef - texture reference
      • ncuTexRefGetFormat

        public static int ncuTexRefGetFormat​(long pFormat,
                                             long pNumChannels,
                                             long hTexRef)
        Unsafe version of: TexRefGetFormat
      • cuTexRefGetFormat

        public static int cuTexRefGetFormat​(java.nio.IntBuffer pFormat,
                                            @Nullable
                                            java.nio.IntBuffer pNumChannels,
                                            long hTexRef)
        Gets the format used by a texture reference. (Deprecated)

        Returns in *pFormat and *pNumChannels the format and number of components of the CUDA array bound to the texture reference hTexRef. If pFormat or pNumChannels is NULL, it will be ignored.

        Parameters:
        pFormat - returned format
        pNumChannels - returned number of components
        hTexRef - texture reference
      • ncuTexRefGetMipmapFilterMode

        public static int ncuTexRefGetMipmapFilterMode​(long pfm,
                                                       long hTexRef)
        Unsafe version of: TexRefGetMipmapFilterMode
      • cuTexRefGetMipmapFilterMode

        public static int cuTexRefGetMipmapFilterMode​(java.nio.IntBuffer pfm,
                                                      long hTexRef)
        Gets the mipmap filtering mode for a texture reference. (Deprecated)

        Returns the mipmap filtering mode in pfm that's used when reading memory through the texture reference hTexRef.

        Parameters:
        pfm - returned mipmap filtering mode
        hTexRef - texture reference
      • ncuTexRefGetMipmapLevelBias

        public static int ncuTexRefGetMipmapLevelBias​(long pbias,
                                                      long hTexRef)
        Unsafe version of: TexRefGetMipmapLevelBias
      • cuTexRefGetMipmapLevelBias

        public static int cuTexRefGetMipmapLevelBias​(java.nio.FloatBuffer pbias,
                                                     long hTexRef)
        Gets the mipmap level bias for a texture reference. (Deprecated)

        Returns the mipmap level bias in pBias that's added to the specified mipmap level when reading memory through the texture reference hTexRef.

        Parameters:
        pbias - returned mipmap level bias
        hTexRef - texture reference
      • ncuTexRefGetMipmapLevelClamp

        public static int ncuTexRefGetMipmapLevelClamp​(long pminMipmapLevelClamp,
                                                       long pmaxMipmapLevelClamp,
                                                       long hTexRef)
        Unsafe version of: TexRefGetMipmapLevelClamp
      • cuTexRefGetMipmapLevelClamp

        public static int cuTexRefGetMipmapLevelClamp​(java.nio.FloatBuffer pminMipmapLevelClamp,
                                                      java.nio.FloatBuffer pmaxMipmapLevelClamp,
                                                      long hTexRef)
        Gets the min/max mipmap level clamps for a texture reference. (Deprecated)

        Returns the min/max mipmap level clamps in pminMipmapLevelClamp and pmaxMipmapLevelClamp that's used when reading memory through the texture reference hTexRef.

        Parameters:
        pminMipmapLevelClamp - returned mipmap min level clamp
        pmaxMipmapLevelClamp - returned mipmap max level clamp
        hTexRef - texture reference
      • ncuTexRefGetMaxAnisotropy

        public static int ncuTexRefGetMaxAnisotropy​(long pmaxAniso,
                                                    long hTexRef)
        Unsafe version of: TexRefGetMaxAnisotropy
      • cuTexRefGetMaxAnisotropy

        public static int cuTexRefGetMaxAnisotropy​(java.nio.IntBuffer pmaxAniso,
                                                   long hTexRef)
        Gets the maximum anisotropy for a texture reference. (Deprecated)

        Returns the maximum anisotropy in pmaxAniso that's used when reading memory through the texture reference hTexRef.

