cudart¶
Profiler Control¶
This section describes the profiler control functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaProfilerStart()¶
Enable profiling.
Enables profile collection by the active profiling tool for the current context. If profiling is already enabled, then cudaProfilerStart() has no effect.
cudaProfilerStart and cudaProfilerStop APIs are used to programmatically control the profiling granularity by allowing profiling to be done only on selective pieces of code.
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
cudaProfilerInitialize
cudaProfilerStop
cuProfilerStart
- cuda.cudart.cudaProfilerStop()¶
Disable profiling.
Disables profile collection by the active profiling tool for the current context. If profiling is already disabled, then cudaProfilerStop() has no effect.
cudaProfilerStart and cudaProfilerStop APIs are used to programmatically control the profiling granularity by allowing profiling to be done only on selective pieces of code.
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
cudaProfilerInitialize
cudaProfilerStart
cuProfilerStop
Device Management¶
impl_private
This section describes the device management functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaDeviceReset()¶
Destroy all allocations and reset all state on the current device in the current process.
Explicitly destroys and cleans up all resources associated with the current device in the current process. It is the caller’s responsibility to ensure that the 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 cudaStream_t, cudaEvent_t, cudaArray_t, cudaMipmappedArray_t, cudaTextureObject_t, cudaSurfaceObject_t, textureReference, surfaceReference, cudaExternalMemory_t, cudaExternalSemaphore_t and cudaGraphicsResource_t. Any subsequent API call to this device will reinitialize the device.
Note that this function will reset the device immediately. It is the caller’s responsibility to ensure that the device is not being accessed by any other host threads from the process when this function is called.
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
- cuda.cudart.cudaDeviceSynchronize()¶
Wait for compute device to finish.
Blocks until the device has completed all preceding requested tasks. cudaDeviceSynchronize() returns an error if one of the preceding tasks has failed. If the cudaDeviceScheduleBlockingSync flag was set for this device, the host thread will block until the device has finished its work.
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
cudaDeviceReset
cuCtxSynchronize
- cuda.cudart.cudaDeviceSetLimit(limit: cudaLimit, size_t value)¶
Set resource limits.
Setting limit to value is a request by the application to update the current limit maintained by the device. 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 cudaDeviceGetLimit() to find out exactly what the limit has been set to.
Setting each cudaLimit has its own specific restrictions, so each is discussed here.
cudaLimitStackSize controls the stack size in bytes of each GPU
thread. - cudaLimitPrintfFifoSize controls the size in bytes of the shared FIFO used by the printf() device system call. Setting cudaLimitPrintfFifoSize must not be performed after launching any kernel that uses the printf() device system call - in such case cudaErrorInvalidValue will be returned. - cudaLimitMallocHeapSize controls the size in bytes of the heap used by the malloc() and free() device system calls. Setting cudaLimitMallocHeapSize must not be performed after launching any kernel that uses the malloc() or free() device system calls - in such case cudaErrorInvalidValue will be returned. - cudaLimitDevRuntimeSyncDepth 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 runtime to reserve large amounts of device memory which can no longer be used for user allocations. If these reservations of device memory fail, cudaDeviceSetLimit will return cudaErrorMemoryAllocation, 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 cudaErrorUnsupportedLimit being returned. - cudaLimitDevRuntimePendingLaunchCount controls the maximum number of outstanding device runtime launches that can be made from the current device. 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 runtime to reserve larger amounts of device memory upfront which can no longer be used for allocations. If these reservations fail, cudaDeviceSetLimit will return cudaErrorMemoryAllocation, 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 cudaErrorUnsupportedLimit being returned. - cudaLimitMaxL2FetchGranularity controls the L2 cache fetch granularity. Values can range from 0B to 128B. This is purely a performance hint and it can be ignored or clamped depending on the platform. - cudaLimitPersistingL2CacheSize controls size in bytes available for persisting L2 cache. This is purely a performance hint and it can be ignored or clamped depending on the platform.
- Parameters
- limitcudaLimit
Limit to set
- valuesize_t
Size of limit
- Returns
- cudaError_t
cudaSuccess cudaErrorUnsupportedLimit cudaErrorInvalidValue cudaErrorMemoryAllocation
- None
None
See also
cudaDeviceGetLimit
cuCtxSetLimit
- cuda.cudart.cudaDeviceGetLimit(limit: cudaLimit)¶
Returns resource limits.
Returns in *pValue the current size of limit. The supported cudaLimit values are: - cudaLimitStackSize: stack size in bytes of each GPU thread; - cudaLimitPrintfFifoSize: size in bytes of the shared FIFO used by the printf() device system call. - cudaLimitMallocHeapSize: size in bytes of the heap used by the malloc() and free() device system calls; - cudaLimitDevRuntimeSyncDepth: maximum grid depth at which a thread can isssue the device runtime call cudaDeviceSynchronize() to wait on child grid launches to complete. - cudaLimitDevRuntimePendingLaunchCount: maximum number of outstanding device runtime launches. - cudaLimitMaxL2FetchGranularity: L2 cache fetch granularity. - cudaLimitPersistingL2CacheSize: Persisting L2 cache size in bytes
- Parameters
- limitcudaLimit
Limit to query
- Returns
- cudaError_t
cudaSuccess cudaErrorUnsupportedLimit cudaErrorInvalidValue
- pValueint
Returned size of the limit
See also
cudaDeviceSetLimit
cuCtxGetLimit
- cuda.cudart.cudaDeviceGetTexture1DLinearMaxWidth(cudaChannelFormatDesc fmtDesc: cudaChannelFormatDesc, int device)¶
Returns the maximum number of elements allocatable in a 1D linear texture for a given element size.
Returns in maxWidthInElements the maximum number of elements allocatable in a 1D linear texture for given format descriptor fmtDesc.
- Parameters
- fmtDesccudaChannelFormatDesc
Texture format description.
- Returns
- cudaError_t
cudaSuccess cudaErrorUnsupportedLimit cudaErrorInvalidValue
- maxWidthInElementsint
Returns maximum number of texture elements allocatable for given fmtDesc.
- cuda.cudart.cudaDeviceGetCacheConfig()¶
Returns the preferred cache configuration for the current device.
On devices where the L1 cache and shared memory use the same hardware resources, this returns through pCacheConfig the preferred cache configuration for the current device. This is only a preference. The runtime 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 pCacheConfig of cudaFuncCachePreferNone on devices where the size of the L1 cache and shared memory are fixed.
The supported cache configurations are: - cudaFuncCachePreferNone: no preference for shared memory or L1 (default) - cudaFuncCachePreferShared: prefer larger shared memory and smaller L1 cache - cudaFuncCachePreferL1: prefer larger L1 cache and smaller shared memory - cudaFuncCachePreferEqual: prefer equal size L1 cache and shared memory
- Returns
- cudaError_t
cudaSuccess
- pCacheConfigcudaFuncCache
Returned cache configuration
See also
cudaDeviceSetCacheConfig
cudaFuncSetCacheConfig
cuCtxGetCacheConfig
- cuda.cudart.cudaDeviceGetStreamPriorityRange()¶
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 the meaningful range as specified by this API, the priority is automatically clamped down or up to either *leastPriority or *greatestPriority respectively. See cudaStreamCreateWithPriority 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 cudaDeviceGetAttribute).
- Returns
- cudaError_t
cudaSuccess
- leastPriorityint
Pointer to an int in which the numerical value for least stream priority is returned
- greatestPriorityint
Pointer to an int in which the numerical value for greatest stream priority is returned
See also
cudaStreamCreateWithPriority
cudaStreamGetPriority
cuCtxGetStreamPriorityRange
- cuda.cudart.cudaDeviceSetCacheConfig(cacheConfig: cudaFuncCache)¶
Sets the preferred cache configuration for the current device.
On devices where the L1 cache and shared memory use the same hardware resources, this sets through cacheConfig the preferred cache configuration for the current device. This is only a preference. The runtime 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 cudaFuncSetCacheConfig (C API) or cudaFuncSetCacheConfig (C++ API) will be preferred over this device-wide setting. Setting the device-wide cache configuration to cudaFuncCachePreferNone 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.
The supported cache configurations are: - cudaFuncCachePreferNone: no preference for shared memory or L1 (default) - cudaFuncCachePreferShared: prefer larger shared memory and smaller L1 cache - cudaFuncCachePreferL1: prefer larger L1 cache and smaller shared memory - cudaFuncCachePreferEqual: prefer equal size L1 cache and shared memory
- Parameters
- cacheConfigcudaFuncCache
Requested cache configuration
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
cudaDeviceGetCacheConfig
cudaFuncSetCacheConfig
cuCtxSetCacheConfig
Returns the shared memory configuration for the current device.
This function will return in pConfig the current size of shared memory banks on the current device. On devices with configurable shared memory banks, cudaDeviceSetSharedMemConfig can be used to change this setting, so that all subsequent kernel launches will by default use the new bank size. When cudaDeviceGetSharedMemConfig is called on devices without configurable shared memory, it will return the fixed bank size of the hardware.
The returned bank configurations can be either: - cudaSharedMemBankSizeFourByte - shared memory bank width is four bytes. - cudaSharedMemBankSizeEightByte - shared memory bank width is eight bytes.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pConfigcudaSharedMemConfig
Returned cache configuration
See also
cudaDeviceSetCacheConfig
cudaDeviceGetCacheConfig
cudaDeviceSetSharedMemConfig
cudaFuncSetCacheConfig
cuCtxGetSharedMemConfig
Sets the shared memory configuration for the current device.
On devices with configurable shared memory banks, this function will set the shared memory bank size which is used for all subsequent kernel launches. Any per-function setting of shared memory set via cudaFuncSetSharedMemConfig will override the device wide setting.
Changing the shared memory configuration between launches may introduce a device side synchronization point.
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: - cudaSharedMemBankSizeDefault: set bank width the device default (currently, four bytes) - cudaSharedMemBankSizeFourByte: set shared memory bank width to be four bytes natively. - cudaSharedMemBankSizeEightByte: set shared memory bank width to be eight bytes natively.
- Parameters
- configcudaSharedMemConfig
Requested cache configuration
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaDeviceSetCacheConfig
cudaDeviceGetCacheConfig
cudaDeviceGetSharedMemConfig
cudaFuncSetCacheConfig
cuCtxSetSharedMemConfig
- cuda.cudart.cudaDeviceGetByPCIBusId(char *pciBusId)¶
Returns a handle to a compute device.
Returns in *device a device ordinal given a PCI bus ID string.
- Parameters
- pciBusIdbytes
String in one of the following forms:
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- deviceint
Returned device ordinal
See also
cudaDeviceGetPCIBusId
cuDeviceGetByPCIBusId
- cuda.cudart.cudaDeviceGetPCIBusId(int length, int device)¶
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. length specifies the maximum length of the string that may be returned.
- Parameters
- lengthint
Maximum length of string to store in name
- deviceint
Device to get identifier string for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- pciBusIdbytes
Returned identifier string for the device in the following format
See also
cudaDeviceGetByPCIBusId
cuDeviceGetPCIBusId
- cuda.cudart.cudaIpcGetEventHandle(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 cudaEventInterprocess and cudaEventDisableTiming flags set. This opaque handle may be copied into other processes and opened with cudaIpcOpenEventHandle to allow efficient hardware synchronization between GPU work in different processes.
After the event has been been opened in the importing process, cudaEventRecord, cudaEventSynchronize, cudaStreamWaitEvent and cudaEventQuery may be used in either process. Performing operations on the imported event after the exported event has been freed with cudaEventDestroy will result in undefined behavior.
IPC functionality is restricted to devices with support for unified addressing on Linux operating systems. IPC functionality is not supported on Tegra platforms.
- Parameters
- eventCUevent or cudaEvent_t
Event allocated with cudaEventInterprocess and cudaEventDisableTiming flags.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorMemoryAllocation cudaErrorMapBufferObjectFailed cudaErrorNotSupported cudaErrorInvalidValue
- handlecudaIpcEventHandle_t
Pointer to a user allocated cudaIpcEventHandle in which to return the opaque event handle
- cuda.cudart.cudaIpcOpenEventHandle(cudaIpcEventHandle_t handle: cudaIpcEventHandle_t)¶
Opens an interprocess event handle for use in the current process.
Opens an interprocess event handle exported from another process with cudaIpcGetEventHandle. This function returns a cudaEvent_t that behaves like a locally created event with the cudaEventDisableTiming flag specified. This event must be freed with cudaEventDestroy.
Performing operations on the imported event after the exported event has been freed with cudaEventDestroy will result in undefined behavior.
IPC functionality is restricted to devices with support for unified addressing on Linux operating systems. IPC functionality is not supported on Tegra platforms.
- Parameters
- handlecudaIpcEventHandle_t
Interprocess handle to open
- Returns
- cudaError_t
cudaSuccess cudaErrorMapBufferObjectFailed cudaErrorNotSupported cudaErrorInvalidValue cudaErrorDeviceUninitialized
- eventcudaEvent_t
Returns the imported event
- cuda.cudart.cudaIpcGetMemHandle(devPtr)¶
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 cudaMalloc 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 cudaFree and a subsequent call to cudaMalloc returns memory with the same device address, cudaIpcGetMemHandle will return a unique handle for the new memory.
IPC functionality is restricted to devices with support for unified addressing on Linux operating systems. IPC functionality is not supported on Tegra platforms.
- Parameters
- devPtrAny
Base pointer to previously allocated device memory
- Returns
- cudaError_t
cudaSuccess cudaErrorMemoryAllocation cudaErrorMapBufferObjectFailed cudaErrorNotSupported cudaErrorInvalidValue
- handlecudaIpcMemHandle_t
Pointer to user allocated cudaIpcMemHandle to return the handle in.
See also
- cuda.cudart.cudaIpcOpenMemHandle(cudaIpcMemHandle_t handle: cudaIpcMemHandle_t, unsigned 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 cudaIpcGetMemHandle into the current device address space. For contexts on different devices cudaIpcOpenMemHandle can attempt to enable peer access between the devices as if the user called cudaDeviceEnablePeerAccess. This behavior is controlled by the cudaIpcMemLazyEnablePeerAccess flag. cudaDeviceCanAccessPeer can determine if a mapping is possible.
cudaIpcOpenMemHandle can open handles to devices that may not be visible in the process calling the API.
Contexts that may open cudaIpcMemHandles are restricted in the following way. cudaIpcMemHandles from each device in a given process may only be opened by one context per device 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 cudaIpcOpenMemHandle must be freed with cudaIpcCloseMemHandle.
Calling cudaFree on an exported memory region before calling cudaIpcCloseMemHandle in the importing context will result in undefined behavior.
IPC functionality is restricted to devices with support for unified addressing on Linux operating systems. IPC functionality is not supported on Tegra platforms.
- Parameters
- handlecudaIpcMemHandle_t
::cudaIpcMemHandle to open
- flagsunsigned int
Flags for this operation. Must be specified as cudaIpcMemLazyEnablePeerAccess
- Returns
- cudaError_t
cudaSuccess cudaErrorMapBufferObjectFailed cudaErrorInvalidResourceHandle cudaErrorDeviceUninitialized cudaErrorTooManyPeers cudaErrorNotSupported cudaErrorInvalidValue
- devPtrint
Returned device pointer
See also
Notes
- No guarantees are made about the address returned in *devPtr.
In particular, multiple processes may not receive the same address for the same handle.
- cuda.cudart.cudaIpcCloseMemHandle(devPtr)¶
Attempts to close memory mapped with cudaIpcOpenMemHandle.
Decrements the reference count of the memory returnd by cudaIpcOpenMemHandle 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 operating systems. IPC functionality is not supported on Tegra platforms.
- Parameters
- devPtrAny
Device pointer returned by cudaIpcOpenMemHandle
- Returns
- cudaError_t
cudaSuccess cudaErrorMapBufferObjectFailed cudaErrorNotSupported cudaErrorInvalidValue
- None
None
See also
cudaMalloc
cudaFree
cudaIpcGetEventHandle
cudaIpcOpenEventHandle
cudaIpcGetMemHandle
cudaIpcOpenMemHandle
cuIpcCloseMemHandle
- cuda.cudart.cudaDeviceFlushGPUDirectRDMAWrites(target: cudaFlushGPUDirectRDMAWritesTarget, scope: cudaFlushGPUDirectRDMAWritesScope)¶
Blocks until remote writes are visible to the specified scope.
Blocks until remote writes to the target context via mappings created through GPUDirect RDMA 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 cudaDevAttrGPUDirectRDMAWritesOrdering, 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 cudaDevAttrGPUDirectRDMAFlushWritesOptions.
- Parameters
- targetcudaFlushGPUDirectRDMAWritesTarget
The target of the operation, see cudaFlushGPUDirectRDMAWritesTarget
- scopecudaFlushGPUDirectRDMAWritesScope
The scope of the operation, see cudaFlushGPUDirectRDMAWritesScope
- Returns
- cudaError_t
cudaSuccess cudaErrorNotSupported
- None
None
- cuda.cudart.cudaGetDeviceCount()¶
Returns the number of compute-capable devices.
Returns in *count the number of devices with compute capability greater or equal to 2.0 that are available for execution.
- Returns
- cudaError_t
cudaSuccess
- countint
Returns the number of devices with compute capability greater or equal to 2.0
See also
cudaGetDevice
cudaSetDevice
cudaGetDeviceProperties
cudaChooseDevice
cuDeviceGetCount
- cuda.cudart.cudaGetDeviceProperties(int device)¶
Returns information about the compute-device.
Returns in *prop the properties of device dev. The cudaDeviceProp structure is defined as: structcudaDeviceProp{ charname[256]; cudaUUID_tuuid; size_ttotalGlobalMem; size_tsharedMemPerBlock; intregsPerBlock; intwarpSize; size_tmemPitch; intmaxThreadsPerBlock; intmaxThreadsDim[3]; intmaxGridSize[3]; intclockRate; size_ttotalConstMem; intmajor; intminor; size_ttextureAlignment; size_ttexturePitchAlignment; intdeviceOverlap; intmultiProcessorCount; intkernelExecTimeoutEnabled; intintegrated; intcanMapHostMemory; intcomputeMode; intmaxTexture1D; intmaxTexture1DMipmap; intmaxTexture1DLinear; intmaxTexture2D[2]; intmaxTexture2DMipmap[2]; intmaxTexture2DLinear[3]; intmaxTexture2DGather[2]; intmaxTexture3D[3]; intmaxTexture3DAlt[3]; intmaxTextureCubemap; intmaxTexture1DLayered[2]; intmaxTexture2DLayered[3]; intmaxTextureCubemapLayered[2]; intmaxSurface1D; intmaxSurface2D[2]; intmaxSurface3D[3]; intmaxSurface1DLayered[2]; intmaxSurface2DLayered[3]; intmaxSurfaceCubemap; intmaxSurfaceCubemapLayered[2]; size_tsurfaceAlignment; intconcurrentKernels; intECCEnabled; intpciBusID; intpciDeviceID; intpciDomainID; inttccDriver; intasyncEngineCount; intunifiedAddressing; intmemoryClockRate; intmemoryBusWidth; intl2CacheSize; intpersistingL2CacheMaxSize; intmaxThreadsPerMultiProcessor; intstreamPrioritiesSupported; intglobalL1CacheSupported; intlocalL1CacheSupported; size_tsharedMemPerMultiprocessor; intregsPerMultiprocessor; intmanagedMemory; intisMultiGpuBoard; intmultiGpuBoardGroupID; intsingleToDoublePrecisionPerfRatio; intpageableMemoryAccess; intconcurrentManagedAccess; intcomputePreemptionSupported; intcanUseHostPointerForRegisteredMem; intcooperativeLaunch; intcooperativeMultiDeviceLaunch; intpageableMemoryAccessUsesHostPageTables; intdirectManagedMemAccessFromHost; intaccessPolicyMaxWindowSize; } where: - name[256] is an ASCII string identifying the device; - uuid is a 16-byte unique identifier. - totalGlobalMem is the total amount of global memory available on the device in bytes; - sharedMemPerBlock is the maximum amount of shared memory available to a thread block in bytes; - regsPerBlock is the maximum number of 32-bit registers available to a thread block; - warpSize is the warp size in threads; - memPitch is the maximum pitch in bytes allowed by the memory copy functions that involve memory regions allocated through cudaMallocPitch(); - maxThreadsPerBlock is the maximum number of threads per block; - maxThreadsDim[3] contains the maximum size of each dimension of a block; - maxGridSize[3] contains the maximum size of each dimension of a grid; - clockRate is the clock frequency in kilohertz; - totalConstMem is the total amount of constant memory available on the device in bytes; - major, minor are the major and minor revision numbers defining the device’s compute capability; - textureAlignment is the alignment requirement; texture base addresses that are aligned to textureAlignment bytes do not need an offset applied to texture fetches; - texturePitchAlignment is the pitch alignment requirement for 2D texture references that are bound to pitched memory; - deviceOverlap is 1 if the device can concurrently copy memory between host and device while executing a kernel, or 0 if not. Deprecated, use instead asyncEngineCount. - multiProcessorCount is the number of multiprocessors on the device; - kernelExecTimeoutEnabled is 1 if there is a run time limit for kernels executed on the device, or 0 if not. - integrated is 1 if the device is an integrated (motherboard) GPU and 0 if it is a discrete (card) component. - canMapHostMemory is 1 if the device can map host memory into the CUDA address space for use with cudaHostAlloc()/cudaHostGetDevicePointer(), or 0 if not; - computeMode is the compute mode that the device is currently in. Available modes are as follows: - cudaComputeModeDefault: Default mode - Device is not restricted and multiple threads can use cudaSetDevice() with this device. - cudaComputeModeExclusive: Compute-exclusive mode - Only one thread will be able to use cudaSetDevice() with this device. - cudaComputeModeProhibited: Compute-prohibited mode - No threads can use cudaSetDevice() with this device. - cudaComputeModeExclusiveProcess: Compute-exclusive- process mode - Many threads in one process will be able to use cudaSetDevice() with this device. If cudaSetDevice() is called on an already occupied device with computeMode cudaComputeModeExclusive, cudaErrorDeviceAlreadyInUse will be immediately returned indicating the device cannot be used. When an occupied exclusive mode device is chosen with cudaSetDevice, all subsequent non-device management runtime functions will return cudaErrorDevicesUnavailable. - maxTexture1D is the maximum 1D texture size. - maxTexture1DMipmap is the maximum 1D mipmapped texture texture size. - maxTexture1DLinear is the maximum 1D texture size for textures bound to linear memory. - maxTexture2D[2] contains the maximum 2D texture dimensions. - maxTexture2DMipmap[2] contains the maximum 2D mipmapped texture dimensions. - maxTexture2DLinear[3] contains the maximum 2D texture dimensions for 2D textures bound to pitch linear memory. - maxTexture2DGather[2] contains the maximum 2D texture dimensions if texture gather operations have to be performed. - maxTexture3D[3] contains the maximum 3D texture dimensions. - maxTexture3DAlt[3] contains the maximum alternate 3D texture dimensions. - maxTextureCubemap is the maximum cubemap texture width or height. - maxTexture1DLayered[2] contains the maximum 1D layered texture dimensions. - maxTexture2DLayered[3] contains the maximum 2D layered texture dimensions. - maxTextureCubemapLayered[2] contains the maximum cubemap layered texture dimensions. - maxSurface1D is the maximum 1D surface size. - maxSurface2D[2] contains the maximum 2D surface dimensions. - maxSurface3D[3] contains the maximum 3D surface dimensions. - maxSurface1DLayered[2] contains the maximum 1D layered surface dimensions. - maxSurface2DLayered[3] contains the maximum 2D layered surface dimensions. - maxSurfaceCubemap is the maximum cubemap surface width or height. - maxSurfaceCubemapLayered[2] contains the maximum cubemap layered surface dimensions. - surfaceAlignment specifies the alignment requirements for surfaces. - concurrentKernels is 1 if the device supports executing multiple kernels within the same context simultaneously, or 0 if not. It is not guaranteed that multiple kernels will be resident on the device concurrently so this feature should not be relied upon for correctness; - ECCEnabled is 1 if the device has ECC support turned on, or 0 if not. - pciBusID is the PCI bus identifier of the device. - pciDeviceID is the PCI device (sometimes called slot) identifier of the device. - pciDomainID is the PCI domain identifier of the device. - tccDriver is 1 if the device is using a TCC driver or 0 if not. - asyncEngineCount is 1 when the device can concurrently copy memory between host and device while executing a kernel. It is 2 when the device can concurrently copy memory between host and device in both directions and execute a kernel at the same time. It is 0 if neither of these is supported. - unifiedAddressing is 1 if the device shares a unified address space with the host and 0 otherwise. - memoryClockRate is the peak memory clock frequency in kilohertz. - memoryBusWidth is the memory bus width in bits. - l2CacheSize is L2 cache size in bytes. - persistingL2CacheMaxSize is L2 cache’s maximum persisting lines size in bytes. - maxThreadsPerMultiProcessor is the number of maximum resident threads per multiprocessor. - streamPrioritiesSupported is 1 if the device supports stream priorities, or 0 if it is not supported. - globalL1CacheSupported is 1 if the device supports caching of globals in L1 cache, or 0 if it is not supported. - localL1CacheSupported is 1 if the device supports caching of locals in L1 cache, or 0 if it is not supported. - sharedMemPerMultiprocessor is the maximum amount of shared memory available to a multiprocessor in bytes; this amount is shared by all thread blocks simultaneously resident on a multiprocessor; - regsPerMultiprocessor is the maximum number of 32-bit registers available to a multiprocessor; this number is shared by all thread blocks simultaneously resident on a multiprocessor; - managedMemory is 1 if the device supports allocating managed memory on this system, or 0 if it is not supported. - isMultiGpuBoard is 1 if the device is on a multi-GPU board (e.g. Gemini cards), and 0 if not; - multiGpuBoardGroupID is a unique identifier for a group of devices associated with the same board. Devices on the same multi-GPU board will share the same identifier; - singleToDoublePrecisionPerfRatio is the ratio of single precision performance (in floating-point operations per second) to double precision performance. - pageableMemoryAccess is 1 if the device supports coherently accessing pageable memory without calling cudaHostRegister on it, and 0 otherwise. - concurrentManagedAccess is 1 if the device can coherently access managed memory concurrently with the CPU, and 0 otherwise. - computePreemptionSupported is 1 if the device supports Compute Preemption, and 0 otherwise. - canUseHostPointerForRegisteredMem is 1 if the device can access host registered memory at the same virtual address as the CPU, and 0 otherwise. - cooperativeLaunch is 1 if the device supports launching cooperative kernels via cudaLaunchCooperativeKernel, and 0 otherwise. - cooperativeMultiDeviceLaunch is 1 if the device supports launching cooperative kernels via cudaLaunchCooperativeKernelMultiDevice, and 0 otherwise. - pageableMemoryAccessUsesHostPageTables is 1 if the device accesses pageable memory via the host’s page tables, and 0 otherwise. - directManagedMemAccessFromHost is 1 if the host can directly access managed memory on the device without migration, and 0 otherwise. - maxBlocksPerMultiProcessor is the maximum number of thread blocks that can reside on a multiprocessor. - accessPolicyMaxWindowSize is the maximum value of cudaAccessPolicyWindow::num_bytes.
- Parameters
- deviceint
Device number to get properties for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice
- propcudaDeviceProp
Properties for the specified device
See also
cudaGetDeviceCount
cudaGetDevice
cudaSetDevice
cudaChooseDevice
cudaDeviceGetAttribute
cuDeviceGetAttribute
cuDeviceGetName
- cuda.cudart.cudaDeviceGetAttribute(attr: cudaDeviceAttr, int device)¶
Returns information about the device.
Returns in *value the integer value of the attribute attr on device device. The supported attributes are: - cudaDevAttrMaxThreadsPerBlock: Maximum number of threads per block - cudaDevAttrMaxBlockDimX: Maximum x-dimension of a block - cudaDevAttrMaxBlockDimY: Maximum y-dimension of a block - cudaDevAttrMaxBlockDimZ: Maximum z-dimension of a block - cudaDevAttrMaxGridDimX: Maximum x-dimension of a grid - cudaDevAttrMaxGridDimY: Maximum y-dimension of a grid - cudaDevAttrMaxGridDimZ: Maximum z-dimension of a grid - cudaDevAttrMaxSharedMemoryPerBlock: Maximum amount of shared memory available to a thread block in bytes - cudaDevAttrTotalConstantMemory: Memory available on device for constant variables in a CUDA C kernel in bytes - cudaDevAttrWarpSize: Warp size in threads - cudaDevAttrMaxPitch: Maximum pitch in bytes allowed by the memory copy functions that involve memory regions allocated through cudaMallocPitch() - cudaDevAttrMaxTexture1DWidth: Maximum 1D texture width - cudaDevAttrMaxTexture1DLinearWidth: Maximum width for a 1D texture bound to linear memory - cudaDevAttrMaxTexture1DMipmappedWidth: Maximum mipmapped 1D texture width - cudaDevAttrMaxTexture2DWidth: Maximum 2D texture width - cudaDevAttrMaxTexture2DHeight: Maximum 2D texture height - cudaDevAttrMaxTexture2DLinearWidth: Maximum width for a 2D texture bound to linear memory - cudaDevAttrMaxTexture2DLinearHeight: Maximum height for a 2D texture bound to linear memory - cudaDevAttrMaxTexture2DLinearPitch: Maximum pitch in bytes for a 2D texture bound to linear memory - cudaDevAttrMaxTexture2DMipmappedWidth: Maximum mipmapped 2D texture width - cudaDevAttrMaxTexture2DMipmappedHeight: Maximum mipmapped 2D texture height - cudaDevAttrMaxTexture3DWidth: Maximum 3D texture width - cudaDevAttrMaxTexture3DHeight: Maximum 3D texture height - cudaDevAttrMaxTexture3DDepth: Maximum 3D texture depth - cudaDevAttrMaxTexture3DWidthAlt: Alternate maximum 3D texture width, 0 if no alternate maximum 3D texture size is supported - cudaDevAttrMaxTexture3DHeightAlt: Alternate maximum 3D texture height, 0 if no alternate maximum 3D texture size is supported - cudaDevAttrMaxTexture3DDepthAlt: Alternate maximum 3D texture depth, 0 if no alternate maximum 3D texture size is supported - cudaDevAttrMaxTextureCubemapWidth: Maximum cubemap texture width or height - cudaDevAttrMaxTexture1DLayeredWidth: Maximum 1D layered texture width - cudaDevAttrMaxTexture1DLayeredLayers: Maximum layers in a 1D layered texture - cudaDevAttrMaxTexture2DLayeredWidth: Maximum 2D layered texture width - cudaDevAttrMaxTexture2DLayeredHeight: Maximum 2D layered texture height - cudaDevAttrMaxTexture2DLayeredLayers: Maximum layers in a 2D layered texture - cudaDevAttrMaxTextureCubemapLayeredWidth: Maximum cubemap layered texture width or height - cudaDevAttrMaxTextureCubemapLayeredLayers: Maximum layers in a cubemap layered texture - cudaDevAttrMaxSurface1DWidth: Maximum 1D surface width - cudaDevAttrMaxSurface2DWidth: Maximum 2D surface width - cudaDevAttrMaxSurface2DHeight: Maximum 2D surface height - cudaDevAttrMaxSurface3DWidth: Maximum 3D surface width - cudaDevAttrMaxSurface3DHeight: Maximum 3D surface height - cudaDevAttrMaxSurface3DDepth: Maximum 3D surface depth - cudaDevAttrMaxSurface1DLayeredWidth: Maximum 1D layered surface width - cudaDevAttrMaxSurface1DLayeredLayers: Maximum layers in a 1D layered surface - cudaDevAttrMaxSurface2DLayeredWidth: Maximum 2D layered surface width - cudaDevAttrMaxSurface2DLayeredHeight: Maximum 2D layered surface height - cudaDevAttrMaxSurface2DLayeredLayers: Maximum layers in a 2D layered surface - cudaDevAttrMaxSurfaceCubemapWidth: Maximum cubemap surface width - cudaDevAttrMaxSurfaceCubemapLayeredWidth: Maximum cubemap layered surface width - cudaDevAttrMaxSurfaceCubemapLayeredLayers: Maximum layers in a cubemap layered surface - cudaDevAttrMaxRegistersPerBlock: Maximum number of 32-bit registers available to a thread block - cudaDevAttrClockRate: Peak clock frequency in kilohertz - cudaDevAttrTextureAlignment: Alignment requirement; texture base addresses aligned to textureAlign bytes do not need an offset applied to texture fetches - cudaDevAttrTexturePitchAlignment: Pitch alignment requirement for 2D texture references bound to pitched memory - cudaDevAttrGpuOverlap: 1 if the device can concurrently copy memory between host and device while executing a kernel, or 0 if not - cudaDevAttrMultiProcessorCount: Number of multiprocessors on the device - cudaDevAttrKernelExecTimeout: 1 if there is a run time limit for kernels executed on the device, or 0 if not - cudaDevAttrIntegrated: 1 if the device is integrated with the memory subsystem, or 0 if not - cudaDevAttrCanMapHostMemory: 1 if the device can map host memory into the CUDA address space, or 0 if not - cudaDevAttrComputeMode: Compute mode is the compute mode that the device is currently in. Available modes are as follows: - cudaComputeModeDefault: Default mode - Device is not restricted and multiple threads can use cudaSetDevice() with this device. - cudaComputeModeExclusive: Compute-exclusive mode - Only one thread will be able to use cudaSetDevice() with this device. - cudaComputeModeProhibited: Compute-prohibited mode - No threads can use cudaSetDevice() with this device. - cudaComputeModeExclusiveProcess: Compute-exclusive- process mode - Many threads in one process will be able to use cudaSetDevice() with this device. - cudaDevAttrConcurrentKernels: 1 if the device supports executing multiple kernels within the same context simultaneously, or 0 if not. It is not guaranteed that multiple kernels will be resident on the device concurrently so this feature should not be relied upon for correctness. - cudaDevAttrEccEnabled: 1 if error correction is enabled on the device, 0 if error correction is disabled or not supported by the device - cudaDevAttrPciBusId: PCI bus identifier of the device - cudaDevAttrPciDeviceId: PCI device (also known as slot) identifier of the device - cudaDevAttrTccDriver: 1 if the device is using a TCC driver. TCC is only available on Tesla hardware running Windows Vista or later. - cudaDevAttrMemoryClockRate: Peak memory clock frequency in kilohertz - cudaDevAttrGlobalMemoryBusWidth: Global memory bus width in bits - cudaDevAttrL2CacheSize: Size of L2 cache in bytes. 0 if the device doesn’t have L2 cache. - cudaDevAttrMaxThreadsPerMultiProcessor: Maximum resident threads per multiprocessor - cudaDevAttrUnifiedAddressing: 1 if the device shares a unified address space with the host, or 0 if not - cudaDevAttrComputeCapabilityMajor: Major compute capability version number - cudaDevAttrComputeCapabilityMinor: Minor compute capability version number - cudaDevAttrStreamPrioritiesSupported: 1 if the device supports stream priorities, or 0 if not - cudaDevAttrGlobalL1CacheSupported: 1 if device supports caching globals in L1 cache, 0 if not - cudaDevAttrLocalL1CacheSupported: 1 if device supports caching locals in L1 cache, 0 if not - cudaDevAttrMaxSharedMemoryPerMultiprocessor: Maximum amount of shared memory available to a multiprocessor in bytes; this amount is shared by all thread blocks simultaneously resident on a multiprocessor - cudaDevAttrMaxRegistersPerMultiprocessor: Maximum number of 32-bit registers available to a multiprocessor; this number is shared by all thread blocks simultaneously resident on a multiprocessor - cudaDevAttrManagedMemory: 1 if device supports allocating managed memory, 0 if not - cudaDevAttrIsMultiGpuBoard: 1 if device is on a multi-GPU board, 0 if not - cudaDevAttrMultiGpuBoardGroupID: Unique identifier for a group of devices on the same multi-GPU board - cudaDevAttrHostNativeAtomicSupported: 1 if the link between the device and the host supports native atomic operations - cudaDevAttrSingleToDoublePrecisionPerfRatio: Ratio of single precision performance (in floating-point operations per second) to double precision performance - cudaDevAttrPageableMemoryAccess: 1 if the device supports coherently accessing pageable memory without calling cudaHostRegister on it, and 0 otherwise - cudaDevAttrConcurrentManagedAccess: 1 if the device can coherently access managed memory concurrently with the CPU, and 0 otherwise - cudaDevAttrComputePreemptionSupported: 1 if the device supports Compute Preemption, 0 if not - cudaDevAttrCanUseHostPointerForRegisteredMem: 1 if the device can access host registered memory at the same virtual address as the CPU, and 0 otherwise - cudaDevAttrCooperativeLaunch: 1 if the device supports launching cooperative kernels via cudaLaunchCooperativeKernel, and 0 otherwise - cudaDevAttrCooperativeMultiDeviceLaunch: 1 if the device supports launching cooperative kernels via cudaLaunchCooperativeKernelMultiDevice, and 0 otherwise - cudaDevAttrCanFlushRemoteWrites: 1 if the device supports flushing of outstanding remote writes, and 0 otherwise - cudaDevAttrHostRegisterSupported: 1 if the device supports host memory registration via cudaHostRegister, and 0 otherwise - cudaDevAttrPageableMemoryAccessUsesHostPageTables: 1 if the device accesses pageable memory via the host’s page tables, and 0 otherwise - cudaDevAttrDirectManagedMemAccessFromHost: 1 if the host can directly access managed memory on the device without migration, and 0 otherwise - cudaDevAttrMaxSharedMemoryPerBlockOptin: Maximum per block shared memory size on the device. This value can be opted into when using cudaFuncSetAttribute - cudaDevAttrMaxBlocksPerMultiprocessor: Maximum number of thread blocks that can reside on a multiprocessor - cudaDevAttrMaxPersistingL2CacheSize: Maximum L2 persisting lines capacity setting in bytes - cudaDevAttrMaxAccessPolicyWindowSize: Maximum value of cudaAccessPolicyWindow::num_bytes - cudaDevAttrReservedSharedMemoryPerBlock: Shared memory reserved by CUDA driver per block in bytes - cudaDevAttrSparseCudaArraySupported: 1 if the device supports sparse CUDA arrays and sparse CUDA mipmapped arrays. - cudaDevAttrHostRegisterReadOnlySupported: Device supports using the cudaHostRegister flag cudaHostRegisterReadOnly to register memory that must be mapped as read-only to the GPU - cudaDevAttrMemoryPoolsSupported: 1 if the device supports using the cudaMallocAsync and cudaMemPool family of APIs, and 0 otherwise - cudaDevAttrGPUDirectRDMASupported: 1 if the device supports GPUDirect RDMA APIs, and 0 otherwise - cudaDevAttrGPUDirectRDMAFlushWritesOptions: bitmask to be interpreted according to the cudaFlushGPUDirectRDMAWritesOptions enum - cudaDevAttrGPUDirectRDMAWritesOrdering: see the cudaGPUDirectRDMAWritesOrdering enum for numerical values - cudaDevAttrMemoryPoolSupportedHandleTypes: Bitmask of handle types supported with mempool based IPC - cudaDevAttrDeferredMappingCudaArraySupported : 1 if the device supports deferred mapping CUDA arrays and CUDA mipmapped arrays.
