public class CU101 extends CU100
| Modifier and Type | Class and Description |
|---|---|
static class |
CU101.Functions
Contains the function pointers loaded from
CU.getLibrary(). |
| Modifier and Type | Field and Description |
|---|---|
static int |
CU_STREAM_CAPTURE_MODE_GLOBAL
Possible modes for stream capture thread interactions.
|
static int |
CU_STREAM_CAPTURE_MODE_RELAXED
Possible modes for stream capture thread interactions.
|
static int |
CU_STREAM_CAPTURE_MODE_THREAD_LOCAL
Possible modes for stream capture thread interactions.
|
CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP, CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE, CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD, CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32, CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT, CU_GRAPH_NODE_TYPE_EMPTY, CU_GRAPH_NODE_TYPE_GRAPH, CU_GRAPH_NODE_TYPE_HOST, CU_GRAPH_NODE_TYPE_KERNEL, CU_GRAPH_NODE_TYPE_MEMCPY, CU_GRAPH_NODE_TYPE_MEMSET, CU_STREAM_CAPTURE_STATUS_ACTIVE, CU_STREAM_CAPTURE_STATUS_INVALIDATED, CU_STREAM_CAPTURE_STATUS_NONE, CUDA_EXTERNAL_MEMORY_DEDICATEDCU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC, CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNCCU_DEVICE_CPU, CU_DEVICE_INVALID, CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED, CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED, CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED, CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED, CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK, CU_MEM_ADVISE_SET_ACCESSED_BY, CU_MEM_ADVISE_SET_PREFERRED_LOCATION, CU_MEM_ADVISE_SET_READ_MOSTLY, CU_MEM_ADVISE_UNSET_ACCESSED_BY, CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION, CU_MEM_ADVISE_UNSET_READ_MOSTLY, CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY, CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION, CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION, CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY, CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES, CU_STREAM_MEM_OP_WAIT_VALUE_32, CU_STREAM_MEM_OP_WAIT_VALUE_64, CU_STREAM_MEM_OP_WRITE_VALUE_32, CU_STREAM_MEM_OP_WRITE_VALUE_64, CU_STREAM_WAIT_VALUE_AND, CU_STREAM_WAIT_VALUE_EQ, CU_STREAM_WAIT_VALUE_FLUSH, CU_STREAM_WAIT_VALUE_GEQ, CU_STREAM_WAIT_VALUE_NOR, CU_STREAM_WRITE_VALUE_DEFAULT, CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIERCU_STREAM_LEGACY, CU_STREAM_PER_THREADCU_OCCUPANCY_DEFAULT, CU_OCCUPANCY_DISABLE_CACHING_OVERRIDECU_MEM_ATTACH_GLOBAL, CU_MEM_ATTACH_HOST, CU_MEM_ATTACH_SINGLECU_JIT_INPUT_CUBIN, CU_JIT_INPUT_FATBINARY, CU_JIT_INPUT_LIBRARY, CU_JIT_INPUT_OBJECT, CU_JIT_INPUT_PTXCU_RES_VIEW_FORMAT_FLOAT_1X16, CU_RES_VIEW_FORMAT_FLOAT_1X32, CU_RES_VIEW_FORMAT_FLOAT_2X16, CU_RES_VIEW_FORMAT_FLOAT_2X32, CU_RES_VIEW_FORMAT_FLOAT_4X16, CU_RES_VIEW_FORMAT_FLOAT_4X32, CU_RES_VIEW_FORMAT_NONE, CU_RES_VIEW_FORMAT_SIGNED_BC4, CU_RES_VIEW_FORMAT_SIGNED_BC5, CU_RES_VIEW_FORMAT_SIGNED_BC6H, CU_RES_VIEW_FORMAT_SINT_1X16, CU_RES_VIEW_FORMAT_SINT_1X32, CU_RES_VIEW_FORMAT_SINT_1X8, CU_RES_VIEW_FORMAT_SINT_2X16, CU_RES_VIEW_FORMAT_SINT_2X32, CU_RES_VIEW_FORMAT_SINT_2X8, CU_RES_VIEW_FORMAT_SINT_4X16, CU_RES_VIEW_FORMAT_SINT_4X32, CU_RES_VIEW_FORMAT_SINT_4X8, CU_RES_VIEW_FORMAT_UINT_1X16, CU_RES_VIEW_FORMAT_UINT_1X32, CU_RES_VIEW_FORMAT_UINT_1X8, CU_RES_VIEW_FORMAT_UINT_2X16, CU_RES_VIEW_FORMAT_UINT_2X32, CU_RES_VIEW_FORMAT_UINT_2X8, CU_RES_VIEW_FORMAT_UINT_4X16, CU_RES_VIEW_FORMAT_UINT_4X32, CU_RES_VIEW_FORMAT_UINT_4X8, CU_RES_VIEW_FORMAT_UNSIGNED_BC1, CU_RES_VIEW_FORMAT_UNSIGNED_BC2, CU_RES_VIEW_FORMAT_UNSIGNED_BC3, CU_RES_VIEW_FORMAT_UNSIGNED_BC4, CU_RES_VIEW_FORMAT_UNSIGNED_BC5, CU_RES_VIEW_FORMAT_UNSIGNED_BC6H, CU_RES_VIEW_FORMAT_UNSIGNED_BC7, CU_RESOURCE_TYPE_ARRAY, CU_RESOURCE_TYPE_LINEAR, CU_RESOURCE_TYPE_MIPMAPPED_ARRAY, CU_RESOURCE_TYPE_PITCH2DCU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE, CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE, CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE, CU_SHAREDMEM_CARVEOUT_DEFAULT, CU_SHAREDMEM_CARVEOUT_MAX_L1, CU_SHAREDMEM_CARVEOUT_MAX_SHAREDCU_IPC_HANDLE_SIZE, CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESSCU_LAUNCH_PARAM_BUFFER_POINTER, CU_LAUNCH_PARAM_BUFFER_SIZE, CU_LAUNCH_PARAM_END, CU_POINTER_ATTRIBUTE_BUFFER_ID, CU_POINTER_ATTRIBUTE_CONTEXT, CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL, CU_POINTER_ATTRIBUTE_DEVICE_POINTER, CU_POINTER_ATTRIBUTE_HOST_POINTER, CU_POINTER_ATTRIBUTE_IS_MANAGED, CU_POINTER_ATTRIBUTE_MEMORY_TYPE, CU_POINTER_ATTRIBUTE_P2P_TOKENS, CU_POINTER_ATTRIBUTE_SYNC_MEMOPSCU_AD_FORMAT_FLOAT, CU_AD_FORMAT_HALF, CU_AD_FORMAT_SIGNED_INT16, CU_AD_FORMAT_SIGNED_INT32, CU_AD_FORMAT_SIGNED_INT8, CU_AD_FORMAT_UNSIGNED_INT16, CU_AD_FORMAT_UNSIGNED_INT32, CU_AD_FORMAT_UNSIGNED_INT8, CU_COMPUTEMODE_DEFAULT, CU_COMPUTEMODE_EXCLUSIVE_PROCESS, CU_COMPUTEMODE_PROHIBITED, CU_CTX_BLOCKING_SYNC, CU_CTX_FLAGS_MASK, CU_CTX_LMEM_RESIZE_TO_MAX, CU_CTX_MAP_HOST, CU_CTX_SCHED_AUTO, CU_CTX_SCHED_BLOCKING_SYNC, CU_CTX_SCHED_MASK, CU_CTX_SCHED_SPIN, CU_CTX_SCHED_YIELD, CU_CUBEMAP_FACE_NEGATIVE_X, CU_CUBEMAP_FACE_NEGATIVE_Y, CU_CUBEMAP_FACE_NEGATIVE_Z, CU_CUBEMAP_FACE_POSITIVE_X, CU_CUBEMAP_FACE_POSITIVE_Y, CU_CUBEMAP_FACE_POSITIVE_Z, CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT, CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES, CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY, CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER, CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS, CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS, CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, CU_DEVICE_ATTRIBUTE_COMPUTE_MODE, CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED, CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS, CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH, CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH, CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST, CU_DEVICE_ATTRIBUTE_ECC_ENABLED, CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED, CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH, CU_DEVICE_ATTRIBUTE_GPU_OVERLAP, CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED, CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED, CU_DEVICE_ATTRIBUTE_INTEGRATED, CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT, CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE, CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED, CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y, CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y, CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z, CU_DEVICE_ATTRIBUTE_MAX_PITCH, CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK, CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR, CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK, CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN, CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR, CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK, CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH, CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH, CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE, CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD, CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT, CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS, CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, CU_DEVICE_ATTRIBUTE_PCI_BUS_ID, CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID, CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID, CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK, CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK, CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO, CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED, CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT, CU_DEVICE_ATTRIBUTE_TCC_DRIVER, CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT, CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT, CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY, CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING, CU_DEVICE_ATTRIBUTE_WARP_SIZE, CU_EVENT_BLOCKING_SYNC, CU_EVENT_DEFAULT, CU_EVENT_DISABLE_TIMING, CU_EVENT_INTERPROCESS, CU_FUNC_ATTRIBUTE_BINARY_VERSION, CU_FUNC_ATTRIBUTE_CACHE_MODE_CA, CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES, CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES, CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK, CU_FUNC_ATTRIBUTE_NUM_REGS, CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT, CU_FUNC_ATTRIBUTE_PTX_VERSION, CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES, CU_FUNC_CACHE_PREFER_EQUAL, CU_FUNC_CACHE_PREFER_L1, CU_FUNC_CACHE_PREFER_NONE, CU_FUNC_CACHE_PREFER_SHARED, CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE, CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY, CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD, CU_GRAPHICS_REGISTER_FLAGS_NONE, CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY, CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST, CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER, CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD, CU_JIT_CACHE_MODE, CU_JIT_CACHE_OPTION_CA, CU_JIT_CACHE_OPTION_CG, CU_JIT_CACHE_OPTION_NONE, CU_JIT_ERROR_LOG_BUFFER, CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES, CU_JIT_FALLBACK_STRATEGY, CU_JIT_FAST_COMPILE, CU_JIT_GENERATE_DEBUG_INFO, CU_JIT_GENERATE_LINE_INFO, CU_JIT_GLOBAL_SYMBOL_ADDRESSES, CU_JIT_GLOBAL_SYMBOL_COUNT, CU_JIT_GLOBAL_SYMBOL_NAMES, CU_JIT_INFO_LOG_BUFFER, CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES, CU_JIT_LOG_VERBOSE, CU_JIT_MAX_REGISTERS, CU_JIT_NEW_SM3X_OPT, CU_JIT_OPTIMIZATION_LEVEL, CU_JIT_TARGET, CU_JIT_TARGET_FROM_CUCONTEXT, CU_JIT_THREADS_PER_BLOCK, CU_JIT_WALL_TIME, CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT, CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH, CU_LIMIT_MALLOC_HEAP_SIZE, CU_LIMIT_MAX_L2_FETCH_GRANULARITY, CU_LIMIT_PRINTF_FIFO_SIZE, CU_LIMIT_STACK_SIZE, CU_MEMHOSTALLOC_DEVICEMAP, CU_MEMHOSTALLOC_PORTABLE, CU_MEMHOSTALLOC_WRITECOMBINED, CU_MEMHOSTREGISTER_DEVICEMAP, CU_MEMHOSTREGISTER_IOMEMORY, CU_MEMHOSTREGISTER_PORTABLE, CU_MEMORYTYPE_ARRAY, CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_HOST, CU_MEMORYTYPE_UNIFIED, CU_PARAM_TR_DEFAULT, CU_PREFER_BINARY, CU_PREFER_PTX, CU_STREAM_DEFAULT, CU_STREAM_NON_BLOCKING, CU_TARGET_COMPUTE_20, CU_TARGET_COMPUTE_21, CU_TARGET_COMPUTE_30, CU_TARGET_COMPUTE_32, CU_TARGET_COMPUTE_35, CU_TARGET_COMPUTE_37, CU_TARGET_COMPUTE_50, CU_TARGET_COMPUTE_52, CU_TARGET_COMPUTE_53, CU_TARGET_COMPUTE_60, CU_TARGET_COMPUTE_61, CU_TARGET_COMPUTE_62, CU_TARGET_COMPUTE_70, CU_TARGET_COMPUTE_72, CU_TARGET_COMPUTE_75, CU_TR_ADDRESS_MODE_BORDER, CU_TR_ADDRESS_MODE_CLAMP, CU_TR_ADDRESS_MODE_MIRROR, CU_TR_ADDRESS_MODE_WRAP, CU_TR_FILTER_MODE_LINEAR, CU_TR_FILTER_MODE_POINT, CU_TRSA_OVERRIDE_FORMAT, CU_TRSF_NORMALIZED_COORDINATES, CU_TRSF_READ_AS_INTEGER, CU_TRSF_SRGB, CUDA_ARRAY3D_2DARRAY, CUDA_ARRAY3D_COLOR_ATTACHMENT, CUDA_ARRAY3D_CUBEMAP, CUDA_ARRAY3D_DEPTH_TEXTURE, CUDA_ARRAY3D_LAYERED, CUDA_ARRAY3D_SURFACE_LDST, CUDA_ARRAY3D_TEXTURE_GATHER, CUDA_ERROR_ALREADY_ACQUIRED, CUDA_ERROR_ALREADY_MAPPED, CUDA_ERROR_ARRAY_IS_MAPPED, CUDA_ERROR_ASSERT, CUDA_ERROR_CAPTURED_EVENT, CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE, CUDA_ERROR_CONTEXT_ALREADY_CURRENT, CUDA_ERROR_CONTEXT_ALREADY_IN_USE, CUDA_ERROR_CONTEXT_IS_DESTROYED, CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_ECC_UNCORRECTABLE, CUDA_ERROR_FILE_NOT_FOUND, CUDA_ERROR_HARDWARE_STACK_ERROR, CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED, CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED, CUDA_ERROR_ILLEGAL_ADDRESS, CUDA_ERROR_ILLEGAL_INSTRUCTION, CUDA_ERROR_ILLEGAL_STATE, CUDA_ERROR_INVALID_ADDRESS_SPACE, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_DEVICE, CUDA_ERROR_INVALID_GRAPHICS_CONTEXT, CUDA_ERROR_INVALID_HANDLE, CUDA_ERROR_INVALID_IMAGE, CUDA_ERROR_INVALID_PC, CUDA_ERROR_INVALID_PTX, CUDA_ERROR_INVALID_SOURCE, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_JIT_COMPILER_NOT_FOUND, CUDA_ERROR_LAUNCH_FAILED, CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING, CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES, CUDA_ERROR_LAUNCH_TIMEOUT, CUDA_ERROR_MAP_FAILED, CUDA_ERROR_MISALIGNED_ADDRESS, CUDA_ERROR_NO_BINARY_FOR_GPU, CUDA_ERROR_NO_DEVICE, CUDA_ERROR_NOT_FOUND, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_NOT_MAPPED, CUDA_ERROR_NOT_MAPPED_AS_ARRAY, CUDA_ERROR_NOT_MAPPED_AS_POINTER, CUDA_ERROR_NOT_PERMITTED, CUDA_ERROR_NOT_READY, CUDA_ERROR_NOT_SUPPORTED, CUDA_ERROR_NVLINK_UNCORRECTABLE, CUDA_ERROR_OPERATING_SYSTEM, CUDA_ERROR_OUT_OF_MEMORY, CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED, CUDA_ERROR_PEER_ACCESS_NOT_ENABLED, CUDA_ERROR_PEER_ACCESS_UNSUPPORTED, CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE, CUDA_ERROR_PROFILER_ALREADY_STARTED, CUDA_ERROR_PROFILER_ALREADY_STOPPED, CUDA_ERROR_PROFILER_DISABLED, CUDA_ERROR_PROFILER_NOT_INITIALIZED, CUDA_ERROR_SHARED_OBJECT_INIT_FAILED, CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND, CUDA_ERROR_STREAM_CAPTURE_IMPLICIT, CUDA_ERROR_STREAM_CAPTURE_INVALIDATED, CUDA_ERROR_STREAM_CAPTURE_ISOLATION, CUDA_ERROR_STREAM_CAPTURE_MERGE, CUDA_ERROR_STREAM_CAPTURE_UNJOINED, CUDA_ERROR_STREAM_CAPTURE_UNMATCHED, CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED, CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD, CUDA_ERROR_SYSTEM_DRIVER_MISMATCH, CUDA_ERROR_SYSTEM_NOT_READY, CUDA_ERROR_TOO_MANY_PEERS, CUDA_ERROR_UNKNOWN, CUDA_ERROR_UNMAP_FAILED, CUDA_ERROR_UNSUPPORTED_LIMIT, CUDA_SUCCESS| Modifier and Type | Method and Description |
|---|---|
static int |
cuGraphExecKernelNodeSetParams(long hGraphExec,
long hNode,
CUDA_KERNEL_NODE_PARAMS nodeParams)
Sets the parameters for a kernel node in the given
graphExec. |
static int |
cuStreamBeginCapture_v2(long hStream,
int mode) |
static int |
cuStreamGetCaptureInfo(long hStream,
java.nio.IntBuffer captureStatus,
java.nio.LongBuffer id)
Query capture status of a stream.