        Parameters:
        pmaxAniso - returned maximum anisotropy
        hTexRef - texture reference
      • ncuTexRefGetBorderColor

        public static int ncuTexRefGetBorderColor​(long pBorderColor,
                                                  long hTexRef)
        Unsafe version of: TexRefGetBorderColor
      • cuTexRefGetBorderColor

        public static int cuTexRefGetBorderColor​(java.nio.FloatBuffer pBorderColor,
                                                 long hTexRef)
        Gets the border color used by a texture reference. (Deprecated)

        Returns in pBorderColor, values of the RGBA color used by the texture reference hTexRef. The color value is of type float and holds color components in the following sequence: pBorderColor[0] holds 'R' component pBorderColor[1] holds 'G' component pBorderColor[2] holds 'B' component pBorderColor[3] holds 'A' component

        Parameters:
        pBorderColor - returned Type and Value of RGBA color
        hTexRef - texture reference
      • ncuTexRefGetFlags

        public static int ncuTexRefGetFlags​(long pFlags,
                                            long hTexRef)
        Unsafe version of: TexRefGetFlags
      • cuTexRefGetFlags

        public static int cuTexRefGetFlags​(java.nio.IntBuffer pFlags,
                                           long hTexRef)
        Gets the flags used by a texture reference. (Deprecated)

        Returns in *pFlags the flags of the texture reference hTexRef.

        Parameters:
        pFlags - returned flags
        hTexRef - texture reference
      • ncuTexRefCreate

        public static int ncuTexRefCreate​(long pTexRef)
        Unsafe version of: TexRefCreate
      • cuTexRefCreate

        public static int cuTexRefCreate​(org.lwjgl.PointerBuffer pTexRef)
        Creates a texture reference. (Deprecated)

        Creates a texture reference and returns its handle in *pTexRef. Once created, the application must call TexRefSetArray or TexRefSetAddress to associate the reference with allocated memory. Other texture reference functions are used to specify the format and interpretation (addressing, filtering, etc.) to be used when the memory is read through this texture reference.

        Parameters:
        pTexRef - returned texture reference
      • cuTexRefDestroy

        public static int cuTexRefDestroy​(long hTexRef)
        Destroys a texture reference. (Deprecated)

        Destroys the texture reference specified by hTexRef.

        Parameters:
        hTexRef - texture reference to destroy
      • cuSurfRefSetArray

        public static int cuSurfRefSetArray​(long hSurfRef,
                                            long hArray,
                                            int Flags)
        Sets the CUDA array for a surface reference.Deprecated:

        Sets the CUDA array hArray to be read and written by the surface reference hSurfRef. Any previous CUDA array state associated with the surface reference is superseded by this function. Flags must be set to 0. The CUDA_ARRAY3D_SURFACE_LDST flag must have been set for the CUDA array. Any CUDA array previously bound to hSurfRef is unbound.

        Parameters:
        hSurfRef - surface reference handle
        hArray - CUDA array handle
        Flags - set to 0
      • ncuSurfRefGetArray

        public static int ncuSurfRefGetArray​(long phArray,
                                             long hSurfRef)
        Unsafe version of: SurfRefGetArray
      • cuSurfRefGetArray

        public static int cuSurfRefGetArray​(org.lwjgl.PointerBuffer phArray,
                                            long hSurfRef)
        Passes back the CUDA array bound to a surface reference. (Deprecated)

        Returns in *phArray the CUDA array bound to the surface reference hSurfRef, or returns CUDA_ERROR_INVALID_VALUE if the surface reference is not bound to any CUDA array.

        Parameters:
        phArray - surface reference handle
        hSurfRef - surface reference handle
      • ncuTexObjectCreate

        public static int ncuTexObjectCreate​(long pTexObject,
                                             long pResDesc,
                                             long pTexDesc,
                                             long pResViewDesc)
        Unsafe version of: TexObjectCreate
      • cuTexObjectCreate

        public static int cuTexObjectCreate​(java.nio.LongBuffer pTexObject,
                                            CUDA_RESOURCE_DESC pResDesc,
                                            CUDA_TEXTURE_DESC pTexDesc,
                                            CUDA_RESOURCE_VIEW_DESC pResViewDesc)
        Creates a texture object.