- Parameters
- attrcudaDeviceAttr
Device attribute to query
- deviceint
Device number to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue
- valueint
Returned device attribute value
See also
cudaGetDeviceCount
cudaGetDevice
cudaSetDevice
cudaChooseDevice
cudaGetDeviceProperties
cuDeviceGetAttribute
- cuda.cudart.cudaDeviceGetDefaultMemPool(int device)¶
Returns the default mempool of a device.
The default mempool of a device contains device memory from that device.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorNotSupported
- None
None
- cuda.cudart.cudaDeviceSetMemPool(int device, memPool)¶
Sets the current memory pool of a device.
The memory pool must be local to the specified device. Unless a mempool is specified in the cudaMallocAsync call, cudaMallocAsync allocates from the current mempool of the provided stream’s device. By default, a device’s current memory pool is its default memory pool.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice cudaErrorNotSupported
- None
None
See also
Notes
Use cudaMallocFromPoolAsync to specify asynchronous allocations from a device different than the one the stream runs on.
- cuda.cudart.cudaDeviceGetMemPool(int device)¶
Gets the current mempool for a device.
Returns the last pool provided to cudaDeviceSetMemPool for this device or the device’s default memory pool if cudaDeviceSetMemPool 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 cuDeviceSetMemPool or cudaDeviceSetMemPool.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported
- None
None
- cuda.cudart.cudaDeviceGetNvSciSyncAttributes(int device, 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 that matches this device’s capabilities.
If NvSciSyncAttrKey_RequiredPerm field in nvSciSyncAttrList is already set this API will return cudaErrorInvalidValue.
The applications should set nvSciSyncAttrList to a valid NvSciSyncAttrList failing which this API will return cudaErrorInvalidHandle.
The flags controls how applications intends to use the NvSciSync created from the nvSciSyncAttrList. The valid flags are: - cudaNvSciSyncAttrSignal, specifies that the applications intends to signal an NvSciSync on this CUDA device. - cudaNvSciSyncAttrWait, specifies that the applications intends to wait on an NvSciSync on this CUDA device.
At least one of these flags must be set, failing which the API returns cudaErrorInvalidValue. 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
- deviceint
Valid Cuda Device to get NvSciSync attributes for.
- flagsint
flags describing NvSciSync usage.
- Returns
- cudaError_t
- nvSciSyncAttrListint
Return NvSciSync attributes supported.
- cuda.cudart.cudaDeviceGetP2PAttribute(attr: cudaDeviceP2PAttr, 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: - cudaDevP2PAttrPerformanceRank: A relative value indicating the performance of the link between two devices. Lower value means better performance (0 being the value used for most performant link). - cudaDevP2PAttrAccessSupported: 1 if peer access is enabled. - cudaDevP2PAttrNativeAtomicSupported: 1 if native atomic operations over the link are supported. - cudaDevP2PAttrCudaArrayAccessSupported: 1 if accessing CUDA arrays over the link is supported.
Returns cudaErrorInvalidDevice if srcDevice or dstDevice are not valid or if they represent the same device.
Returns cudaErrorInvalidValue if attrib is not valid or if value is a null pointer.
- Parameters
- attribcudaDeviceP2PAttr
The requested attribute of the link between srcDevice and dstDevice.
- srcDeviceint
The source device of the target link.
- dstDeviceint
The destination device of the target link.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue
- valueint
Returned value of the requested attribute
- cuda.cudart.cudaChooseDevice(cudaDeviceProp prop: cudaDeviceProp)¶
Select compute-device which best matches criteria.
Returns in *device the device which has properties that best match *prop.
- Parameters
- propcudaDeviceProp
Desired device properties
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- deviceint
Device with best match
- cuda.cudart.cudaSetDevice(int device)¶
Set device to be used for GPU executions.
Sets device as the current device for the calling host thread. Valid device id’s are 0 to (cudaGetDeviceCount() - 1).
Any device memory subsequently allocated from this host thread using cudaMalloc(), cudaMallocPitch() or cudaMallocArray() will be physically resident on device. Any host memory allocated from this host thread using cudaMallocHost() or cudaHostAlloc() or cudaHostRegister() will have its lifetime associated with device. Any streams or events created from this host thread will be associated with device. Any kernels launched from this host thread using the <<<>>> operator or cudaLaunchKernel() will be executed on device.
This call may be made from any host thread, to any device, and at any time. This function will do no synchronization with the previous or new device, and should be considered a very low overhead call. If the current context bound to the calling thread is not the primary context, this call will bind the primary context to the calling thread and all the subsequent memory allocations, stream and event creations, and kernel launches will be associated with the primary context.
- Parameters
- deviceint
Device on which the active host thread should execute the device code.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorDeviceAlreadyInUse
- None
None
See also
cudaGetDeviceCount
cudaGetDevice
cudaGetDeviceProperties
cudaChooseDevice
cuCtxSetCurrent
- cuda.cudart.cudaGetDevice()¶
Returns which device is currently being used.
Returns in *device the current device for the calling host thread.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- deviceint
Returns the device on which the active host thread executes the device code.
See also
cudaGetDeviceCount
cudaSetDevice
cudaGetDeviceProperties
cudaChooseDevice
cuCtxGetCurrent
- cuda.cudart.cudaSetDeviceFlags(unsigned int flags)¶
Sets flags to be used for device executions.
Records flags as the flags for the current device. If the current device has been set and that device has already been initialized, the previous flags are overwritten. If the current device has not been initialized, it is initialized with the provided flags. If no device has been made current to the calling thread, a default device is selected and initialized with the provided flags.
The two LSBs of the flags parameter can be used to control how the CPU thread interacts with the OS scheduler when waiting for results from the device.
cudaDeviceScheduleAuto: 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 device, otherwise CUDA will not yield while waiting for results and actively spin on the processor. Additionally, on Tegra devices, cudaDeviceScheduleAuto uses a heuristic based on the power profile of the platform and may choose cudaDeviceScheduleBlockingSync for low- powered devices. - cudaDeviceScheduleSpin: Instruct CUDA to actively spin when waiting for results from the device. This can decrease latency when waiting for the device, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread. - cudaDeviceScheduleYield: Instruct CUDA to yield its thread when waiting for results from the device. This can increase latency when waiting for the device, but can increase the performance of CPU threads performing work in parallel with the device. - cudaDeviceScheduleBlockingSync: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the device to finish work. - cudaDeviceBlockingSync: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the device to finish work. Deprecated: This flag was deprecated as of CUDA 4.0 and replaced with cudaDeviceScheduleBlockingSync. - cudaDeviceMapHost: This flag enables allocating pinned host memory that is accessible to the device. It is implicit for the runtime but may be absent if a context is created using the driver API. If this flag is not set, cudaHostGetDevicePointer() will always return a failure code. - cudaDeviceLmemResizeToMax: 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
- flagsunsigned int
Parameters for device operation
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGetDeviceFlags
cudaGetDeviceCount
cudaGetDevice
cudaGetDeviceProperties
cudaSetDevice
cudaSetValidDevices
cudaChooseDevice
cuDevicePrimaryCtxSetFlags
- cuda.cudart.cudaGetDeviceFlags()¶
Gets the flags for the current device.
Returns in flags the flags for the current device. If there is a current device for the calling thread, the flags for the device are returned. If there is no current device, the flags for the first device are returned, which may be the default flags. Compare to the behavior of cudaSetDeviceFlags.
Typically, the flags returned should match the behavior that will be seen if the calling thread uses a device after this call, without any change to the flags or current device inbetween by this or another thread. Note that if the device is not initialized, it is possible for another thread to change the flags for the current device before it is initialized. Additionally, when using exclusive mode, if this thread has not requested a specific device, it may use a device other than the first device, contrary to the assumption made by this function.
If a context has been created via the driver API and is current to the calling thread, the flags for that context are always returned.
Flags returned by this function may specifically include cudaDeviceMapHost even though it is not accepted by cudaSetDeviceFlags because it is implicit in runtime API flags. The reason for this is that the current context may have been created via the driver API in which case the flag is not implicit and may be unset.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice
- flagsunsigned int
Pointer to store the device flags
See also
cudaGetDevice
cudaGetDeviceProperties
cudaSetDevice
cudaSetDeviceFlags
cuCtxGetFlags
cuDevicePrimaryCtxGetState
Error Handling¶
This section describes the error handling functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaGetLastError()¶
Returns the last error from a runtime call.
Returns the last error that has been produced by any of the runtime calls in the same host thread and resets it to cudaSuccess.
- Returns
- cudaError_t
cudaSuccess cudaErrorMissingConfiguration cudaErrorMemoryAllocation cudaErrorInitializationError cudaErrorLaunchFailure cudaErrorLaunchTimeout cudaErrorLaunchOutOfResources cudaErrorInvalidDeviceFunction cudaErrorInvalidConfiguration cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidSymbol cudaErrorUnmapBufferObjectFailed cudaErrorInvalidDevicePointer cudaErrorInvalidTexture cudaErrorInvalidTextureBinding cudaErrorInvalidChannelDescriptor cudaErrorInvalidMemcpyDirection cudaErrorInvalidFilterSetting cudaErrorInvalidNormSetting cudaErrorUnknown cudaErrorInvalidResourceHandle cudaErrorInsufficientDriver cudaErrorNoDevice cudaErrorSetOnActiveProcess cudaErrorStartupFailure cudaErrorInvalidPtx cudaErrorUnsupportedPtxVersion cudaErrorNoKernelImageForDevice cudaErrorJitCompilerNotFound cudaErrorJitCompilationDisabled
- None
None
See also
- cuda.cudart.cudaPeekAtLastError()¶
Returns the last error from a runtime call.
Returns the last error that has been produced by any of the runtime calls in the same host thread. Note that this call does not reset the error to cudaSuccess like cudaGetLastError().
- Returns
- cudaError_t
cudaSuccess cudaErrorMissingConfiguration cudaErrorMemoryAllocation cudaErrorInitializationError cudaErrorLaunchFailure cudaErrorLaunchTimeout cudaErrorLaunchOutOfResources cudaErrorInvalidDeviceFunction cudaErrorInvalidConfiguration cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidSymbol cudaErrorUnmapBufferObjectFailed cudaErrorInvalidDevicePointer cudaErrorInvalidTexture cudaErrorInvalidTextureBinding cudaErrorInvalidChannelDescriptor cudaErrorInvalidMemcpyDirection cudaErrorInvalidFilterSetting cudaErrorInvalidNormSetting cudaErrorUnknown cudaErrorInvalidResourceHandle cudaErrorInsufficientDriver cudaErrorNoDevice cudaErrorSetOnActiveProcess cudaErrorStartupFailure cudaErrorInvalidPtx cudaErrorUnsupportedPtxVersion cudaErrorNoKernelImageForDevice cudaErrorJitCompilerNotFound cudaErrorJitCompilationDisabled
- None
None
See also
- cuda.cudart.cudaGetErrorName(error: cudaError_t)¶
Returns the string representation of an error code enum name.
Returns a string containing the name of an error code in the enum. If the error code is not recognized, “unrecognized error code” is returned.
- Parameters
- errorcudaError_t
Error code to convert to string
- Returns
- cudaError_t
char* pointer to a NULL-terminated string
- None
None
See also
cudaGetErrorString
cudaGetLastError
cudaPeekAtLastError
cudaError
cuGetErrorName
- cuda.cudart.cudaGetErrorString(error: cudaError_t)¶
Returns the description string for an error code.
Returns the description string for an error code. If the error code is not recognized, “unrecognized error code” is returned.
- Parameters
- errorcudaError_t
Error code to convert to string
- Returns
- cudaError_t
char* pointer to a NULL-terminated string
- None
None
See also
cudaGetErrorName
cudaGetLastError
cudaPeekAtLastError
cudaError
cuGetErrorString
Stream Management¶
This section describes the stream management functions of the CUDA runtime application programming interface.
- class cuda.cudart.cudaStreamCallback_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- cuda.cudart.cudaStreamCreate()¶
Create an asynchronous stream.
Creates a new asynchronous stream.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pStreamcudaStream_t
Pointer to new stream identifier
- cuda.cudart.cudaStreamCreateWithFlags(unsigned int flags)¶
Create an asynchronous stream.
Creates a new asynchronous stream. The flags argument determines the behaviors of the stream. Valid values for flags are - cudaStreamDefault: Default stream creation flag. - cudaStreamNonBlocking: 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
- flagsunsigned int
Parameters for stream creation
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pStreamcudaStream_t
Pointer to new stream identifier
- cuda.cudart.cudaStreamCreateWithPriority(unsigned int flags, int priority)¶
Create an asynchronous stream with the specified priority.
Creates a stream with the specified priority and returns a handle in pStream. 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 cudaDeviceGetStreamPriorityRange. If the specified priority is outside the numerical range returned by cudaDeviceGetStreamPriorityRange, it will automatically be clamped to the lowest or the highest number in the range.
- Parameters
- flagsunsigned int
Flags for stream creation. See cudaStreamCreateWithFlags for a list of valid flags that can be passed
- priorityint
Priority of the stream. Lower numbers represent higher priorities. See cudaDeviceGetStreamPriorityRange for more information about the meaningful stream priorities that can be passed.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pStreamcudaStream_t
Pointer to new stream identifier
See also
Notes
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.
- cuda.cudart.cudaStreamGetPriority(hStream)¶
Query the priority of a stream.
Query the priority of a stream. The priority is returned in in priority. Note that if the stream was created with a priority outside the meaningful numerical range returned by cudaDeviceGetStreamPriorityRange, this function returns the clamped priority. See cudaStreamCreateWithPriority for details about priority clamping.
- Parameters
- hStreamCUstream or cudaStream_t
Handle to the stream to be queried
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- priorityint
Pointer to a signed integer in which the stream’s priority is returned
See also
cudaStreamCreateWithPriority
cudaDeviceGetStreamPriorityRange
cudaStreamGetFlags
cuStreamGetPriority
- cuda.cudart.cudaStreamGetFlags(hStream)¶
Query the flags of a stream.
Query the flags of a stream. The flags are returned in flags. See cudaStreamCreateWithFlags for a list of valid flags.
- Parameters
- hStreamCUstream or cudaStream_t
Handle to the stream to be queried
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- flagsunsigned int
Pointer to an unsigned integer in which the stream’s flags are returned
See also
cudaStreamCreateWithPriority
cudaStreamCreateWithFlags
cudaStreamGetPriority
cuStreamGetFlags
- cuda.cudart.cudaCtxResetPersistingL2Cache()¶
Resets all persisting lines in cache to normal status.
Resets all persisting lines in cache to normal status. Takes effect on function return.
- Returns
- cudaError_t
cudaSuccess
- None
None
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaStreamCopyAttributes(dst, 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
- dstAny
Destination stream
- srcAny
Source stream For attributes see cudaStreamAttrID
- Returns
- cudaError_t
cudaSuccess cudaErrorNotSupported
- None
None
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaStreamGetAttribute(hStream, attr: cudaStreamAttrID)¶
Queries stream attribute.