|
static int |
cuThreadExchangeStreamCaptureMode(java.nio.IntBuffer mode)
Swaps the stream capture interaction mode for a thread.
|
static int |
ncuGraphExecKernelNodeSetParams(long hGraphExec,
long hNode,
long nodeParams)
Unsafe version of:
GraphExecKernelNodeSetParams |
static int |
ncuStreamGetCaptureInfo(long hStream,
long captureStatus,
long id)
Unsafe version of:
StreamGetCaptureInfo |
static int |
ncuThreadExchangeStreamCaptureMode(long mode)
Unsafe version of:
ThreadExchangeStreamCaptureMode |
cuDestroyExternalMemory, cuDestroyExternalSemaphore, cuDeviceGetLuid, cuExternalMemoryGetMappedBuffer, cuExternalMemoryGetMappedMipmappedArray, cuGraphAddChildGraphNode, cuGraphAddDependencies, cuGraphAddEmptyNode, cuGraphAddHostNode, cuGraphAddKernelNode, cuGraphAddMemcpyNode, cuGraphAddMemsetNode, cuGraphChildGraphNodeGetGraph, cuGraphClone, cuGraphCreate, cuGraphDestroy, cuGraphDestroyNode, cuGraphExecDestroy, cuGraphGetEdges, cuGraphGetNodes, cuGraphGetRootNodes, cuGraphHostNodeGetParams, cuGraphHostNodeSetParams, cuGraphInstantiate, cuGraphKernelNodeGetParams, cuGraphKernelNodeSetParams, cuGraphLaunch, cuGraphMemcpyNodeGetParams, cuGraphMemcpyNodeSetParams, cuGraphMemsetNodeGetParams, cuGraphMemsetNodeSetParams, cuGraphNodeFindInClone, cuGraphNodeGetDependencies, cuGraphNodeGetDependentNodes, cuGraphNodeGetType, cuGraphRemoveDependencies, cuImportExternalMemory, cuImportExternalSemaphore, cuLaunchHostFunc, cuSignalExternalSemaphoresAsync, cuStreamBeginCapture, cuStreamEndCapture, cuStreamIsCapturing, cuWaitExternalSemaphoresAsync, ncuDeviceGetLuid, ncuExternalMemoryGetMappedBuffer, ncuExternalMemoryGetMappedMipmappedArray, ncuGraphAddChildGraphNode, ncuGraphAddDependencies, ncuGraphAddEmptyNode, ncuGraphAddHostNode, ncuGraphAddKernelNode, ncuGraphAddMemcpyNode, ncuGraphAddMemsetNode, ncuGraphChildGraphNodeGetGraph, ncuGraphClone, ncuGraphCreate, ncuGraphGetEdges, ncuGraphGetNodes, ncuGraphGetRootNodes, ncuGraphHostNodeGetParams, ncuGraphHostNodeSetParams, ncuGraphInstantiate, ncuGraphKernelNodeGetParams, ncuGraphKernelNodeSetParams, ncuGraphMemcpyNodeGetParams, ncuGraphMemcpyNodeSetParams, ncuGraphMemsetNodeGetParams, ncuGraphMemsetNodeSetParams, ncuGraphNodeFindInClone, ncuGraphNodeGetDependencies, ncuGraphNodeGetDependentNodes, ncuGraphNodeGetType, ncuGraphRemoveDependencies, ncuImportExternalMemory, ncuImportExternalSemaphore, ncuLaunchHostFunc, ncuSignalExternalSemaphoresAsync, ncuStreamEndCapture, ncuStreamIsCapturing, ncuWaitExternalSemaphoresAsynccuDeviceGetUuid, cuStreamGetCtx, ncuDeviceGetUuid, ncuStreamGetCtxcuFuncSetAttribute, cuLaunchCooperativeKernel, cuLaunchCooperativeKernelMultiDevice, ncuLaunchCooperativeKernel, ncuLaunchCooperativeKernelMultiDevicecuDeviceGetP2PAttribute, cuMemAdvise, cuMemPrefetchAsync, cuMemRangeGetAttribute, cuMemRangeGetAttributes, cuStreamBatchMemOp, cuStreamWaitValue32, cuStreamWaitValue64, cuStreamWriteValue32, cuStreamWriteValue64, ncuDeviceGetP2PAttribute, ncuMemRangeGetAttribute, ncuMemRangeGetAttributes, ncuStreamBatchMemOpcuCtxGetFlags, cuDevicePrimaryCtxGetState, cuDevicePrimaryCtxRelease, cuDevicePrimaryCtxReset, cuDevicePrimaryCtxRetain, cuDevicePrimaryCtxSetFlags, cuPointerGetAttributes, ncuCtxGetFlags, ncuDevicePrimaryCtxGetState, ncuDevicePrimaryCtxRetain, ncuPointerGetAttributescuOccupancyMaxActiveBlocksPerMultiprocessor, cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags, cuOccupancyMaxPotentialBlockSize, cuOccupancyMaxPotentialBlockSizeWithFlags, ncuOccupancyMaxActiveBlocksPerMultiprocessor, ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags, ncuOccupancyMaxPotentialBlockSize, ncuOccupancyMaxPotentialBlockSizeWithFlagscuMemAllocManaged, cuPointerSetAttribute, cuStreamAttachMemAsync, ncuMemAllocManaged, ncuPointerSetAttributecuLinkAddData, cuLinkAddData, cuLinkAddFile, cuLinkAddFile, cuLinkComplete, cuLinkCreate, cuLinkDestroy, ncuLinkAddData, ncuLinkAddFile, ncuLinkComplete, ncuLinkCreatecuGraphicsResourceGetMappedMipmappedArray, cuMipmappedArrayCreate, cuMipmappedArrayDestroy, cuMipmappedArrayGetLevel, cuSurfObjectCreate, cuSurfObjectDestroy, cuSurfObjectGetResourceDesc, cuTexObjectCreate, cuTexObjectDestroy, cuTexObjectGetResourceDesc, cuTexObjectGetResourceViewDesc, cuTexObjectGetTextureDesc, ncuGraphicsResourceGetMappedMipmappedArray, ncuMipmappedArrayCreate, ncuMipmappedArrayGetLevel, ncuSurfObjectCreate, ncuSurfObjectGetResourceDesc, ncuTexObjectCreate, ncuTexObjectGetResourceDesc, ncuTexObjectGetResourceViewDesc, ncuTexObjectGetTextureDesccuCtxGetSharedMemConfig, cuCtxSetSharedMemConfig, cuFuncSetSharedMemConfig, ncuCtxGetSharedMemConfigcuDeviceGetByPCIBusId, cuDeviceGetByPCIBusId, cuDeviceGetPCIBusId, cuIpcCloseMemHandle, cuIpcGetEventHandle, cuIpcGetMemHandle, ncuDeviceGetByPCIBusId, ncuDeviceGetPCIBusId, ncuIpcGetEventHandle, ncuIpcGetMemHandlecuCtxDestroy, cuCtxDisablePeerAccess, cuCtxEnablePeerAccess, cuCtxGetCurrent, cuCtxPopCurrent, cuCtxPushCurrent, cuCtxSetCurrent, cuDeviceCanAccessPeer, cuEventDestroy, cuLaunchKernel, cuMemcpy, cuMemcpy3DPeer, cuMemcpy3DPeerAsync, cuMemcpyAsync, cuMemcpyPeer, cuMemcpyPeerAsync, cuMemHostRegister, cuMemHostUnregister, cuPointerGetAttribute, cuStreamDestroy, ncuCtxGetCurrent, ncuCtxPopCurrent, ncuDeviceCanAccessPeer, ncuLaunchKernel, ncuMemcpy3DPeer, ncuMemcpy3DPeerAsync, ncuMemHostRegister, ncuMemHostUnregister, ncuPointerGetAttributecuArray3DCreate, cuArray3DGetDescriptor, cuArrayCreate, cuArrayDestroy, cuArrayGetDescriptor, cuCtxAttach, cuCtxCreate, cuCtxDetach, cuCtxGetApiVersion, cuCtxGetCacheConfig, cuCtxGetDevice, cuCtxGetLimit, cuCtxGetStreamPriorityRange, cuCtxSetCacheConfig, cuCtxSetLimit, cuCtxSynchronize, cuDeviceComputeCapability, cuDeviceGet, cuDeviceGetAttribute, cuDeviceGetCount, cuDeviceGetName, cuDeviceGetProperties, cuDeviceTotalMem, cuDriverGetVersion, cuEventCreate, cuEventElapsedTime, cuEventQuery, cuEventRecord, cuEventSynchronize, cuFuncGetAttribute, cuFuncSetBlockShape, cuFuncSetCacheConfig, cuFuncSetSharedSize, cuGetErrorName, cuGetErrorString, cuGetExportTable, cuGraphicsMapResources, cuGraphicsResourceGetMappedPointer, cuGraphicsResourceSetMapFlags, cuGraphicsSubResourceGetMappedArray, cuGraphicsUnmapResources, cuGraphicsUnregisterResource, cuInit, cuLaunch, cuLaunchGrid, cuLaunchGridAsync, cuMemAlloc, cuMemAllocHost, cuMemAllocPitch, cuMemcpy2D, cuMemcpy2DAsync, cuMemcpy2DUnaligned, cuMemcpy3D, cuMemcpy3DAsync, cuMemcpyAtoA, cuMemcpyAtoD, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoH, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyAtoHAsync, cuMemcpyDtoA, cuMemcpyDtoD, cuMemcpyDtoDAsync, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoH, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyDtoHAsync, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoA, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoAAsync, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoD, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemcpyHtoDAsync, cuMemFree, cuMemFreeHost, cuMemGetAddressRange, cuMemGetInfo, cuMemHostAlloc, cuMemHostGetDevicePointer, cuMemHostGetFlags, cuMemsetD16, cuMemsetD16Async, cuMemsetD2D16, cuMemsetD2D16Async, cuMemsetD2D32, cuMemsetD2D32Async, cuMemsetD2D8, cuMemsetD2D8Async, cuMemsetD32, cuMemsetD32Async, cuMemsetD8, cuMemsetD8Async, cuModuleGetFunction, cuModuleGetFunction, cuModuleGetGlobal, cuModuleGetGlobal, cuModuleGetSurfRef, cuModuleGetSurfRef, cuModuleGetTexRef, cuModuleGetTexRef, cuModuleLoad, cuModuleLoad, cuModuleLoadData, cuModuleLoadDataEx, cuModuleLoadFatBinary, cuModuleUnload, cuParamSetf, cuParamSeti, cuParamSetSize, cuParamSetTexRef, cuParamSetv, cuStreamAddCallback, cuStreamCreate, cuStreamCreateWithPriority, cuStreamGetFlags, cuStreamGetPriority, cuStreamQuery, cuStreamSynchronize, cuStreamWaitEvent, cuSurfRefGetArray, cuSurfRefSetArray, cuTexRefCreate, cuTexRefDestroy, cuTexRefGetAddress, cuTexRefGetAddressMode, cuTexRefGetArray, cuTexRefGetBorderColor, cuTexRefGetFilterMode, cuTexRefGetFlags, cuTexRefGetFormat, cuTexRefGetMaxAnisotropy, cuTexRefGetMipmapFilterMode, cuTexRefGetMipmapLevelBias, cuTexRefGetMipmapLevelClamp, cuTexRefGetMipmappedArray, cuTexRefSetAddress, cuTexRefSetAddress2D, cuTexRefSetAddressMode, cuTexRefSetArray, cuTexRefSetBorderColor, cuTexRefSetFilterMode, cuTexRefSetFlags, cuTexRefSetFormat, cuTexRefSetMaxAnisotropy, cuTexRefSetMipmapFilterMode, cuTexRefSetMipmapLevelBias, cuTexRefSetMipmapLevelClamp, cuTexRefSetMipmappedArray, getLibrary, ncuArray3DCreate, ncuArray3DGetDescriptor, ncuArrayCreate, ncuArrayGetDescriptor, ncuCtxAttach, ncuCtxCreate, ncuCtxGetApiVersion, ncuCtxGetCacheConfig, ncuCtxGetDevice, ncuCtxGetLimit, ncuCtxGetStreamPriorityRange, ncuDeviceComputeCapability, ncuDeviceGet, ncuDeviceGetAttribute, ncuDeviceGetCount, ncuDeviceGetName, ncuDeviceGetProperties, ncuDeviceTotalMem, ncuDriverGetVersion, ncuEventCreate, ncuEventElapsedTime, ncuFuncGetAttribute, ncuGetErrorName, ncuGetErrorString, ncuGetExportTable, ncuGraphicsMapResources, ncuGraphicsResourceGetMappedPointer, ncuGraphicsSubResourceGetMappedArray, ncuGraphicsUnmapResources, ncuMemAlloc, ncuMemAllocHost, ncuMemAllocPitch, ncuMemcpy2D, ncuMemcpy2DAsync, ncuMemcpy2DUnaligned, ncuMemcpy3D, ncuMemcpy3DAsync, ncuMemcpyAtoH, ncuMemcpyAtoHAsync