        Creates a texture object and returns it in pTexObject. pResDesc describes the data to texture from. pTexDesc describes how the data should be sampled. pResViewDesc is an optional argument that specifies an alternate format for the data described by pResDesc, and also describes the subresource region to restrict access to when texturing. pResViewDesc can only be specified if the type of resource is a CUDA array or a CUDA mipmapped array.

        Texture objects are only supported on devices of compute capability 3.0 or higher. Additionally, a texture object is an opaque value, and, as such, should only be accessed through CUDA API calls.

        • CUDA_TEXTURE_DESC::addressMode specifies the addressing mode for each dimension of the texture data. This is ignored if CUDA_RESOURCE_DESC::resType is RESOURCE_TYPE_LINEAR. Also, if the flag, TRSF_NORMALIZED_COORDINATES is not set, the only supported address mode is TR_ADDRESS_MODE_CLAMP.
        • CUDA_TEXTURE_DESC::filterMode specifies the filtering mode to be used when fetching from the texture. This is ignored if CUDA_RESOURCE_DESC::resType is RESOURCE_TYPE_LINEAR.
        • CUDA_TEXTURE_DESC::flags can be any combination of the following:
          • TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified.
          • TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension; Note that for CUDA mipmapped arrays, this flag has to be set.
          • TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.
        • CUDA_TEXTURE_DESC::maxAnisotropy specifies the maximum anisotropy ratio to be used when doing anisotropic filtering. This value will be clamped to the range [1,16].
        • CUDA_TEXTURE_DESC::mipmapFilterMode specifies the filter mode when the calculated mipmap level lies between two defined mipmap levels.
        • CUDA_TEXTURE_DESC::mipmapLevelBias specifies the offset to be applied to the calculated mipmap level.
        • CUDA_TEXTURE_DESC::minMipmapLevelClamp specifies the lower end of the mipmap level range to clamp access to.
        • CUDA_TEXTURE_DESC::maxMipmapLevelClamp specifies the upper end of the mipmap level range to clamp access to.
        • CUDA_RESOURCE_VIEW_DESC::format specifies how the data contained in the CUDA array or CUDA mipmapped array should be interpreted. Note that this can incur a change in size of the texture data. If the resource view format is a block compressed format, then the underlying CUDA array or CUDA mipmapped array has to have a base of format AD_FORMAT_UNSIGNED_INT32. with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have a format of AD_FORMAT_UNSIGNED_INT32 with 2 channels. The other BC formats require the underlying resource to have the same base format but with 4 channels.
        • CUDA_RESOURCE_VIEW_DESC::width specifies the new width of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original width of the resource. For non block compressed formats, this value has to be equal to that of the original resource.
        • CUDA_RESOURCE_VIEW_DESC::height specifies the new height of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original height of the resource. For non block compressed formats, this value has to be equal to that of the original resource.
        • CUDA_RESOURCE_VIEW_DESC::depth specifies the new depth of the texture data. This value has to be equal to that of the original resource.
        • CUDA_RESOURCE_VIEW_DESC::firstMipmapLevel specifies the most detailed mipmap level. This will be the new mipmap level zero. For non-mipmapped resources, this value has to be zero. CUDA_TEXTURE_DESC::minMipmapLevelClamp and CUDA_TEXTURE_DESC::maxMipmapLevelClamp will be relative to this value. For ex., if the firstMipmapLevel is set to 2, and a minMipmapLevelClamp of 1.2 is specified, then the actual minimum mipmap level clamp will be 3.2.
        • CUDA_RESOURCE_VIEW_DESC::lastMipmapLevel specifies the least detailed mipmap level. For non-mipmapped resources, this value has to be zero.
        • CUDA_RESOURCE_VIEW_DESC::firstLayer specifies the first layer index for layered textures. This will be the new layer zero. For non-layered resources, this value has to be zero.
        • CUDA_RESOURCE_VIEW_DESC::lastLayer specifies the last layer index for layered textures. For non-layered resources, this value has to be zero.
        Parameters:
        pTexObject - texture object to create
        pResDesc - resource descriptor
        pTexDesc - texture descriptor
        pResViewDesc - resource view descriptor
      • cuTexObjectDestroy

        public static int cuTexObjectDestroy​(long texObject)
        Destroys a texture object.