Queries attribute attr from hStream and stores it in corresponding member of value_out.
- Parameters
- hStreamCUstream or cudaStream_t
- attrcudaStreamAttrID
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- value_outcudaStreamAttrValue
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaStreamSetAttribute(hStream, attr: cudaStreamAttrID, cudaStreamAttrValue value: cudaStreamAttrValue)¶
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.
- Parameters
- hStreamCUstream or cudaStream_t
- attrcudaStreamAttrID
- valuecudaStreamAttrValue
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- None
None
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaStreamDestroy(stream)¶
Destroys and cleans up an asynchronous stream.
Destroys and cleans up the asynchronous stream specified by stream.
In case the device is still doing work in the stream stream when cudaStreamDestroy() is called, the function will return immediately and the resources associated with stream will be released automatically once the device has completed all work in stream.
- Parameters
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- None
None
See also
- cuda.cudart.cudaStreamWaitEvent(stream, event, unsigned int flags)¶
Make a compute stream wait on an event.
Makes all future work submitted to stream wait for all work captured in event. See cudaEventRecord() for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. event may be from a different device than stream.
flags include: - cudaEventWaitDefault: Default event creation flag. - cudaEventWaitExternal: Event is captured in the graph as an external event node when performing stream capture.
- Parameters
- streamCUstream or cudaStream_t
Stream to wait
- eventCUevent or cudaEvent_t
Event to wait on
- flagsunsigned int
Parameters for the operation(See above)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- None
None
See also
- cuda.cudart.cudaStreamAddCallback(stream, callback, userData, unsigned int flags)¶
Add a callback to a compute stream.
The callback may be passed cudaSuccess or an error code. In the event of a device error, all subsequently executed callbacks will receive an appropriate cudaError_t.
Callbacks must not make any CUDA API calls. Attempting to use CUDA APIs may result in cudaErrorNotPermitted. 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 callbacks have executed. Thus, for example, a callback might use global attached memory even if work has been added to another stream, if it has been properly ordered 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
- streamCUstream or cudaStream_t
Stream to add callback to
- callbackAny
The function to call once preceding stream operations are complete
- userDataAny
User specified data to be passed to the callback function
- flagsunsigned int
Reserved for future use, must be 0
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorInvalidValue cudaErrorNotSupported
- None
None
See also
Notes
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 cudaLaunchHostFunc. Additionally, this function is not supported with cudaStreamBeginCapture and cudaStreamEndCapture, unlike cudaLaunchHostFunc.
- cuda.cudart.cudaStreamSynchronize(stream)¶
Waits for stream tasks to complete.
Blocks until stream has completed all operations. If the cudaDeviceScheduleBlockingSync flag was set for this device, the host thread will block until the stream is finished with all of its tasks.
- Parameters
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle
- None
None
See also
- cuda.cudart.cudaStreamQuery(stream)¶
Queries an asynchronous stream for completion status.
Returns cudaSuccess if all operations in stream have completed, or cudaErrorNotReady if not.
For the purposes of Unified Memory, a return value of cudaSuccess is equivalent to having called cudaStreamSynchronize().
- Parameters
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorNotReady cudaErrorInvalidResourceHandle
- None
None
- cuda.cudart.cudaStreamAttachMemAsync(stream, devPtr, size_t length, unsigned int flags)¶
Attach memory to a stream asynchronously.
Enqueues an operation in stream to specify stream association of length bytes of memory starting from devPtr. 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.
devPtr must point to an one of the following types of memories: - managed memory declared using the managed keyword or allocated with cudaMallocManaged. - 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 cudaDevAttrPageableMemoryAccess.
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 allocations, length must be non-zero.
The stream association is specified using flags which must be one of cudaMemAttachGlobal, cudaMemAttachHost or cudaMemAttachSingle. The default value for flags is cudaMemAttachSingle If the cudaMemAttachGlobal flag is specified, the memory can be accessed by any stream on any device. If the cudaMemAttachHost 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 cudaDevAttrConcurrentManagedAccess. If the cudaMemAttachSingle flag is specified and stream is associated with a device that has a zero value for the device attribute cudaDevAttrConcurrentManagedAccess, the program makes a guarantee that it will only access the memory on the device from stream. 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 stream 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 cudaStreamAttachMemAsync 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 stream 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 cudaMallocManaged. For managed variables, the default association is always cudaMemAttachGlobal. 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
- streamCUstream or cudaStream_t
Stream in which to enqueue the attach operation
- devPtrAny
Pointer to memory (must be a pointer to managed memory or to a valid host-accessible region of system-allocated memory)
- lengthsize_t
Length of memory (defaults to zero)
- flagsunsigned int
Must be one of cudaMemAttachGlobal, cudaMemAttachHost or cudaMemAttachSingle (defaults to cudaMemAttachSingle)
- Returns
- cudaError_t
cudaSuccess cudaErrorNotReady cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- None
None
See also
- cuda.cudart.cudaStreamBeginCapture(stream, mode: cudaStreamCaptureMode)¶
Begins graph capture on a stream.
Begin graph capture on stream. 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 cudaStreamEndCapture. Capture may not be initiated if stream is cudaStreamLegacy. 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 cudaStreamIsCapturing. A unique id representing the capture sequence may be queried via cudaStreamGetCaptureInfo.
If mode is not cudaStreamCaptureModeRelaxed, cudaStreamEndCapture must be called on this stream from the same thread.
- Parameters
- streamCUstream or cudaStream_t
Stream in which to initiate capture
- modecudaStreamCaptureMode
Controls the interaction of this capture sequence with other API calls that are potentially unsafe. For more details see cudaThreadExchangeStreamCaptureMode.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
Notes
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.
- cuda.cudart.cudaThreadExchangeStreamCaptureMode(mode: cudaStreamCaptureMode)¶
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:cudaStreamCaptureModemode=desiredMode; cudaThreadExchangeStreamCaptureMode(&mode); … cudaThreadExchangeStreamCaptureMode(&mode);//restorepreviousmode
During stream capture (see cudaStreamBeginCapture), 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 cudaStreamBeginCapture 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 cudaStreamBeginCapture- cudaStreamEndCapture sequence. This behavior can be controlled via this API and flags to cudaStreamBeginCapture.
A thread’s mode is one of the following: - cudaStreamCaptureModeGlobal: This is the default mode. If the local thread has an ongoing capture sequence that was not initiated with cudaStreamCaptureModeRelaxed at cuStreamBeginCapture, or if any other thread has a concurrent capture sequence initiated with cudaStreamCaptureModeGlobal, this thread is prohibited from potentially unsafe API calls. - cudaStreamCaptureModeThreadLocal: If the local thread has an ongoing capture sequence not initiated with cudaStreamCaptureModeRelaxed, it is prohibited from potentially unsafe API calls. Concurrent capture sequences in other threads are ignored. - cudaStreamCaptureModeRelaxed: 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 cudaEventQuery on an event that was last recorded inside a capture sequence.
- Parameters
- modecudaStreamCaptureMode
Pointer to mode value to swap with the current mode
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
- cuda.cudart.cudaStreamEndCapture(stream)¶
Ends capture on a stream, returning the captured graph.
End capture on stream, returning the captured graph via pGraph. Capture must have been initiated on stream via a call to cudaStreamBeginCapture. 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 cudaStreamBeginCapture was not cudaStreamCaptureModeRelaxed, this call must be from the same thread as cudaStreamBeginCapture.
- Parameters
- streamCUstream or cudaStream_t
Stream to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorStreamCaptureWrongThread
- pGraphcudaGraph_t
The captured graph
- cuda.cudart.cudaStreamIsCapturing(stream)¶
Returns a stream’s capture status.
Return the capture status of stream via pCaptureStatus. After a successful call, *pCaptureStatus will contain one of the following: - cudaStreamCaptureStatusNone: The stream is not capturing. - cudaStreamCaptureStatusActive: The stream is capturing. - cudaStreamCaptureStatusInvalidated: The stream was capturing but an error has invalidated the capture sequence. The capture sequence must be terminated with cudaStreamEndCapture on the stream where it was initiated in order to continue using stream.
Note that, if this is called on cudaStreamLegacy (the “null stream”) while a blocking stream on the same device is capturing, it will return cudaErrorStreamCaptureImplicit and *pCaptureStatus 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
- streamCUstream or cudaStream_t
Stream to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorStreamCaptureImplicit
- pCaptureStatuscudaStreamCaptureStatus
Returns the stream’s capture status
- cuda.cudart.cudaStreamGetCaptureInfo(stream)¶
Query capture status of a stream.
Note there is a later version of this API, cudaStreamGetCaptureInfo_v2. It will supplant this version in 12.0, which is retained for minor version compatibility.
Query the capture status of a stream and get a unique id representing the capture sequence over the lifetime of the process.
If called on cudaStreamLegacy (the “null stream”) while a stream not created with cudaStreamNonBlocking is capturing, returns cudaErrorStreamCaptureImplicit.
A valid id is returned only if both of the following are true: - the call returns cudaSuccess - captureStatus is set to cudaStreamCaptureStatusActive
- Parameters
- streamCUstream or cudaStream_t
Stream to query
- Returns
- cudaError_t
cudaSuccess cudaErrorStreamCaptureImplicit
- pCaptureStatuscudaStreamCaptureStatus
Returns the stream’s capture status
- pIdunsigned long long
Returns the unique id of the capture sequence
- cuda.cudart.cudaStreamGetCaptureInfo_v2(stream) Query a stream's capture state (11.3+)¶
Query a stream’s capture state (11.3+)
Query stream state related to stream capture.
If called on cudaStreamLegacy (the “null stream”) while a stream not created with cudaStreamNonBlocking is capturing, returns cudaErrorStreamCaptureImplicit.
Valid data (other than capture status) is returned only if both of the following are true: - the call returns cudaSuccess - the returned capture status is cudaStreamCaptureStatusActive
This version of cudaStreamGetCaptureInfo is introduced in CUDA 11.3 and will supplant the previous version cudaStreamGetCaptureInfo in 12.0. Developers requiring compatibility across minor versions to CUDA 11.0 (driver version 445) can do one of the following: - Use the older version of the API, cudaStreamGetCaptureInfo - Pass null for all of graph_out, dependencies_out, and numDependencies_out.
- Parameters
- streamCUstream or cudaStream_t
The stream to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorStreamCaptureImplicit
- captureStatus_outcudaStreamCaptureStatus
Location to return the capture status of the stream; required
- id_outunsigned long long
Optional location to return an id for the capture sequence, which is unique over the lifetime of the process
- graph_outcudaGraph_t
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 cudaStreamEndCapture. 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 cudaStreamEndCapture due to direct actions on the graph do not trigger cudaErrorStreamCaptureUnjoined.
- dependencies_outList[cudaGraphNode_t]
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_outint
Optional location to store the size of the array returned in dependencies_out.
- cuda.cudart.cudaStreamUpdateCaptureDependencies(stream, dependencies: List[cudaGraphNode_t], size_t numDependencies, unsigned int flags) Update the set of dependencies in a capturing stream (11.3+)¶
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 cudaStreamAddCaptureDependencies and cudaStreamSetCaptureDependencies. 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 cudaStreamAddCaptureDependencies.
Nodes that are removed from the dependency set via this API do not result in cudaErrorStreamCaptureUnjoined if they are unreachable from the stream at cudaStreamEndCapture.
Returns cudaErrorIllegalState if the stream is not capturing.
This API is new in CUDA 11.3. Developers requiring compatibility across minor versions of the CUDA driver to 11.0 should not use this API or provide a fallback.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorIllegalState
- None
None
Event Management¶
This section describes the event management functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaEventCreate()¶
Creates an event object.
Creates an event object for the current device using cudaEventDefault.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorLaunchFailure cudaErrorMemoryAllocation
- eventcudaEvent_t
Newly created event
- cuda.cudart.cudaEventCreateWithFlags(unsigned int flags)¶
Creates an event object with the specified flags.
Creates an event object for the current device with the specified flags. Valid flags include: - cudaEventDefault: Default event creation flag. - cudaEventBlockingSync: Specifies that event should use blocking synchronization. A host thread that uses cudaEventSynchronize() to wait on an event created with this flag will block until the event actually completes. - cudaEventDisableTiming: Specifies that the created event does not need to record timing data. Events created with this flag specified and the cudaEventBlockingSync flag not specified will provide the best performance when used with cudaStreamWaitEvent() and cudaEventQuery(). - cudaEventInterprocess: Specifies that the created event may be used as an interprocess event by cudaIpcGetEventHandle(). cudaEventInterprocess must be specified along with cudaEventDisableTiming.
- Parameters
- flagsunsigned int
Flags for new event
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorLaunchFailure cudaErrorMemoryAllocation
- eventcudaEvent_t
Newly created event
See also
- cuda.cudart.cudaEventRecord(event, stream)¶
Records an event.
Captures in event the contents of stream at the time of this call. event and stream must be on the same CUDA context. Calls such as cudaEventQuery() or cudaStreamWaitEvent() will then examine or wait for completion of the work that was captured. Uses of stream after this call do not modify event. See note on default stream behavior for what is captured in the default case.
cudaEventRecord() can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as cudaStreamWaitEvent() use the most recently captured state at the time of the API call, and are not affected by later calls to cudaEventRecord(). Before the first call to cudaEventRecord(), an event represents an empty set of work, so for example cudaEventQuery() would return cudaSuccess.
- Parameters
- eventCUevent or cudaEvent_t
Event to record
- streamCUstream or cudaStream_t
Stream in which to record event
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- None
None
- cuda.cudart.cudaEventRecordWithFlags(event, stream, unsigned int flags)¶
Records an event.
Captures in event the contents of stream at the time of this call. event and stream must be on the same CUDA context. Calls such as cudaEventQuery() or cudaStreamWaitEvent() will then examine or wait for completion of the work that was captured. Uses of stream after this call do not modify event. See note on default stream behavior for what is captured in the default case.
cudaEventRecordWithFlags() can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as cudaStreamWaitEvent() use the most recently captured state at the time of the API call, and are not affected by later calls to cudaEventRecordWithFlags(). Before the first call to cudaEventRecordWithFlags(), an event represents an empty set of work, so for example cudaEventQuery() would return cudaSuccess.
flags include: - cudaEventRecordDefault: Default event creation flag. - cudaEventRecordExternal: Event is captured in the graph as an external event node when performing stream capture.
- Parameters
- eventCUevent or cudaEvent_t
Event to record
- streamCUstream or cudaStream_t
Stream in which to record event
- flagsunsigned int
Parameters for the operation(See above)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- None
None
- cuda.cudart.cudaEventQuery(event)¶
Queries an event’s status.
Queries the status of all work currently captured by event. See cudaEventRecord() for details on what is captured by an event.
Returns cudaSuccess if all captured work has been completed, or cudaErrorNotReady if any captured work is incomplete.
For the purposes of Unified Memory, a return value of cudaSuccess is equivalent to having called cudaEventSynchronize().
- Parameters
- eventCUevent or cudaEvent_t
Event to query
- Returns
- cudaError_t
cudaSuccess cudaErrorNotReady cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- None
None
- cuda.cudart.cudaEventSynchronize(event)¶
Waits for an event to complete.
Waits until the completion of all work currently captured in event. See cudaEventRecord() for details on what is captured by an event.
Waiting for an event that was created with the cudaEventBlockingSync flag will cause the calling CPU thread to block until the event has been completed by the device. If the cudaEventBlockingSync flag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.
- Parameters
- eventCUevent or cudaEvent_t
Event to wait for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- None
None
See also
- cuda.cudart.cudaEventDestroy(event)¶
Destroys an event object.
Destroys the event specified by event.
An event may be destroyed before it is complete (i.e., while cudaEventQuery() would return cudaErrorNotReady). 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
- eventCUevent or cudaEvent_t
Event to destroy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- None
None
See also
- cuda.cudart.cudaEventElapsedTime(start, end)¶
Computes the elapsed time between 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 cudaEventRecord() 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 cudaEventRecord() has not been called on either event, then cudaErrorInvalidResourceHandle is returned. If cudaEventRecord() has been called on both events but one or both of them has not yet been completed (that is, cudaEventQuery() would return cudaErrorNotReady on at least one of the events), cudaErrorNotReady is returned. If either event was created with the cudaEventDisableTiming flag, then this function will return cudaErrorInvalidResourceHandle.
- Parameters
- startAny
Starting event
- endAny
Ending event
- Returns
- cudaError_t
cudaSuccess cudaErrorNotReady cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorLaunchFailure
- msfloat
Time between start and end in ms
See also
External Resource Interoperability¶
This section describes the external resource interoperability functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaImportExternalMemory(cudaExternalMemoryHandleDesc memHandleDesc: cudaExternalMemoryHandleDesc)¶
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. The cudaExternalMemoryHandleDesc structure is defined as follows:
typedefstructcudaExternalMemoryHandleDesc_st{ cudaExternalMemoryHandleTypetype; union{ intfd; struct{ void*handle; constvoid*name; }win32; constvoid*nvSciBufObject; }handle; unsignedlonglongsize; unsignedintflags; }cudaExternalMemoryHandleDesc;
where cudaExternalMemoryHandleDesc::type specifies the type of handle being imported. cudaExternalMemoryHandleType is defined as:
typedefenumcudaExternalMemoryHandleType_enum{ cudaExternalMemoryHandleTypeOpaqueFd=1, cudaExternalMemoryHandleTypeOpaqueWin32=2, cudaExternalMemoryHandleTypeOpaqueWin32Kmt=3, cudaExternalMemoryHandleTypeD3D12Heap=4, cudaExternalMemoryHandleTypeD3D12Resource=5, cudaExternalMemoryHandleTypeD3D11Resource=6, cudaExternalMemoryHandleTypeD3D11ResourceKmt=7, cudaExternalMemoryHandleTypeNvSciBuf=8 }cudaExternalMemoryHandleType;
If cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeOpaqueFd, then cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeOpaqueWin32, then exactly one of cudaExternalMemoryHandleDesc::handle::win32::handle and cudaExternalMemoryHandleDesc::handle::win32::name must not be NULL. If cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeOpaqueWin32Kmt, then cudaExternalMemoryHandleDesc::handle::win32::handle must be non-NULL and cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeD3D12Heap, then exactly one of cudaExternalMemoryHandleDesc::handle::win32::handle and cudaExternalMemoryHandleDesc::handle::win32::name must not be NULL. If cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeD3D12Resource, then exactly one of cudaExternalMemoryHandleDesc::handle::win32::handle and cudaExternalMemoryHandleDesc::handle::win32::name must not be NULL. If cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeD3D11Resource,then exactly one of cudaExternalMemoryHandleDesc::handle::win32::handle and cudaExternalMemoryHandleDesc::handle::win32::name must not be NULL. If cudaExternalMemoryHandleDesc::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a ID3D11Resource object. If cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeD3D11ResourceKmt, then cudaExternalMemoryHandleDesc::handle::win32::handle must be non-NULL and cudaExternalMemoryHandleDesc::handle::win32::name must be NULL. The handle specified must be a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a ID3D11Resource object.