, ncuMemcpyDtoH, ncuMemcpyDtoHAsync, ncuMemcpyHtoA, ncuMemcpyHtoAAsync, ncuMemcpyHtoD, ncuMemcpyHtoDAsync, ncuMemFreeHost, ncuMemGetAddressRange, ncuMemGetInfo, ncuMemHostAlloc, ncuMemHostGetDevicePointer, ncuMemHostGetFlags, ncuModuleGetFunction, ncuModuleGetGlobal, ncuModuleGetSurfRef, ncuModuleGetTexRef, ncuModuleLoad, ncuModuleLoadData, ncuModuleLoadDataEx, ncuModuleLoadFatBinary, ncuParamSetv, ncuStreamAddCallback, ncuStreamCreate, ncuStreamCreateWithPriority, ncuStreamGetFlags, ncuStreamGetPriority, ncuSurfRefGetArray, ncuTexRefCreate, ncuTexRefGetAddress, ncuTexRefGetAddressMode, ncuTexRefGetArray, ncuTexRefGetBorderColor, ncuTexRefGetFilterMode, ncuTexRefGetFlags, ncuTexRefGetFormat, ncuTexRefGetMaxAnisotropy, ncuTexRefGetMipmapFilterMode, ncuTexRefGetMipmapLevelBias, ncuTexRefGetMipmapLevelClamp, ncuTexRefGetMipmappedArray, ncuTexRefSetAddress, ncuTexRefSetAddress2D, ncuTexRefSetBorderColorpublic static final int CU_STREAM_CAPTURE_MODE_GLOBAL
CUstreamCaptureMode)
For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode
public static final int CU_STREAM_CAPTURE_MODE_THREAD_LOCAL
CUstreamCaptureMode)
For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode
public static final int CU_STREAM_CAPTURE_MODE_RELAXED
CUstreamCaptureMode)
For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode
public static int cuStreamBeginCapture_v2(long hStream,
int mode)
public static int ncuThreadExchangeStreamCaptureMode(long mode)
ThreadExchangeStreamCaptureModepublic static int cuThreadExchangeStreamCaptureMode(java.nio.IntBuffer mode)
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 modeDuring 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
cuStreamBeginCapture 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 cuStreamBeginCapture-cuStreamEndCapture
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 CU_STREAM_CAPTURE_MODE_RELAXED at
cuStreamBeginCapture, or if any other thread has a concurrent capture sequence initiated with CU_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.mode - pointer to mode value to swap with the current modepublic static int ncuStreamGetCaptureInfo(long hStream,
long captureStatus,
long id)
StreamGetCaptureInfopublic static int cuStreamGetCaptureInfo(long hStream,
java.nio.IntBuffer captureStatus,
java.nio.LongBuffer id)
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
CU.CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.
A valid id is returned only if both of the following are true:
SUCCESScaptureStatus is set to STREAM_CAPTURE_STATUS_ACTIVEpublic static int ncuGraphExecKernelNodeSetParams(long hGraphExec,
long hNode,
long nodeParams)
GraphExecKernelNodeSetParamspublic static int cuGraphExecKernelNodeSetParams(long hGraphExec,
long hNode,
CUDA_KERNEL_NODE_PARAMS nodeParams)
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.
hGraphExec - the executable graph in which to set the specified nodehNode - kernel node from the graph from which graphExec was instantiatednodeParams - updated parameters to setCopyright LWJGL. All Rights Reserved. License terms.