        Destroys the texture object specified by texObject.

        Parameters:
        texObject - texture object to destroy
      • ncuTexObjectGetResourceDesc

        public static int ncuTexObjectGetResourceDesc​(long pResDesc,
                                                      long texObject)
        Unsafe version of: TexObjectGetResourceDesc
      • cuTexObjectGetResourceDesc

        public static int cuTexObjectGetResourceDesc​(CUDA_RESOURCE_DESC pResDesc,
                                                     long texObject)
        Returns a texture object's resource descriptor.

        Returns the resource descriptor for the texture object specified by texObject.

        Parameters:
        pResDesc - resource descriptor
        texObject - texture object
      • ncuTexObjectGetTextureDesc

        public static int ncuTexObjectGetTextureDesc​(long pTexDesc,
                                                     long texObject)
        Unsafe version of: TexObjectGetTextureDesc
      • cuTexObjectGetTextureDesc

        public static int cuTexObjectGetTextureDesc​(CUDA_TEXTURE_DESC pTexDesc,
                                                    long texObject)
        Returns a texture object's texture descriptor.

        Returns the texture descriptor for the texture object specified by texObject.

        Parameters:
        pTexDesc - texture descriptor
        texObject - texture object
      • ncuTexObjectGetResourceViewDesc

        public static int ncuTexObjectGetResourceViewDesc​(long pResViewDesc,
                                                          long texObject)
        Unsafe version of: TexObjectGetResourceViewDesc
      • cuTexObjectGetResourceViewDesc

        public static int cuTexObjectGetResourceViewDesc​(CUDA_RESOURCE_VIEW_DESC pResViewDesc,
                                                         long texObject)
        Returns a texture object's resource view descriptor.

        Returns the resource view descriptor for the texture object specified by texObject. If no resource view was set for texObject, the CUDA_ERROR_INVALID_VALUE is returned.

        Parameters:
        pResViewDesc - resource view descriptor
        texObject - texture object
      • ncuSurfObjectCreate

        public static int ncuSurfObjectCreate​(long pSurfObject,
                                              long pResDesc)
        Unsafe version of: SurfObjectCreate
      • cuSurfObjectCreate

        public static int cuSurfObjectCreate​(java.nio.LongBuffer pSurfObject,
                                             CUDA_RESOURCE_DESC pResDesc)
        Creates a surface object.

        Creates a surface object and returns it in pSurfObject. pResDesc describes the data to perform surface load/stores on. CUDA_RESOURCE_DESC::resType must be RESOURCE_TYPE_ARRAY and CUDA_RESOURCE_DESC::res::array::hArray must be set to a valid CUDA array handle. CUDA_RESOURCE_DESC::flags must be set to zero.

        Surface objects are only supported on devices of compute capability 3.0 or higher. Additionally, a surface object is an opaque value, and, as such, should only be accessed through CUDA API calls.

        Parameters:
        pSurfObject - surface object to create
        pResDesc - resource descriptor
      • cuSurfObjectDestroy

        public static int cuSurfObjectDestroy​(long surfObject)
        Destroys a surface object.

        Destroys the surface object specified by surfObject.

        Parameters:
        surfObject - surface object to destroy
      • ncuSurfObjectGetResourceDesc

        public static int ncuSurfObjectGetResourceDesc​(long pResDesc,
                                                       long surfObject)
        Unsafe version of: SurfObjectGetResourceDesc
      • cuSurfObjectGetResourceDesc

        public static int cuSurfObjectGetResourceDesc​(CUDA_RESOURCE_DESC pResDesc,
                                                      long surfObject)
        Returns a surface object's resource descriptor.