If cudaExternalMemoryHandleDesc::type is cudaExternalMemoryHandleTypeNvSciBuf, then cudaExternalMemoryHandleDesc::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 cudaWaitExternalSemaphoresAsync or cudaSignalExternalSemaphoresAsync as approprriate barriers to maintain coherence between CUDA and the other drivers. See cudaExternalSemaphoreWaitSkipNvSciBufMemSync and cudaExternalSemaphoreSignalSkipNvSciBufMemSync for memory synchronization.
The size of the memory object must be specified in cudaExternalMemoryHandleDesc::size.
Specifying the flag cudaExternalMemoryDedicated in cudaExternalMemoryHandleDesc::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 cudaExternalMemoryHandleDesc::type is one of the following: cudaExternalMemoryHandleTypeD3D12Resource cudaExternalMemoryHandleTypeD3D11Resource cudaExternalMemoryHandleTypeD3D11ResourceKmt
- Parameters
- memHandleDesccudaExternalMemoryHandleDesc
Memory import handle descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- extMem_outcudaExternalMemory_t
Returned handle to an external memory object
See also
Notes
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.
- cuda.cudart.cudaExternalMemoryGetMappedBuffer(extMem, cudaExternalMemoryBufferDesc bufferDesc: cudaExternalMemoryBufferDesc)¶
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 cudaExternalMemoryBufferDesc structure is defined as follows:
typedefstructcudaExternalMemoryBufferDesc_st{ unsignedlonglongoffset; unsignedlonglongsize; unsignedintflags; }cudaExternalMemoryBufferDesc;
where cudaExternalMemoryBufferDesc::offset is the offset in the memory object where the buffer’s base address is. cudaExternalMemoryBufferDesc::size is the size of the buffer. cudaExternalMemoryBufferDesc::flags must be zero.
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 cudaFree.
- Parameters
- extMemAny
Handle to external memory object
- bufferDesccudaExternalMemoryBufferDesc
Buffer descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- devPtrint
Returned device pointer to buffer
- cuda.cudart.cudaExternalMemoryGetMappedMipmappedArray(extMem, cudaExternalMemoryMipmappedArrayDesc mipmapDesc: cudaExternalMemoryMipmappedArrayDesc)¶
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. The structure cudaExternalMemoryMipmappedArrayDesc is defined as follows:
typedefstructcudaExternalMemoryMipmappedArrayDesc_st{ unsignedlonglongoffset; cudaChannelFormatDescformatDesc; cudaExtentextent; unsignedintflags; unsignedintnumLevels; }cudaExternalMemoryMipmappedArrayDesc;
where cudaExternalMemoryMipmappedArrayDesc::offset is the offset in the memory object where the base level of the mipmap chain is. cudaExternalMemoryMipmappedArrayDesc::formatDesc describes the format of the data. cudaExternalMemoryMipmappedArrayDesc::extent specifies the dimensions of the base level of the mipmap chain. cudaExternalMemoryMipmappedArrayDesc::flags are flags associated with CUDA mipmapped arrays. For further details, please refer to the documentation for cudaMalloc3DArray. Note that if the mipmapped array is bound as a color target in the graphics API, then the flag cudaArrayColorAttachment must be specified in cudaExternalMemoryMipmappedArrayDesc::flags. cudaExternalMemoryMipmappedArrayDesc::numLevels specifies the total number of levels in the mipmap chain.
The returned CUDA mipmapped array must be freed using cudaFreeMipmappedArray.
- Parameters
- extMemAny
Handle to external memory object
- mipmapDesccudaExternalMemoryMipmappedArrayDesc
CUDA array descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- mipmapcudaMipmappedArray_t
Returned CUDA mipmapped array
Notes
If cudaExternalMemoryHandleDesctype is cudaExternalMemoryHandleTypeNvSciBuf, then cudaExternalMemoryMipmappedArrayDescnumLevels must not be greater than 1.
- cuda.cudart.cudaDestroyExternalMemory(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 cudaFree and cudaFreeMipmappedArray respectively.
- Parameters
- extMemAny
External memory object to be destroyed
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle
- None
None
- cuda.cudart.cudaImportExternalSemaphore(cudaExternalSemaphoreHandleDesc semHandleDesc: cudaExternalSemaphoreHandleDesc)¶
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. The cudaExternalSemaphoreHandleDesc is defined as follows:
typedefstructcudaExternalSemaphoreHandleDesc_st{ cudaExternalSemaphoreHandleTypetype; union{ intfd; struct{ void*handle; constvoid*name; }win32; constvoid*NvSciSyncObj; }handle; unsignedintflags; }cudaExternalSemaphoreHandleDesc;
where cudaExternalSemaphoreHandleDesc::type specifies the type of handle being imported. cudaExternalSemaphoreHandleType is defined as:
typedefenumcudaExternalSemaphoreHandleType_enum{ cudaExternalSemaphoreHandleTypeOpaqueFd=1, cudaExternalSemaphoreHandleTypeOpaqueWin32=2, cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt=3, cudaExternalSemaphoreHandleTypeD3D12Fence=4, cudaExternalSemaphoreHandleTypeD3D11Fence=5, cudaExternalSemaphoreHandleTypeNvSciSync=6, cudaExternalSemaphoreHandleTypeKeyedMutex=7, cudaExternalSemaphoreHandleTypeKeyedMutexKmt=8, cudaExternalSemaphoreHandleTypeTimelineSemaphoreFd=9, cudaExternalSemaphoreHandleTypeTimelineSemaphoreWin32=10 }cudaExternalSemaphoreHandleType;
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeOpaqueFd, then cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeOpaqueWin32, then exactly one of cudaExternalSemaphoreHandleDesc::handle::win32::handle and cudaExternalSemaphoreHandleDesc::handle::win32::name must not be NULL. If cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::handle::win32::name is not NULL, then it must name a valid synchronization object.
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt, then cudaExternalSemaphoreHandleDesc::handle::win32::handle must be non-NULL and cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeD3D12Fence, then exactly one of cudaExternalSemaphoreHandleDesc::handle::win32::handle and cudaExternalSemaphoreHandleDesc::handle::win32::name must not be NULL. If cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D12Fence object.
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeD3D11Fence, then exactly one of cudaExternalSemaphoreHandleDesc::handle::win32::handle and cudaExternalSemaphoreHandleDesc::handle::win32::name must not be NULL. If cudaExternalSemaphoreHandleDesc::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D11Fence::CreateSharedHandle. If cudaExternalSemaphoreHandleDesc::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D11Fence object.
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeNvSciSync, then cudaExternalSemaphoreHandleDesc::handle::nvSciSyncObj represents a valid NvSciSyncObj.
::cudaExternalSemaphoreHandleTypeKeyedMutex, then exactly one of cudaExternalSemaphoreHandleDesc::handle::win32::handle and cudaExternalSemaphoreHandleDesc::handle::win32::name must not be NULL. If cudaExternalSemaphoreHandleDesc::handle::win32::handle is not NULL, then it represent a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a IDXGIKeyedMutex object.
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeKeyedMutexKmt, then cudaExternalSemaphoreHandleDesc::handle::win32::handle must be non-NULL and cudaExternalSemaphoreHandleDesc::handle::win32::name must be NULL. The handle specified must represent a valid KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a IDXGIKeyedMutex object.
If cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeTimelineSemaphoreFd, then cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::type is cudaExternalSemaphoreHandleTypeTimelineSemaphoreWin32, then exactly one of cudaExternalSemaphoreHandleDesc::handle::win32::handle and cudaExternalSemaphoreHandleDesc::handle::win32::name must not be NULL. If cudaExternalSemaphoreHandleDesc::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 cudaExternalSemaphoreHandleDesc::handle::win32::name is not NULL, then it must name a valid synchronization object.
- Parameters
- semHandleDesccudaExternalSemaphoreHandleDesc
Semaphore import handle descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle
- extSem_outcudaExternalSemaphore_t
Returned handle to an external semaphore
- cuda.cudart.cudaSignalExternalSemaphoresAsync(extSemArray: List[cudaExternalSemaphore_t], paramsArray: List[cudaExternalSemaphoreSignalParams], unsigned int numExtSems, stream)¶
Signals a set of external semaphore objects.
Enqueues a signal operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.
The exact semantics of signaling a semaphore depends on the type of the object.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeOpaqueFd, cudaExternalSemaphoreHandleTypeOpaqueWin32, cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt then signaling the semaphore will set it to the signaled state.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeD3D12Fence, cudaExternalSemaphoreHandleTypeD3D11Fence, cudaExternalSemaphoreHandleTypeTimelineSemaphoreFd, cudaExternalSemaphoreHandleTypeTimelineSemaphoreWin32 then the semaphore will be set to the value specified in cudaExternalSemaphoreSignalParams::params::fence::value.
If the semaphore object is of the type cudaExternalSemaphoreHandleTypeNvSciSync this API sets cudaExternalSemaphoreSignalParams::params::nvSciSync::fence to a value that can be used by subsequent waiters of the same NvSciSync object to order operations with those currently submitted in stream. Such an update will overwrite previous contents of cudaExternalSemaphoreSignalParams::params::nvSciSync::fence. By deefault, signaling such an external semaphore object causes appropriate memory synchronization operations to be performed over all the external memory objects that are imported as cudaExternalMemoryHandleTypeNvSciBuf. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag cudaExternalSemaphoreSignalSkipNvSciBufMemSync, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type cudaExternalSemaphoreHandleTypeNvSciSync, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in cudaDeviceGetNvSciSyncAttributes to cudaNvSciSyncAttrSignal, this API will return cudaErrorNotSupported.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeKeyedMutex, cudaExternalSemaphoreHandleTypeKeyedMutexKmt, then the keyed mutex will be released with the key specified in cudaExternalSemaphoreSignalParams::params::keyedmutex::key.
- Parameters
- extSemArrayList[cudaExternalSemaphore_t]
Set of external semaphores to be signaled
- paramsArrayList[cudaExternalSemaphoreSignalParams]
Array of semaphore parameters
- numExtSemsunsigned int
Number of semaphores to signal
- streamCUstream or cudaStream_t
Stream to enqueue the signal operations in
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle
- None
None
- cuda.cudart.cudaWaitExternalSemaphoresAsync(extSemArray: List[cudaExternalSemaphore_t], paramsArray: List[cudaExternalSemaphoreWaitParams], unsigned int numExtSems, stream)¶
Waits on a set of external semaphore objects.
Enqueues a wait operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.
The exact semantics of waiting on a semaphore depends on the type of the object.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeOpaqueFd, cudaExternalSemaphoreHandleTypeOpaqueWin32, cudaExternalSemaphoreHandleTypeOpaqueWin32Kmt then waiting on the semaphore will wait until the semaphore reaches the signaled state. The semaphore will then be reset to the unsignaled state. Therefore for every signal operation, there can only be one wait operation.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeD3D12Fence, cudaExternalSemaphoreHandleTypeD3D11Fence, cudaExternalSemaphoreHandleTypeTimelineSemaphoreFd, cudaExternalSemaphoreHandleTypeTimelineSemaphoreWin32 then waiting on the semaphore will wait until the value of the semaphore is greater than or equal to cudaExternalSemaphoreWaitParams::params::fence::value.
If the semaphore object is of the type cudaExternalSemaphoreHandleTypeNvSciSync then, waiting on the semaphore will wait until the cudaExternalSemaphoreSignalParams::params::nvSciSync::fence is signaled by the signaler of the NvSciSyncObj that was associated with this semaphore object. By default, waiting on such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported as cudaExternalMemoryHandleTypeNvSciBuf. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag cudaExternalSemaphoreWaitSkipNvSciBufMemSync, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type cudaExternalSemaphoreHandleTypeNvSciSync, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in cudaDeviceGetNvSciSyncAttributes to cudaNvSciSyncAttrWait, this API will return cudaErrorNotSupported.
If the semaphore object is any one of the following types: cudaExternalSemaphoreHandleTypeKeyedMutex, cudaExternalSemaphoreHandleTypeKeyedMutexKmt, then the keyed mutex will be acquired when it is released with the key specified in cudaExternalSemaphoreSignalParams::params::keyedmutex::key or until the timeout specified by cudaExternalSemaphoreSignalParams::params::keyedmutex::timeoutMs has lapsed. The timeout interval can either be a finite value specified in milliseconds or an infinite value. In case an infinite value is specified the timeout never elapses. The windows INFINITE macro must be used to specify infinite timeout
- Parameters
- extSemArrayList[cudaExternalSemaphore_t]
External semaphores to be waited on
- paramsArrayList[cudaExternalSemaphoreWaitParams]
Array of semaphore parameters
- numExtSemsunsigned int
Number of semaphores to wait on
- streamCUstream or cudaStream_t
Stream to enqueue the wait operations in
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorTimeout
- None
None
- cuda.cudart.cudaDestroyExternalSemaphore(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
- extSemAny
External semaphore to be destroyed
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle
- None
None
Execution Control¶
This section describes the execution control functions of the CUDA runtime application programming interface.
Some functions have overloaded C++ API template versions documented separately in the C++ API Routines module.
- cuda.cudart.cudaFuncSetCacheConfig(func, cacheConfig: cudaFuncCache)¶
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 cacheConfig the preferred cache configuration for the function specified via func. This is only a preference. The runtime will use the requested configuration if possible, but it is free to choose a different configuration if required to execute func.
func is a device function symbol and must be declared as a global function. If the specified function does not exist, then cudaErrorInvalidDeviceFunction is returned. For templated functions, pass the function symbol as follows: func_name<template_arg_0,…,template_arg_N>
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: - cudaFuncCachePreferNone: no preference for shared memory or L1 (default) - cudaFuncCachePreferShared: prefer larger shared memory and smaller L1 cache - cudaFuncCachePreferL1: prefer larger L1 cache and smaller shared memory - cudaFuncCachePreferEqual: prefer equal size L1 cache and shared memory
- Parameters
- funcAny
Device function symbol
- cacheConfigcudaFuncCache
Requested cache configuration
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDeviceFunction
- None
None
See also
cudaFuncGetAttributes
cudaLaunchKernel
cudaThreadGetCacheConfig
cudaThreadSetCacheConfig
cuFuncSetCacheConfig
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 cudaFuncSetSharedMemConfig will override the device wide setting set by cudaDeviceSetSharedMemConfig.
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.
For templated functions, pass the function symbol as follows: func_name<template_arg_0,…,template_arg_N>
The supported bank configurations are: - cudaSharedMemBankSizeDefault: use the device’s shared memory configuration when launching this function. - cudaSharedMemBankSizeFourByte: set shared memory bank width to be four bytes natively when launching this function. - cudaSharedMemBankSizeEightByte: set shared memory bank width to be eight bytes natively when launching this function.
- Parameters
- funcAny
Device function symbol
- configcudaSharedMemConfig
Requested shared memory configuration
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDeviceFunction cudaErrorInvalidValue
- None
None
See also
- cuda.cudart.cudaFuncGetAttributes(func)¶
Find out attributes for a given function.
This function obtains the attributes of a function specified via func. func is a device function symbol and must be declared as a global function. The fetched attributes are placed in attr. If the specified function does not exist, then cudaErrorInvalidDeviceFunction is returned. For templated functions, pass the function symbol as follows: func_name<template_arg_0,…,template_arg_N>
Note that some function attributes such as maxThreadsPerBlock may vary based on the device that is currently being used.
- Parameters
- funcAny
Device function symbol
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDeviceFunction
- attrcudaFuncAttributes
Return pointer to function’s attributes
See also
cudaFuncSetCacheConfig
cudaFuncGetAttributes
cudaLaunchKernel
cuFuncGetAttribute
- cuda.cudart.cudaFuncSetAttribute(func, attr: cudaFuncAttribute, int value)¶
Set attributes for a given function.
This function sets the attributes of a function specified via func. The parameter func must be a pointer to a function that executes on the device. The parameter specified by func must be declared as a global function. The enumeration defined by attr is set to the value defined by value. If the specified function does not exist, then cudaErrorInvalidDeviceFunction is returned. If the specified attribute cannot be written, or if the value is incorrect, then cudaErrorInvalidValue is returned.
Valid values for attr are: - cudaFuncAttributeMaxDynamicSharedMemorySize - The requested maximum size in bytes of dynamically-allocated shared memory. The sum of this value and the function attribute sharedSizeBytes cannot exceed the device attribute cudaDevAttrMaxSharedMemoryPerBlockOptin. The maximal size of requestable dynamic shared memory may differ by GPU architecture. - cudaFuncAttributePreferredSharedMemoryCarveout - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. See cudaDevAttrMaxSharedMemoryPerMultiprocessor. This is only a hint, and the driver can choose a different ratio if required to execute the function.
- Parameters
- funcAny
Function to get attributes of
- attrcudaFuncAttribute
Attribute to set
- valueint
Value to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDeviceFunction cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaSetDoubleForDevice(double d)¶
Converts a double argument to be executed on a device.
Converts the double value of d to an internal float representation if the device does not support double arithmetic. If the device does natively support doubles, then this function does nothing.
- Parameters
- ddouble
Double to convert
- Returns
- cudaError_t
cudaSuccess
- None
None
- cuda.cudart.cudaSetDoubleForHost(double d)¶
Converts a double argument after execution on a device.
DeprecatedThis function is deprecated as of CUDA 7.5
Converts the double value of d from a potentially internal float representation if the device does not support double arithmetic. If the device does natively support doubles, then this function does nothing.
- Parameters
- ddouble
Double to convert
- Returns
- cudaError_t
cudaSuccess
- None
None
- cuda.cudart.cudaLaunchHostFunc(stream, fn, 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 cudaErrorNotPermitted, 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 constrast to cuStreamAddCallback, the function will not be called in the event of an error in the CUDA context.
- Parameters
- hStreamCUstream or cudaStream_t
Stream to enqueue function call in
- fnAny
The function to call once preceding stream operations are complete
- userDataAny
User-specified data to be passed to the function
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorInvalidValue cudaErrorNotSupported
- None
None
Occupancy¶
This section describes the occupancy calculation functions of the CUDA runtime application programming interface.
Besides the occupancy calculator functions (cudaOccupancyMaxActiveBlocksPerMultiprocessor and cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags), there are also C++ only occupancy-based launch configuration functions documented in C++ API Routines module.
See cudaOccupancyMaxPotentialBlockSize (C++ API), cudaOccupancyMaxPotentialBlockSize (C++ API), cudaOccupancyMaxPotentialBlockSizeVariableSMem (C++ API), cudaOccupancyMaxPotentialBlockSizeVariableSMem (C++ API) cudaOccupancyAvailableDynamicSMemPerBlock (C++ API),
- cuda.cudart.cudaOccupancyMaxActiveBlocksPerMultiprocessor(func, int blockSize, size_t dynamicSMemSize)¶
Returns occupancy for a device function.
Returns in *numBlocks the maximum number of active blocks per streaming multiprocessor for the device function.
- Parameters
- funcAny
Kernel function for which occupancy is calculated
- blockSizeint
Block size the kernel is intended to be launched with
- dynamicSMemSizesize_t
Per-block dynamic shared memory usage intended, in bytes
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidDeviceFunction cudaErrorInvalidValue cudaErrorUnknown
- numBlocksint
Returned occupancy
See also
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
cudaOccupancyAvailableDynamicSMemPerBlock
cuOccupancyMaxActiveBlocksPerMultiprocessor
- cuda.cudart.cudaOccupancyAvailableDynamicSMemPerBlock(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
- funcAny
Kernel function for which occupancy is calculated
- numBlocksint
Number of blocks to fit on SM
- blockSizeint
Size of the block
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidDeviceFunction cudaErrorInvalidValue cudaErrorUnknown
- dynamicSmemSizeint
Returned maximum dynamic shared memory
See also
cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
cudaOccupancyAvailableDynamicSMemPerBlock
- cuda.cudart.cudaOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(func, int blockSize, size_t dynamicSMemSize, unsigned int flags)¶
Returns occupancy for a device function with the specified flags.
Returns in *numBlocks the maximum number of active blocks per streaming multiprocessor for the device function.
The flags parameter controls how special cases are handled. Valid flags include:
cudaOccupancyDefault: keeps the default behavior as
cudaOccupancyMaxActiveBlocksPerMultiprocessor - cudaOccupancyDisableCachingOverride: This flag 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 this flag 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
- funcAny
Kernel function for which occupancy is calculated
- blockSizeint
Block size the kernel is intended to be launched with
- dynamicSMemSizesize_t
Per-block dynamic shared memory usage intended, in bytes
- flagsunsigned int
Requested behavior for the occupancy calculator
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidDeviceFunction cudaErrorInvalidValue cudaErrorUnknown
- numBlocksint
Returned occupancy
See also
cudaOccupancyMaxActiveBlocksPerMultiprocessor
cudaOccupancyMaxPotentialBlockSize
cudaOccupancyMaxPotentialBlockSizeWithFlags
cudaOccupancyMaxPotentialBlockSizeVariableSMem
cudaOccupancyMaxPotentialBlockSizeVariableSMemWithFlags
cudaOccupancyAvailableDynamicSMemPerBlock
cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags
Memory Management¶
This section describes the memory management functions of the CUDA runtime application programming interface.
Some functions have overloaded C++ API template versions documented separately in the C++ API Routines module.
- cuda.cudart.cudaMallocManaged(size_t size, unsigned int flags)¶
Allocates memory that will be automatically managed by the Unified Memory system.
Allocates size bytes of managed memory on the device and returns in *devPtr a pointer to the allocated memory. If the device doesn’t support allocating managed memory, cudaErrorNotSupported is returned. Support for managed memory can be queried using the device attribute cudaDevAttrManagedMemory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If size is 0, cudaMallocManaged returns cudaErrorInvalidValue. 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 cudaMemAttachGlobal or cudaMemAttachHost. The default value for flags is cudaMemAttachGlobal. If cudaMemAttachGlobal is specified, then this memory is accessible from any stream on any device. If cudaMemAttachHost is specified, then the allocation should not be accessed from devices that have a zero value for the device attribute cudaDevAttrConcurrentManagedAccess; an explicit call to cudaStreamAttachMemAsync will be required to enable access on such devices.
If the association is later changed via cudaStreamAttachMemAsync to a single stream, the default association, as specifed during cudaMallocManaged, is restored when that stream is destroyed. For managed variables, the default association is always cudaMemAttachGlobal. 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 cudaMallocManaged should be released with cudaFree.
Device memory oversubscription is possible for GPUs that have a non- zero value for the device attribute cudaDevAttrConcurrentManagedAccess. 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 cudaDevAttrConcurrentManagedAccess, 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 cudaMemAdvise. The application can also explicitly migrate memory to a desired processor’s memory via cudaMemPrefetchAsync.
In a multi-GPU system where all of the GPUs have a zero value for the device attribute cudaDevAttrConcurrentManagedAccess 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 cudaMallocManaged 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 cudaDevAttrConcurrentManagedAccess 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 cudaDevAttrConcurrentManagedAccess. 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 devices used in that process that support managed memory have to be peer-to-peer compatible with each other. The error cudaErrorInvalidDevice will be returned if a device that supports managed memory is used and it is not peer-to-peer compatible with any of the other managed memory supporting devices that were previously used in that process, even if cudaDeviceReset has been called on those devices. These environment variables are described in the CUDA programming guide under the “CUDA environment variables” section.
- Parameters
- sizesize_t
Requested allocation size in bytes
- flagsunsigned int
Must be either cudaMemAttachGlobal or cudaMemAttachHost (defaults to cudaMemAttachGlobal)
- Returns
- cudaError_t
cudaSuccess cudaErrorMemoryAllocation cudaErrorNotSupported cudaErrorInvalidValue
- devPtrint
Pointer to allocated device memory
- cuda.cudart.cudaMalloc(size_t size)¶
Allocate memory on the device.
Allocates size bytes of linear memory on the device and returns in *devPtr a pointer to the allocated memory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. cudaMalloc() returns cudaErrorMemoryAllocation in case of failure.
The device version of cudaFree cannot be used with a *devPtr allocated using the host API, and vice versa.
- Parameters
- sizesize_t
Requested allocation size in bytes
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- devPtrint
Pointer to allocated device memory
- cuda.cudart.cudaMallocHost(size_t size)¶
Allocates page-locked memory on the host.
Allocates size 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 cudaMemcpy*(). 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 cudaMallocHost() 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.
- Parameters
- sizesize_t
Requested allocation size in bytes
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- ptrint
Pointer to allocated host memory
See also
- cuda.cudart.cudaMallocPitch(size_t width, size_t height)¶
Allocates pitched memory on the device.
Allocates at least width (in bytes) * height bytes of linear memory on the device and returns in *devPtr 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. The pitch returned in *pitch by cudaMallocPitch() 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;
For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations using cudaMallocPitch(). Due to pitch 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).
- Parameters
- widthsize_t
Requested pitched allocation width (in bytes)
- heightsize_t
Requested pitched allocation height
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- devPtrint
Pointer to allocated pitched device memory
- pitchint
Pitch for allocation
See also
- cuda.cudart.cudaMallocArray(cudaChannelFormatDesc desc: cudaChannelFormatDesc, size_t width, size_t height, unsigned int flags)¶
Allocate an array on the device.
Allocates a CUDA array according to the cudaChannelFormatDesc structure desc and returns a handle to the new CUDA array in *array.
The cudaChannelFormatDesc is defined as: structcudaChannelFormatDesc{ intx,y,z,w; enumcudaChannelFormatKindf; }; where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or cudaChannelFormatKindFloat.
The flags parameter enables different options to be specified that affect the allocation, as follows. - cudaArrayDefault: This flag’s value is defined to be 0 and provides default array allocation - cudaArraySurfaceLoadStore: Allocates an array that can be read from or written to using a surface reference - cudaArrayTextureGather: This flag indicates that texture gather operations will be performed on the array. - cudaArraySparse: Allocates a CUDA array without physical backing memory. The subregions within this sparse array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. The physical backing memory must be allocated via cuMemCreate. - cudaArrayDeferredMapping: Allocates a CUDA array without physical backing memory. The entire array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. The physical backing memory must be allocated via cuMemCreate.
width and height must meet certain size requirements. See cudaMalloc3DArray() for more details.
- Parameters
- desccudaChannelFormatDesc
Requested channel format
- widthsize_t
Requested array allocation width
- heightsize_t
Requested array allocation height
- flagsunsigned int
Requested properties of allocated array
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- arraycudaArray_t
Pointer to allocated array in device memory
See also
- cuda.cudart.cudaFree(devPtr)¶
Frees memory on the device.
Frees the memory space pointed to by devPtr, which must have been returned by a previous call to cudaMalloc() or cudaMallocPitch(). Otherwise, or if cudaFree(devPtr) has already been called before, an error is returned. If devPtr is 0, no operation is performed. cudaFree() returns cudaErrorValue in case of failure.
The device version of cudaFree cannot be used with a *devPtr allocated using the host API, and vice versa.
- Parameters
- devPtrAny
Device pointer to memory to free
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaFreeHost(ptr)¶
Frees page-locked memory.
Frees the memory space pointed to by hostPtr, which must have been returned by a previous call to cudaMallocHost() or cudaHostAlloc().
- Parameters
- ptrAny
Pointer to memory to free
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
- cuda.cudart.cudaFreeArray(array)¶
Frees an array on the device.
Frees the CUDA array array, which must have been returned by a previous call to cudaMallocArray(). If devPtr is 0, no operation is performed.
- Parameters
- arrayAny
Pointer to array to free
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
- cuda.cudart.cudaFreeMipmappedArray(mipmappedArray)¶
Frees a mipmapped array on the device.
Frees the CUDA mipmapped array mipmappedArray, which must have been returned by a previous call to cudaMallocMipmappedArray(). If devPtr is 0, no operation is performed.
- Parameters
- mipmappedArrayAny
Pointer to mipmapped array to free
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMalloc
cudaMallocPitch
cudaFree
cudaMallocArray
cudaMallocHost
cudaFreeHost
cudaHostAlloc
cuMipmappedArrayDestroy
- cuda.cudart.cudaHostAlloc(size_t size, unsigned int flags)¶
Allocates page-locked memory on the host.
Allocates size 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 cudaMemcpy(). 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. - cudaHostAllocDefault: This flag’s value is defined to be 0 and causes cudaHostAlloc() to emulate cudaMallocHost(). - cudaHostAllocPortable: The memory returned by this call will be considered as pinned memory by all CUDA contexts, not just the one that performed the allocation. - cudaHostAllocMapped: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling cudaHostGetDevicePointer(). - cudaHostAllocWriteCombined: 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 device 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.
In order for the cudaHostAllocMapped flag to have any effect, the CUDA context must support the cudaDeviceMapHost flag, which can be checked via cudaGetDeviceFlags(). The cudaDeviceMapHost flag is implicitly set for contexts created via the runtime API.
The cudaHostAllocMapped flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to cudaHostGetDevicePointer() because the memory may be mapped into other CUDA contexts via the cudaHostAllocPortable flag.
Memory allocated by this function must be freed with cudaFreeHost().
- Parameters
- sizesize_t
Requested allocation size in bytes
- flagsunsigned int
Requested properties of allocated memory
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- pHostint
Device pointer to allocated memory
See also
cudaSetDeviceFlags
cudaMallocHost
cudaFreeHost
cudaGetDeviceFlags
cuMemHostAlloc
- cuda.cudart.cudaHostRegister(ptr, size_t size, unsigned int flags)¶
Registers an existing host memory range for use by CUDA.
Page-locks the memory range specified by ptr and size and maps it for the device(s) as specified by flags. This memory range also is added to the same tracking mechanism as cudaHostAlloc() to automatically accelerate calls to functions such as cudaMemcpy(). 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.
cudaHostRegister is supported only on I/O coherent devices that have a non-zero value for the device attribute cudaDevAttrHostRegisterSupported.
The flags parameter enables different options to be specified that affect the allocation, as follows.
cudaHostRegisterDefault: On a system with unified virtual addressing,
the memory will be both mapped and portable. On a system with no unified virtual addressing, the memory will be neither mapped nor portable. - cudaHostRegisterPortable: The memory returned by this call will be considered as pinned memory by all CUDA contexts, not just the one that performed the allocation. - cudaHostRegisterMapped: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling cudaHostGetDevicePointer(). - cudaHostRegisterIoMemory: The passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third- party PCIe device, and it will marked as non cache-coherent and contiguous. - cudaHostRegisterReadOnly: The passed memory pointer is treated as pointing to memory that is considered read-only by the device. On platforms without cudaDevAttrPageableMemoryAccessUsesHostPageTables, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attribute cudaDeviceAttrReadOnlyHostRegisterSupported. Using this flag with a current context associated with a device that does not have this attribute set will cause cudaHostRegister to error with cudaErrorNotSupported.
All of these flags are orthogonal to one another: a developer may page- lock memory that is portable or mapped with no restrictions.
The CUDA context must have been created with the cudaMapHost flag in order for the cudaHostRegisterMapped flag to have any effect.
The cudaHostRegisterMapped flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to cudaHostGetDevicePointer() because the memory may be mapped into other CUDA contexts via the cudaHostRegisterPortable flag.
For devices that have a non-zero value for the device attribute cudaDevAttrCanUseHostPointerForRegisteredMem, the memory can also be accessed from the device using the host pointer ptr. The device pointer returned by cudaHostGetDevicePointer() 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 cudaHostGetDevicePointer() 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 cudaHostGetDevicePointer() 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 cudaHostUnregister().
- Parameters
- ptrAny
Host pointer to memory to page-lock
- sizesize_t
Size in bytes of the address range to page-lock in bytes
- flagsunsigned int
Flags for allocation request
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation cudaErrorHostMemoryAlreadyRegistered cudaErrorNotSupported
- None
None
See also
cudaHostUnregister
cudaHostGetFlags
cudaHostGetDevicePointer
cuMemHostRegister
- cuda.cudart.cudaHostUnregister(ptr)¶
Unregisters a memory range that was registered with cudaHostRegister.
Unmaps the memory range whose base address is specified by ptr, and makes it pageable again.
The base address must be the same one specified to cudaHostRegister().
- Parameters
- ptrAny
Host pointer to memory to unregister
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorHostMemoryNotRegistered
- None
None
See also
cudaHostUnregister
cuMemHostUnregister
- cuda.cudart.cudaHostGetDevicePointer(pHost, unsigned int flags)¶
Passes back device pointer of mapped host memory allocated by cudaHostAlloc or registered by cudaHostRegister.
Passes back the device pointer corresponding to the mapped, pinned host buffer allocated by cudaHostAlloc() or registered by cudaHostRegister().
cudaHostGetDevicePointer() will fail if the cudaDeviceMapHost flag was not specified before deferred context creation occurred, or if called on a device that does not support mapped, pinned memory.
For devices that have a non-zero value for the device attribute cudaDevAttrCanUseHostPointerForRegisteredMem, the memory can also be accessed from the device using the host pointer pHost. The device pointer returned by cudaHostGetDevicePointer() may or may not match the original host pointer pHost 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 cudaHostGetDevicePointer() will match the original pointer pHost. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cudaHostGetDevicePointer() will not match the original host pointer pHost, 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
- pHostAny
Requested host pointer mapping
- flagsunsigned int
Flags for extensions (must be 0 for now)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- pDeviceint
Returned device pointer for mapped memory
See also
cudaSetDeviceFlags
cudaHostAlloc
cuMemHostGetDevicePointer
- cuda.cudart.cudaHostGetFlags(pHost)¶
Passes back flags used to allocate pinned host memory allocated by cudaHostAlloc.
cudaHostGetFlags() will fail if the input pointer does not reside in an address range allocated by cudaHostAlloc().
- Parameters
- pHostAny
Host pointer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pFlagsunsigned int
Returned flags word
See also
cudaHostAlloc
cuMemHostGetFlags
- cuda.cudart.cudaMalloc3D(cudaExtent extent: cudaExtent)¶
Allocates logical 1D, 2D, or 3D memory objects on the device.
Allocates at least width * height * depth bytes of linear memory on the device and returns a cudaPitchedPtr in which ptr is a pointer to the allocated memory. The function may pad the allocation to ensure hardware alignment requirements are met. The pitch returned in the pitch field of pitchedDevPtr is the width in bytes of the allocation.
The returned cudaPitchedPtr contains additional fields xsize and ysize, the logical width and height of the allocation, which are equivalent to the width and height extent parameters provided by the programmer during allocation.
For allocations of 2D and 3D objects, it is highly recommended that programmers perform allocations using cudaMalloc3D() or cudaMallocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing memory copies involving 2D or 3D objects (whether linear memory or CUDA arrays).
- Parameters
- extentcudaExtent
Requested allocation size (width field in bytes)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- pitchedDevPtrcudaPitchedPtr
Pointer to allocated pitched device memory
See also
cudaMallocPitch
cudaFree
cudaMemcpy3D
cudaMemset3D
cudaMalloc3DArray
cudaMallocArray
cudaFreeArray
cudaMallocHost
cudaFreeHost
cudaHostAlloc
make_cudaPitchedPtr
make_cudaExtent
cuMemAllocPitch
- cuda.cudart.cudaMalloc3DArray(cudaChannelFormatDesc desc: cudaChannelFormatDesc, cudaExtent extent: cudaExtent, unsigned int flags)¶
Allocate an array on the device.