        Returns the resource descriptor for the surface object specified by surfObject.

        Parameters:
        pResDesc - resource descriptor
        surfObject - surface object
      • ncuDeviceCanAccessPeer

        public static int ncuDeviceCanAccessPeer​(long canAccessPeer,
                                                 int dev,
                                                 int peerDev)
        Unsafe version of: DeviceCanAccessPeer
      • cuDeviceCanAccessPeer

        public static int cuDeviceCanAccessPeer​(java.nio.IntBuffer canAccessPeer,
                                                int dev,
                                                int peerDev)
        Queries if a device may directly access a peer device's memory.

        Returns in *canAccessPeer a value of 1 if contexts on dev are capable of directly accessing memory from contexts on peerDev and 0 otherwise. If direct access of peerDev from dev is possible, then access may be enabled on two specific contexts by calling CtxEnablePeerAccess.

        Parameters:
        canAccessPeer - returned access capability
        dev - device from which allocations on peerDev are to be directly accessed
        peerDev - device on which the allocations to be directly accessed by dev reside
      • cuCtxEnablePeerAccess

        public static int cuCtxEnablePeerAccess​(long peerContext,
                                                int Flags)
        Enables direct access to memory allocations in a peer context.

        If both the current context and peerContext are on devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING) and same major compute capability, then on success all allocations from peerContext will immediately be accessible by the current context. See ref for additional details.

        Note that access granted by this call is unidirectional and that in order to access memory from the current context in peerContext, a separate symmetric call to CtxEnablePeerAccess is required.

        Note that there are both device-wide and system-wide limitations per system configuration, as noted in the CUDA Programming Guide under the section "Peer-to-Peer Memory Access".

        Returns CUDA_ERROR_PEER_ACCESS_UNSUPPORTED if DeviceCanAccessPeer indicates that the CUdevice of the current context cannot directly access memory from the CUdevice of peerContext.

        Returns CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED if direct access of peerContext from the current context has already been enabled.

        Returns CUDA_ERROR_TOO_MANY_PEERS if direct peer access is not possible because hardware resources required for peer access have been exhausted.

        Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, peerContext is not a valid context, or if the current context is peerContext.

        Returns CUDA_ERROR_INVALID_VALUE if Flags is not 0.

        Parameters:
        peerContext - peer context to enable direct access to from the current context
        Flags - reserved for future use and must be set to 0
      • cuCtxDisablePeerAccess

        public static int cuCtxDisablePeerAccess​(long peerContext)
        Disables direct access to memory allocations in a peer context and unregisters any registered allocations.

        Returns CUDA_ERROR_PEER_ACCESS_NOT_ENABLED if direct peer access has not yet been enabled from peerContext to the current context.

        Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, or if peerContext is not a valid context.

        Parameters:
        peerContext - peer context to disable direct access to
      • ncuDeviceGetP2PAttribute

        public static int ncuDeviceGetP2PAttribute​(long value,
                                                   int attrib,
                                                   int srcDevice,
                                                   int dstDevice)
        Unsafe version of: DeviceGetP2PAttribute
      • cuDeviceGetP2PAttribute

        public static int cuDeviceGetP2PAttribute​(java.nio.IntBuffer value,
                                                  int attrib,
                                                  int srcDevice,
                                                  int dstDevice)
        Queries attributes of the link between two devices.

        Returns in *value the value of the requested attribute attrib of the link between srcDevice and dstDevice. The supported attributes are:

        Returns CUDA_ERROR_INVALID_DEVICE if srcDevice or dstDevice are not valid or if they represent the same device.

        Returns CUDA_ERROR_INVALID_VALUE if attrib is not valid or if value is a null pointer.

        Parameters:
        value - returned value of the requested attribute
        attrib - the requested attribute of the link between srcDevice and dstDevice
        srcDevice - the source device of the target link
        dstDevice - the destination device of the target link
      • cuGraphicsUnregisterResource

        public static int cuGraphicsUnregisterResource​(long resource)
        Unregisters a graphics resource for access by CUDA.

        Unregisters the graphics resource resource so it is not accessible by CUDA unless registered again.

        If resource is invalid then CUDA_ERROR_INVALID_HANDLE is returned.

        Parameters:
        resource - resource to unregister
      • ncuGraphicsSubResourceGetMappedArray

        public static int ncuGraphicsSubResourceGetMappedArray​(long pArray,
                                                               long resource,
                                                               int arrayIndex,
                                                               int mipLevel)
      • cuGraphicsSubResourceGetMappedArray

        public static int cuGraphicsSubResourceGetMappedArray​(org.lwjgl.PointerBuffer pArray,
                                                              long resource,
                                                              int arrayIndex,
                                                              int mipLevel)
        Get an array through which to access a subresource of a mapped graphics resource.

        Returns in *pArray an array through which the subresource of the mapped graphics resource resource which corresponds to array index arrayIndex and mipmap level mipLevel may be accessed. The value set in *pArray may change every time that resource is mapped.

        If resource is not a texture then it cannot be accessed via an array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If arrayIndex is not a valid array index for resource then CUDA_ERROR_INVALID_VALUE is returned. If mipLevel is not a valid mipmap level for resource then CUDA_ERROR_INVALID_VALUE is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

        Parameters:
        pArray - returned array through which a subresource of resource may be accessed
        resource - mapped resource to access
        arrayIndex - array index for array textures or cubemap face index as defined by CUarray_cubemap_face for cubemap textures for the subresource to access
        mipLevel - mipmap level for the subresource to access
      • ncuGraphicsResourceGetMappedMipmappedArray

        public static int ncuGraphicsResourceGetMappedMipmappedArray​(long pMipmappedArray,
                                                                     long resource)
      • cuGraphicsResourceGetMappedMipmappedArray

        public static int cuGraphicsResourceGetMappedMipmappedArray​(org.lwjgl.PointerBuffer pMipmappedArray,
                                                                    long resource)
        Get a mipmapped array through which to access a mapped graphics resource.

        Returns in *pMipmappedArray a mipmapped array through which the mapped graphics resource resource. The value set in *pMipmappedArray may change every time that resource is mapped.

        If resource is not a texture then it cannot be accessed via a mipmapped array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

        Parameters:
        pMipmappedArray - returned mipmapped array through which resource may be accessed
        resource - mapped resource to access
      • ncuGraphicsResourceGetMappedPointer

        public static int ncuGraphicsResourceGetMappedPointer​(long pDevPtr,
                                                              long pSize,
                                                              long resource)
      • cuGraphicsResourceGetMappedPointer

        public static int cuGraphicsResourceGetMappedPointer​(org.lwjgl.PointerBuffer pDevPtr,
                                                             org.lwjgl.PointerBuffer pSize,
                                                             long resource)
        Get a device pointer through which to access a mapped graphics resource.

        Returns in *pDevPtr a pointer through which the mapped graphics resource resource may be accessed. Returns in pSize the size of the memory in bytes which may be accessed from that pointer. The value set in pPointer may change every time that resource is mapped.

        If resource is not a buffer then it cannot be accessed via a pointer and CUDA_ERROR_NOT_MAPPED_AS_POINTER is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned. *

        Parameters:
        pDevPtr - returned pointer through which resource may be accessed
        pSize - returned size of the buffer accessible starting at *pPointer
        resource - mapped resource to access
      • cuGraphicsResourceSetMapFlags

        public static int cuGraphicsResourceSetMapFlags​(long resource,
                                                        int flags)
        Set usage flags for mapping a graphics resource.

        Set flags for mapping the graphics resource resource.