Allocates a CUDA array according to the cudaChannelFormatDesc structure desc and returns a handle to the new CUDA array in *array.
The cudaChannelFormatDesc is defined as: structcudaChannelFormatDesc{ intx,y,z,w; enumcudaChannelFormatKindf; }; where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or cudaChannelFormatKindFloat.
cudaMalloc3DArray() can allocate the following:
A 1D array is allocated if the height and depth extents are both
zero. - A 2D array is allocated if only the 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 the height extent is zero and the cudaArrayLayered 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 cudaArrayLayered 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 cudaArrayCubemap 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 cudaGraphicsCubeFace. - A cubemap layered CUDA array is allocated if all three extents are non- zero, and both, cudaArrayCubemap and cudaArrayLayered 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.
The flags parameter enables different options to be specified that affect the allocation, as follows. - cudaArrayDefault: This flag’s value is defined to be 0 and provides default array allocation - cudaArrayLayered: Allocates a layered CUDA array, with the depth extent indicating the number of layers - cudaArrayCubemap: Allocates a cubemap CUDA array. Width must be equal to height, and depth must be six. If the cudaArrayLayered flag is also set, depth must be a multiple of six. - cudaArraySurfaceLoadStore: Allocates a CUDA array that could be read from or written to using a surface reference. - cudaArrayTextureGather: This flag indicates that texture gather operations will be performed on the CUDA array. Texture gather can only be performed on 2D CUDA arrays. - cudaArraySparse: Allocates a CUDA array without physical backing memory. The subregions within this sparse array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. This flag can only be used for creating 2D, 3D or 2D layered sparse CUDA arrays. The physical backing memory must be allocated via cuMemCreate. - cudaArrayDeferredMapping: Allocates a CUDA array without physical backing memory. The entire array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. The physical backing memory must be allocated via cuMemCreate.
The width, height and depth extents must meet certain size requirements as listed in the following table. All values are specified in elements.
Note that 2D CUDA arrays have different size requirements if the cudaArrayTextureGather flag is set. In that case, the valid range for (width, height, depth) is ((1,maxTexture2DGather[0]), (1,maxTexture2DGather[1]), 0).
CUDA array type Valid extents that must always be met {(width
range in elements), (height range), (depth range)} Valid extents with cudaArraySurfaceLoadStore set {(width range in elements), (height range), (depth range)} 1D { (1,maxTexture1D), 0, 0 } { (1,maxSurface1D), 0, 0 } 2D { (1,maxTexture2D[0]), (1,maxTexture2D[1]), 0 } { (1,maxSurface2D[0]), (1,maxSurface2D[1]), 0 } 3D { (1,maxTexture3D[0]), (1,maxTexture3D[1]), (1,maxTexture3D[2]) } OR { (1,maxTexture3DAlt[0]), (1,maxTexture3DAlt[1]), (1,maxTexture3DAlt[2]) } { (1,maxSurface3D[0]), (1,maxSurface3D[1]), (1,maxSurface3D[2]) } 1D Layered { (1,maxTexture1DLayered[0]), 0, (1,maxTexture1DLayered[1]) } { (1,maxSurface1DLayered[0]), 0, (1,maxSurface1DLayered[1]) } 2D Layered { (1,maxTexture2DLayered[0]), (1,maxTexture2DLayered[1]), (1,maxTexture2DLayered[2]) } { (1,maxSurface2DLayered[0]), (1,maxSurface2DLayered[1]), (1,maxSurface2DLayered[2]) } Cubemap { (1,maxTextureCubemap), (1,maxTextureCubemap), 6 } { (1,maxSurfaceCubemap), (1,maxSurfaceCubemap), 6 } Cubemap Layered { (1,maxTextureCubemapLayered[0]), (1,maxTextureCubemapLayered[0]), (1,maxTextureCubemapLayered[1]) } { (1,maxSurfaceCubemapLayered[0]), (1,maxSurfaceCubemapLayered[0]), (1,maxSurfaceCubemapLayered[1]) }
- Parameters
- desccudaChannelFormatDesc
Requested channel format
- extentcudaExtent
Requested allocation size (width field in elements)
- flagsunsigned int
Flags for extensions
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- arraycudaArray_t
Pointer to allocated array in device memory
See also
cudaMalloc3D
cudaMalloc
cudaMallocPitch
cudaFree
cudaFreeArray
cudaMallocHost
cudaFreeHost
cudaHostAlloc
make_cudaExtent
cuArray3DCreate
- cuda.cudart.cudaMallocMipmappedArray(cudaChannelFormatDesc desc: cudaChannelFormatDesc, cudaExtent extent: cudaExtent, unsigned int numLevels, unsigned int flags)¶
Allocate a mipmapped array on the device.
Allocates a CUDA mipmapped array according to the cudaChannelFormatDesc structure desc and returns a handle to the new CUDA mipmapped array in *mipmappedArray. numLevels specifies the number of mipmap levels to be allocated. This value is clamped to the range [1, 1 + floor(log2(max(width, height, depth)))].
The cudaChannelFormatDesc is defined as: structcudaChannelFormatDesc{ intx,y,z,w; enumcudaChannelFormatKindf; }; where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or cudaChannelFormatKindFloat.
cudaMallocMipmappedArray() can allocate the following:
A 1D mipmapped array is allocated if the height and depth extents are
both zero. - A 2D mipmapped array is allocated if only the 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 the height extent is zero and the cudaArrayLayered flag is set. Each layer is a 1D mipmapped 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 cudaArrayLayered flag is set. Each layer is a 2D mipmapped 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 cudaArrayCubemap flag is set. Width must be equal to height, and depth must be six. The order of the six layers in memory is the same as that listed in cudaGraphicsCubeFace. - A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, and both, cudaArrayCubemap and cudaArrayLayered flags are set. Width must be equal to height, and depth must be a multiple of six. A cubemap layered CUDA mipmapped array is a special type of 2D layered CUDA mipmapped array that consists of a collection of cubemap mipmapped arrays. The first six layers represent the first cubemap mipmapped array, the next six layers form the second cubemap mipmapped array, and so on.
The flags parameter enables different options to be specified that affect the allocation, as follows. - cudaArrayDefault: This flag’s value is defined to be 0 and provides default mipmapped array allocation - cudaArrayLayered: Allocates a layered CUDA mipmapped array, with the depth extent indicating the number of layers - cudaArrayCubemap: Allocates a cubemap CUDA mipmapped array. Width must be equal to height, and depth must be six. If the cudaArrayLayered flag is also set, depth must be a multiple of six. - cudaArraySurfaceLoadStore: This flag indicates that individual mipmap levels of the CUDA mipmapped array will be read from or written to using a surface reference. - cudaArrayTextureGather: This flag indicates that texture gather operations will be performed on the CUDA array. Texture gather can only be performed on 2D CUDA mipmapped arrays, and the gather operations are performed only on the most detailed mipmap level. - cudaArraySparse: Allocates a CUDA mipmapped array without physical backing memory. The subregions within this sparse array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. This flag can only be used for creating 2D, 3D or 2D layered sparse CUDA mipmapped arrays. The physical backing memory must be allocated via cuMemCreate. - cudaArrayDeferredMapping: Allocates a CUDA mipmapped array without physical backing memory. The entire array can later be mapped onto a physical memory allocation by calling cuMemMapArrayAsync. The physical backing memory must be allocated via cuMemCreate.
The width, height and depth extents must meet certain size requirements as listed in the following table. All values are specified in elements.
CUDA array type Valid extents that must always be met {(width
range in elements), (height range), (depth range)} Valid extents with cudaArraySurfaceLoadStore set {(width range in elements), (height range), (depth range)} 1D { (1,maxTexture1DMipmap), 0, 0 } { (1,maxSurface1D), 0, 0 } 2D { (1,maxTexture2DMipmap[0]), (1,maxTexture2DMipmap[1]), 0 } { (1,maxSurface2D[0]), (1,maxSurface2D[1]), 0 } 3D { (1,maxTexture3D[0]), (1,maxTexture3D[1]), (1,maxTexture3D[2]) } OR { (1,maxTexture3DAlt[0]), (1,maxTexture3DAlt[1]), (1,maxTexture3DAlt[2]) } { (1,maxSurface3D[0]), (1,maxSurface3D[1]), (1,maxSurface3D[2]) } 1D Layered { (1,maxTexture1DLayered[0]), 0, (1,maxTexture1DLayered[1]) } { (1,maxSurface1DLayered[0]), 0, (1,maxSurface1DLayered[1]) } 2D Layered { (1,maxTexture2DLayered[0]), (1,maxTexture2DLayered[1]), (1,maxTexture2DLayered[2]) } { (1,maxSurface2DLayered[0]), (1,maxSurface2DLayered[1]), (1,maxSurface2DLayered[2]) } Cubemap { (1,maxTextureCubemap), (1,maxTextureCubemap), 6 } { (1,maxSurfaceCubemap), (1,maxSurfaceCubemap), 6 } Cubemap Layered { (1,maxTextureCubemapLayered[0]), (1,maxTextureCubemapLayered[0]), (1,maxTextureCubemapLayered[1]) } { (1,maxSurfaceCubemapLayered[0]), (1,maxSurfaceCubemapLayered[0]), (1,maxSurfaceCubemapLayered[1]) }
- Parameters
- desccudaChannelFormatDesc
Requested channel format
- extentcudaExtent
Requested allocation size (width field in elements)
- numLevelsunsigned int
Number of mipmap levels to allocate
- flagsunsigned int
Flags for extensions
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- mipmappedArraycudaMipmappedArray_t
Pointer to allocated mipmapped array in device memory
See also
cudaMalloc3D
cudaMalloc
cudaMallocPitch
cudaFree
cudaFreeArray
cudaMallocHost
cudaFreeHost
cudaHostAlloc
make_cudaExtent
cuMipmappedArrayCreate
- cuda.cudart.cudaGetMipmappedArrayLevel(mipmappedArray, unsigned int level)¶
Gets a mipmap level of a CUDA mipmapped array.
Returns in *levelArray a CUDA array that represents a single mipmap level of the CUDA mipmapped array mipmappedArray.
If level is greater than the maximum number of levels in this mipmapped array, cudaErrorInvalidValue is returned.
If mipmappedArray is NULL, cudaErrorInvalidResourceHandle is returned.
- Parameters
- mipmappedArrayAny
CUDA mipmapped array
- levelunsigned int
Mipmap level
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- levelArraycudaArray_t
Returned mipmap level CUDA array
See also
cudaMalloc3D
cudaMalloc
cudaMallocPitch
cudaFree
cudaFreeArray
cudaMallocHost
cudaFreeHost
cudaHostAlloc
make_cudaExtent
cuMipmappedArrayGetLevel
- cuda.cudart.cudaMemcpy3D(cudaMemcpy3DParms p: cudaMemcpy3DParms)¶
Copies data between 3D objects.
structcudaExtent{ size_twidth; size_theight; size_tdepth; }; structcudaExtentmake_cudaExtent(size_tw,size_th,size_td); structcudaPos{ size_tx; size_ty; size_tz; }; structcudaPosmake_cudaPos(size_tx,size_ty,size_tz); structcudaMemcpy3DParms{ cudaArray_tsrcArray; structcudaPossrcPos; structcudaPitchedPtrsrcPtr; cudaArray_tdstArray; structcudaPosdstPos; structcudaPitchedPtrdstPtr; structcudaExtentextent; enumcudaMemcpyKindkind; };
cudaMemcpy3D() copies data betwen two 3D objects. The source and destination objects may be in either host memory, device memory, or a CUDA array. The source, destination, extent, and kind of copy performed is specified by the cudaMemcpy3DParms struct which should be initialized to zero before use: cudaMemcpy3DParmsmyParms={0};
The struct passed to cudaMemcpy3D() must specify one of srcArray or srcPtr and one of dstArray or dstPtr. Passing more than one non- zero source or destination will cause cudaMemcpy3D() to return an error.
The srcPos and dstPos fields are optional offsets into the source and destination objects and are defined in units of each object’s elements. The element for a host or device pointer is assumed to be unsigned char.
The extent field defines the dimensions of the transferred area in elements. If a CUDA array is participating in the copy, the extent is defined in terms of that array’s elements. If no CUDA array is participating in the copy then the extents are defined in elements of unsigned char.
The kind field defines the direction of the copy. It must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. For cudaMemcpyHostToHost or cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost passed as kind and cudaArray type passed as source or destination, if the kind implies cudaArray type to be present on the host, cudaMemcpy3D() will disregard that implication and silently correct the kind based on the fact that cudaArray type can only be present on the device.
If the source and destination are both arrays, cudaMemcpy3D() will return an error if they do not have the same element size.
The source and destination object may not overlap. If overlapping source and destination objects are specified, undefined behavior will result.
The source object must entirely contain the region defined by srcPos and extent. The destination object must entirely contain the region defined by dstPos and extent.
cudaMemcpy3D() returns an error if the pitch of srcPtr or dstPtr exceeds the maximum allowed. The pitch of a cudaPitchedPtr allocated with cudaMalloc3D() will always be valid.
- Parameters
- pcudaMemcpy3DParms
3D memory copy parameters
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMalloc3D
cudaMalloc3DArray
cudaMemset3D
cudaMemcpy3DAsync
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
make_cudaExtent
make_cudaPos
cuMemcpy3D
- cuda.cudart.cudaMemcpy3DPeer(cudaMemcpy3DPeerParms p: cudaMemcpy3DPeerParms)¶
Copies memory between devices.
Perform a 3D memory copy according to the parameters specified in p. See the definition of the cudaMemcpy3DPeerParms structure for documentation of its parameters.
Note that this function is synchronous with respect to the host only if the source or destination of the transfer is host memory. Note also that this copy is serialized with respect to all pending and future asynchronous work in to the current device, the copy’s source device, and the copy’s destination device (use cudaMemcpy3DPeerAsync to avoid this synchronization).
- Parameters
- pcudaMemcpy3DPeerParms
Parameters for the memory copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
- cuda.cudart.cudaMemcpy3DAsync(cudaMemcpy3DParms p: cudaMemcpy3DParms, stream)¶
Copies data between 3D objects.
structcudaExtent{ size_twidth; size_theight; size_tdepth; }; structcudaExtentmake_cudaExtent(size_tw,size_th,size_td); structcudaPos{ size_tx; size_ty; size_tz; }; structcudaPosmake_cudaPos(size_tx,size_ty,size_tz); structcudaMemcpy3DParms{ cudaArray_tsrcArray; structcudaPossrcPos; structcudaPitchedPtrsrcPtr; cudaArray_tdstArray; structcudaPosdstPos; structcudaPitchedPtrdstPtr; structcudaExtentextent; enumcudaMemcpyKindkind; };
cudaMemcpy3DAsync() copies data betwen two 3D objects. The source and destination objects may be in either host memory, device memory, or a CUDA array. The source, destination, extent, and kind of copy performed is specified by the cudaMemcpy3DParms struct which should be initialized to zero before use: cudaMemcpy3DParmsmyParms={0};
The struct passed to cudaMemcpy3DAsync() must specify one of srcArray or srcPtr and one of dstArray or dstPtr. Passing more than one non-zero source or destination will cause cudaMemcpy3DAsync() to return an error.
The srcPos and dstPos fields are optional offsets into the source and destination objects and are defined in units of each object’s elements. The element for a host or device pointer is assumed to be unsigned char. For CUDA arrays, positions must be in the range [0, 2048) for any dimension.
The extent field defines the dimensions of the transferred area in elements. If a CUDA array is participating in the copy, the extent is defined in terms of that array’s elements. If no CUDA array is participating in the copy then the extents are defined in elements of unsigned char.
The kind field defines the direction of the copy. It must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. For cudaMemcpyHostToHost or cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost passed as kind and cudaArray type passed as source or destination, if the kind implies cudaArray type to be present on the host, cudaMemcpy3DAsync() will disregard that implication and silently correct the kind based on the fact that cudaArray type can only be present on the device.
If the source and destination are both arrays, cudaMemcpy3DAsync() will return an error if they do not have the same element size.
The source and destination object may not overlap. If overlapping source and destination objects are specified, undefined behavior will result.
The source object must lie entirely within the region defined by srcPos and extent. The destination object must lie entirely within the region defined by dstPos and extent.
cudaMemcpy3DAsync() returns an error if the pitch of srcPtr or dstPtr exceeds the maximum allowed. The pitch of a cudaPitchedPtr allocated with cudaMalloc3D() will always be valid.
cudaMemcpy3DAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- pcudaMemcpy3DParms
3D memory copy parameters
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMalloc3D
cudaMalloc3DArray
cudaMemset3D
cudaMemcpy3D
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
make_cudaExtent
make_cudaPos
cuMemcpy3DAsync
- cuda.cudart.cudaMemcpy3DPeerAsync(cudaMemcpy3DPeerParms p: cudaMemcpy3DPeerParms, stream)¶
Copies memory between devices asynchronously.
Perform a 3D memory copy according to the parameters specified in p. See the definition of the cudaMemcpy3DPeerParms structure for documentation of its parameters.
- Parameters
- pcudaMemcpy3DPeerParms
Parameters for the memory copy
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
cudaMemcpy
cudaMemcpyPeer
cudaMemcpyAsync
cudaMemcpyPeerAsync
cudaMemcpy3DPeerAsync
cuMemcpy3DPeerAsync
- cuda.cudart.cudaMemGetInfo()¶
Gets free and total device 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. In a multi- tenet situation, free estimate returned is prone to race condition where a new allocation/free done by a different process or a different thread in the same process between the time when free memory was estimated and reported, will result in deviation in free value reported and actual free memory.
The integrated GPU on Tegra shares memory with CPU and other component of the SoC. The free and total values returned by the API excludes the SWAP memory space maintained by the OS on some platforms. The OS may move some of the memory pages into swap area as the GPU or CPU allocate or access memory. See Tegra app note on how to calculate total and free memory on Tegra.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorLaunchFailure
- freeint
Returned free memory in bytes
- totalint
Returned total memory in bytes
- cuda.cudart.cudaArrayGetInfo(array)¶
Gets info about the specified cudaArray.