        Changes to flags will take effect the next time resource is mapped. The flags argument may be any of the following:

        • GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA kernels. This is the default value.
        • GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA kernels which access this resource will not write to this resource.
        • GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA kernels which access this resource will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

        If resource is presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned. If flags is not one of the above values then CUDA_ERROR_INVALID_VALUE is returned.

        Parameters:
        resource - registered resource to set flags for
        flags - parameters for resource mapping
      • ncuGraphicsMapResources

        public static int ncuGraphicsMapResources​(int count,
                                                  long resources,
                                                  long hStream)
        Unsafe version of: GraphicsMapResources
        Parameters:
        count - number of resources to map
      • cuGraphicsMapResources

        public static int cuGraphicsMapResources​(org.lwjgl.PointerBuffer resources,
                                                 long hStream)
        Map graphics resources for access by CUDA.

        Maps the count graphics resources in resources for access by CUDA.

        The resources in resources may be accessed by CUDA until they are unmapped. The graphics API from which resources were registered should not access any resources while they are mapped by CUDA. If an application does so, the results are undefined.

        This function provides the synchronization guarantee that any graphics calls issued before GraphicsMapResources will complete before any subsequent CUDA work issued in stream begins.

        If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned.

        Parameters:
        resources - resources to map for CUDA usage
        hStream - stream with which to synchronize
      • ncuGraphicsUnmapResources

        public static int ncuGraphicsUnmapResources​(int count,
                                                    long resources,
                                                    long hStream)
        Unsafe version of: GraphicsUnmapResources
        Parameters:
        count - number of resources to unmap
      • cuGraphicsUnmapResources

        public static int cuGraphicsUnmapResources​(org.lwjgl.PointerBuffer resources,
                                                   long hStream)
        Unmap graphics resources.

        Unmaps the count graphics resources in resources.

        Once unmapped, the resources in resources may not be accessed by CUDA until they are mapped again.

        This function provides the synchronization guarantee that any CUDA work issued in stream before GraphicsUnmapResources will complete before any subsequently issued graphics work begins.

        If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are not presently mapped for access by CUDA then CUDA_ERROR_NOT_MAPPED is returned.

        Parameters:
        resources - resources to unmap
        hStream - stream with which to synchronize
      • ncuGetProcAddress

        public static int ncuGetProcAddress​(long symbol,
                                            long pfn,
                                            int cudaVersion,
                                            long flags)
        Unsafe version of: GetProcAddress
      • cuGetProcAddress

        public static int cuGetProcAddress​(java.nio.ByteBuffer symbol,
                                           org.lwjgl.PointerBuffer pfn,
                                           int cudaVersion,
                                           long flags)
        
        public static int cuGetProcAddress​(java.lang.CharSequence symbol,
                                           org.lwjgl.PointerBuffer pfn,
                                           int cudaVersion,
                                           long flags)
        
        Returns the requested driver API function pointer.

        Returns in **pfn the address of the CUDA driver function for the requested CUDA version and flags.

        The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.

        The pointer returned by the API should be cast to a function pointer matching the requested driver function's definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.

        The API will return CUDA_ERROR_NOT_FOUND if the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specified cudaVersion or if the driver symbol is invalid.

        The requested flags can be:

        Parameters:
        symbol - the base name of the driver API function to look for. As an example, for the driver API cuMemAlloc_v2(), symbol would be cuMemAlloc and cudaVersion would be the ABI compatible CUDA version for the _v2 variant.
        pfn - location to return the function pointer to the requested driver function
        cudaVersion - the CUDA version to look for the requested driver symbol
        flags - flags to specify search options
      • ncuGetExportTable

        public static int ncuGetExportTable​(long ppExportTable,
                                            long pExportTableId)
      • cuGetExportTable

        public static int cuGetExportTable​(org.lwjgl.PointerBuffer ppExportTable,
                                           CUuuid pExportTableId)