Returns in *desc, *extent and *flags respectively, the type, shape and flags of array.
Any of *desc, *extent and *flags may be specified as NULL.
- Parameters
- arrayAny
The cudaArray to get info for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- desccudaChannelFormatDesc
Returned array type
- extentcudaExtent
Returned array shape. 2D arrays will have depth of zero
- flagsunsigned int
Returned array flags
- cuda.cudart.cudaArrayGetPlane(hArray, unsigned 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: cudaChannelFormatKindNV12, then cudaErrorInvalidValue is returned.
Note that if the hArray has format cudaChannelFormatKindNV12, then passing in 0 for planeIdx returns a CUDA array of the same size as hArray but with one 8-bit channel and cudaChannelFormatKindUnsigned as its format kind. If 1 is passed for planeIdx, then the returned CUDA array has half the height and width of hArray with two 8-bit channels and cudaChannelFormatKindUnsigned as its format kind.
- Parameters
- hArrayAny
CUDA array
- planeIdxunsigned int
Plane index
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- pPlaneArraycudaArray_t
Returned CUDA array referenced by the planeIdx
- cuda.cudart.cudaArrayGetMemoryRequirements(array, int device)¶
Returns the memory requirements of a CUDA array.
Returns the memory requirements of a CUDA array in memoryRequirements If the CUDA array is not allocated with flag cudaArrayDeferredMapping cudaErrorInvalidValue will be returned.
The returned value in cudaArrayMemoryRequirements::size represents the total size of the CUDA array. The returned value in cudaArrayMemoryRequirements::alignment represents the alignment necessary for mapping the CUDA array.
- Parameters
- arrayAny
CUDA array to get the memory requirements of
- deviceint
Device to get the memory requirements for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- memoryRequirementscudaArrayMemoryRequirements
Pointer to cudaArrayMemoryRequirements
- cuda.cudart.cudaMipmappedArrayGetMemoryRequirements(mipmap, int device)¶
Returns the memory requirements of a CUDA mipmapped array.
Returns the memory requirements of a CUDA mipmapped array in memoryRequirements If the CUDA mipmapped array is not allocated with flag cudaArrayDeferredMapping cudaErrorInvalidValue will be returned.
The returned value in cudaArrayMemoryRequirements::size represents the total size of the CUDA mipmapped array. The returned value in cudaArrayMemoryRequirements::alignment represents the alignment necessary for mapping the CUDA mipmapped array.
- Parameters
- mipmapAny
CUDA mipmapped array to get the memory requirements of
- deviceint
Device to get the memory requirements for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- memoryRequirementscudaArrayMemoryRequirements
Pointer to cudaArrayMemoryRequirements
See also
- cuda.cudart.cudaArrayGetSparseProperties(array)¶
Returns the layout properties of a sparse CUDA array.
Returns the layout properties of a sparse CUDA array in sparseProperties. If the CUDA array is not allocated with flag cudaArraySparse cudaErrorInvalidValue will be returned.
If the returned value in cudaArraySparseProperties::flags contains cudaArraySparsePropertiesSingleMipTail, then cudaArraySparseProperties::miptailSize represents the total size of the array. Otherwise, it will be zero. Also, the returned value in cudaArraySparseProperties::miptailFirstLevel is always zero. Note that the array must have been allocated using cudaMallocArray or cudaMalloc3DArray. For CUDA arrays obtained using cudaMipmappedArrayGetLevel, cudaErrorInvalidValue will be returned. Instead, cudaMipmappedArrayGetSparseProperties must be used to obtain the sparse properties of the entire CUDA mipmapped array to which array belongs to.
- Parameters
- arrayAny
The CUDA array to get the sparse properties of
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- sparsePropertiescudaArraySparseProperties
Pointer to return the cudaArraySparseProperties
See also
cudaMipmappedArrayGetSparseProperties
cuMemMapArrayAsync
- cuda.cudart.cudaMipmappedArrayGetSparseProperties(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 cudaArraySparse cudaErrorInvalidValue will be returned.
For non-layered CUDA mipmapped arrays, cudaArraySparseProperties::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 cudaArraySparseProperties::flags contains cudaArraySparsePropertiesSingleMipTail, then cudaArraySparseProperties::miptailSize specifies the size of the mip tail of all layers combined. Otherwise, cudaArraySparseProperties::miptailSize specifies mip tail size per layer. The returned value of cudaArraySparseProperties::miptailFirstLevel is valid only if cudaArraySparseProperties::miptailSize is non-zero.
- Parameters
- mipmapAny
The CUDA mipmapped array to get the sparse properties of
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- sparsePropertiescudaArraySparseProperties
Pointer to return cudaArraySparseProperties
See also
cudaArrayGetSparseProperties
cuMemMapArrayAsync
- cuda.cudart.cudaMemcpy(dst, src, size_t count, kind: cudaMemcpyKind)¶
Copies data between host and device.
Copies count bytes from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. Calling cudaMemcpy() with dst and src pointers that do not match the direction of the copy results in an undefined behavior.
- Parameters
- dstAny
Destination memory address
- srcAny
Source memory address
- countsize_t
Size in bytes to copy
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpyDtoH
cuMemcpyHtoD
cuMemcpyDtoD
cuMemcpy
- cuda.cudart.cudaMemcpyPeer(dst, int dstDevice, src, int srcDevice, size_t count)¶
Copies memory between two devices.
Copies memory from one device to memory on another device. dst is the base device pointer of the destination memory and dstDevice is the destination device. src is the base device pointer of the source memory and srcDevice is the source device. count specifies the number of bytes to copy.
Note that this function is asynchronous with respect to the host, but serialized with respect all pending and future asynchronous work in to the current device, srcDevice, and dstDevice (use cudaMemcpyPeerAsync to avoid this synchronization).
- Parameters
- dstAny
Destination device pointer
- dstDeviceint
Destination device
- srcAny
Source device pointer
- srcDeviceint
Source device
- countsize_t
Size of memory copy in bytes
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
- cuda.cudart.cudaMemcpy2D(dst, size_t dpitch, src, size_t spitch, size_t width, size_t height, kind: cudaMemcpyKind)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. dpitch and spitch are the widths in memory in bytes of the 2D arrays pointed to by dst and src, including any padding added to the end of each row. The memory areas may not overlap. width must not exceed either dpitch or spitch. Calling cudaMemcpy2D() with dst and src pointers that do not match the direction of the copy results in an undefined behavior. cudaMemcpy2D() returns an error if dpitch or spitch exceeds the maximum allowed.
- Parameters
- dstAny
Destination memory address
- dpitchsize_t
Pitch of destination memory
- srcAny
Source memory address
- spitchsize_t
Pitch of source memory
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpy2D
cuMemcpy2DUnaligned
- cuda.cudart.cudaMemcpy2DToArray(dst, size_t wOffset, size_t hOffset, src, size_t spitch, size_t width, size_t height, kind: cudaMemcpyKind)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the memory area pointed to by src to the CUDA array dst starting at hOffset rows and wOffset bytes from the upper left corner, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. spitch is the width in memory in bytes of the 2D array pointed to by src, including any padding added to the end of each row. wOffset + width must not exceed the width of the CUDA array dst. width must not exceed spitch. cudaMemcpy2DToArray() returns an error if spitch exceeds the maximum allowed.
- Parameters
- dstAny
Destination memory address
- wOffsetsize_t
Destination starting X offset (columns in bytes)
- hOffsetsize_t
Destination starting Y offset (rows)
- srcAny
Source memory address
- spitchsize_t
Pitch of source memory
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpy2D
cuMemcpy2DUnaligned
- cuda.cudart.cudaMemcpy2DFromArray(dst, size_t dpitch, src, size_t wOffset, size_t hOffset, size_t width, size_t height, kind: cudaMemcpyKind)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the CUDA array src starting at hOffset rows and wOffset bytes from the upper left corner to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. dpitch is the width in memory in bytes of the 2D array pointed to by dst, including any padding added to the end of each row. wOffset + width must not exceed the width of the CUDA array src. width must not exceed dpitch. cudaMemcpy2DFromArray() returns an error if dpitch exceeds the maximum allowed.
- Parameters
- dstAny
Destination memory address
- dpitchsize_t
Pitch of destination memory
- srcAny
Source memory address
- wOffsetsize_t
Source starting X offset (columns in bytes)
- hOffsetsize_t
Source starting Y offset (rows)
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpy2D
cuMemcpy2DUnaligned
- cuda.cudart.cudaMemcpy2DArrayToArray(dst, size_t wOffsetDst, size_t hOffsetDst, src, size_t wOffsetSrc, size_t hOffsetSrc, size_t width, size_t height, kind: cudaMemcpyKind)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the CUDA array src starting at hOffsetSrc rows and wOffsetSrc bytes from the upper left corner to the CUDA array dst starting at hOffsetDst rows and wOffsetDst bytes from the upper left corner, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. wOffsetDst + width must not exceed the width of the CUDA array dst. wOffsetSrc + width must not exceed the width of the CUDA array src.
- Parameters
- dstAny
Destination memory address
- wOffsetDstsize_t
Destination starting X offset (columns in bytes)
- hOffsetDstsize_t
Destination starting Y offset (rows)
- srcAny
Source memory address
- wOffsetSrcsize_t
Source starting X offset (columns in bytes)
- hOffsetSrcsize_t
Source starting Y offset (rows)
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpy2D
cuMemcpy2DUnaligned
- cuda.cudart.cudaMemcpyAsync(dst, src, size_t count, kind: cudaMemcpyKind, stream)¶
Copies data between host and device.
Copies count bytes from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing.
The memory areas may not overlap. Calling cudaMemcpyAsync() with dst and src pointers that do not match the direction of the copy results in an undefined behavior.
cudaMemcpyAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and the stream is non-zero, the copy may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- dstAny
Destination memory address
- srcAny
Source memory address
- countsize_t
Size in bytes to copy
- kindcudaMemcpyKind
Type of transfer
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpyAsync
cuMemcpyDtoHAsync
cuMemcpyHtoDAsync
cuMemcpyDtoDAsync
- cuda.cudart.cudaMemcpyPeerAsync(dst, int dstDevice, src, int srcDevice, size_t count, stream)¶
Copies memory between two devices asynchronously.
Copies memory from one device to memory on another device. dst is the base device pointer of the destination memory and dstDevice is the destination device. src is the base device pointer of the source memory and srcDevice is the source device. count specifies the number of bytes to copy.
Note that this function is asynchronous with respect to the host and all work on other devices.
- Parameters
- dstAny
Destination device pointer
- dstDeviceint
Destination device
- srcAny
Source device pointer
- srcDeviceint
Source device
- countsize_t
Size of memory copy in bytes
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
cudaMemcpy
cudaMemcpyPeer
cudaMemcpyAsync
cudaMemcpy3DPeerAsync
cuMemcpyPeerAsync
- cuda.cudart.cudaMemcpy2DAsync(dst, size_t dpitch, src, size_t spitch, size_t width, size_t height, kind: cudaMemcpyKind, stream)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. dpitch and spitch are the widths in memory in bytes of the 2D arrays pointed to by dst and src, including any padding added to the end of each row. The memory areas may not overlap. width must not exceed either dpitch or spitch.
Calling cudaMemcpy2DAsync() with dst and src pointers that do not match the direction of the copy results in an undefined behavior. cudaMemcpy2DAsync() returns an error if dpitch or spitch is greater than the maximum allowed.
cudaMemcpy2DAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- dstAny
Destination memory address
- dpitchsize_t
Pitch of destination memory
- srcAny
Source memory address
- spitchsize_t
Pitch of source memory
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DToArrayAsync
cudaMemcpy2DFromArrayAsync
cudaMemcpyToSymbolAsync
cudaMemcpyFromSymbolAsync
cuMemcpy2DAsync
- cuda.cudart.cudaMemcpy2DToArrayAsync(dst, size_t wOffset, size_t hOffset, src, size_t spitch, size_t width, size_t height, kind: cudaMemcpyKind, stream)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the memory area pointed to by src to the CUDA array dst starting at hOffset rows and wOffset bytes from the upper left corner, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. spitch is the width in memory in bytes of the 2D array pointed to by src, including any padding added to the end of each row. wOffset + width must not exceed the width of the CUDA array dst. width must not exceed spitch. cudaMemcpy2DToArrayAsync() returns an error if spitch exceeds the maximum allowed.
cudaMemcpy2DToArrayAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams.
- Parameters
- dstAny
Destination memory address
- wOffsetsize_t
Destination starting X offset (columns in bytes)
- hOffsetsize_t
Destination starting Y offset (rows)
- srcAny
Source memory address
- spitchsize_t
Pitch of source memory
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
- cuda.cudart.cudaMemcpy2DFromArrayAsync(dst, size_t dpitch, src, size_t wOffset, size_t hOffset, size_t width, size_t height, kind: cudaMemcpyKind, stream)¶
Copies data between host and device.
Copies a matrix (height rows of width bytes each) from the CUDA array src starting at hOffset rows and wOffset bytes from the upper left corner to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. dpitch is the width in memory in bytes of the 2D array pointed to by dst, including any padding added to the end of each row. wOffset + width must not exceed the width of the CUDA array src. width must not exceed dpitch. cudaMemcpy2DFromArrayAsync() returns an error if dpitch exceeds the maximum allowed.
cudaMemcpy2DFromArrayAsync() is asynchronous with respect to the host, so the call may return before the copy is complete. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams.
- Parameters
- dstAny
Destination memory address
- dpitchsize_t
Pitch of destination memory
- srcAny
Source memory address
- wOffsetsize_t
Source starting X offset (columns in bytes)
- hOffsetsize_t
Source starting Y offset (rows)
- widthsize_t
Width of matrix transfer (columns in bytes)
- heightsize_t
Height of matrix transfer (rows)
- kindcudaMemcpyKind
Type of transfer
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidPitchValue cudaErrorInvalidMemcpyDirection
- None
None
See also
cudaMemcpy
cudaMemcpy2D
cudaMemcpy2DToArray
cudaMemcpy2DFromArray
cudaMemcpy2DArrayToArray
cudaMemcpyToSymbol
cudaMemcpyFromSymbol
cudaMemcpyAsync
cudaMemcpy2DAsync
cudaMemcpy2DToArrayAsync
- cuda.cudart.cudaMemset(devPtr, int value, size_t count)¶
Initializes or sets device memory to a value.
Fills the first count bytes of the memory area pointed to by devPtr with the constant byte value value.
Note that this function is asynchronous with respect to the host unless devPtr refers to pinned host memory.
- Parameters
- devPtrAny
Pointer to device memory
- valueint
Value to set for each byte of specified memory
- countsize_t
Size in bytes to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaMemset2D(devPtr, size_t pitch, int value, size_t width, size_t height)¶
Initializes or sets device memory to a value.
Sets to the specified value value a matrix (height rows of width bytes each) pointed to by dstPtr. pitch is the width in bytes of the 2D array pointed to by dstPtr, including any padding added to the end of each row. This function performs fastest when the pitch is one that has been passed back by cudaMallocPitch().
Note that this function is asynchronous with respect to the host unless devPtr refers to pinned host memory.
- Parameters
- devPtrAny
Pointer to 2D device memory
- pitchsize_t
Pitch in bytes of 2D device memory(Unused if height is 1)
- valueint
Value to set for each byte of specified memory
- widthsize_t
Width of matrix set (columns in bytes)
- heightsize_t
Height of matrix set (rows)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemset
cudaMemset3D
cudaMemsetAsync
cudaMemset2DAsync
cudaMemset3DAsync
cuMemsetD2D8
cuMemsetD2D16
cuMemsetD2D32
- cuda.cudart.cudaMemset3D(cudaPitchedPtr pitchedDevPtr: cudaPitchedPtr, int value, cudaExtent extent: cudaExtent)¶
Initializes or sets device memory to a value.
Initializes each element of a 3D array to the specified value value. The object to initialize is defined by pitchedDevPtr. The pitch field of pitchedDevPtr is the width in memory in bytes of the 3D array pointed to by pitchedDevPtr, including any padding added to the end of each row. The xsize field specifies the logical width of each row in bytes, while the ysize field specifies the height of each 2D slice in rows. The pitch field of pitchedDevPtr is ignored when height and depth are both equal to 1.
The extents of the initialized region are specified as a width in bytes, a height in rows, and a depth in slices.
Extents with width greater than or equal to the xsize of pitchedDevPtr may perform significantly faster than extents narrower than the xsize. Secondarily, extents with height equal to the ysize of pitchedDevPtr will perform faster than when the height is shorter than the ysize.
This function performs fastest when the pitchedDevPtr has been allocated by cudaMalloc3D().
Note that this function is asynchronous with respect to the host unless pitchedDevPtr refers to pinned host memory.
- Parameters
- pitchedDevPtrcudaPitchedPtr
Pointer to pitched device memory
- valueint
Value to set for each byte of specified memory
- extentcudaExtent
Size parameters for where to set device memory (width field in bytes)
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemset
cudaMemset2D
cudaMemsetAsync
cudaMemset2DAsync
cudaMemset3DAsync
cudaMalloc3D
make_cudaPitchedPtr
make_cudaExtent
- cuda.cudart.cudaMemsetAsync(devPtr, int value, size_t count, stream)¶
Initializes or sets device memory to a value.
Fills the first count bytes of the memory area pointed to by devPtr with the constant byte value value.
cudaMemsetAsync() is asynchronous with respect to the host, so the call may return before the memset is complete. The operation can optionally be associated to a stream by passing a non-zero stream argument. If stream is non-zero, the operation may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- devPtrAny
Pointer to device memory
- valueint
Value to set for each byte of specified memory
- countsize_t
Size in bytes to set
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemset
cudaMemset2D
cudaMemset3D
cudaMemset2DAsync
cudaMemset3DAsync
cuMemsetD8Async
cuMemsetD16Async
cuMemsetD32Async
- cuda.cudart.cudaMemset2DAsync(devPtr, size_t pitch, int value, size_t width, size_t height, stream)¶
Initializes or sets device memory to a value.
Sets to the specified value value a matrix (height rows of width bytes each) pointed to by dstPtr. pitch is the width in bytes of the 2D array pointed to by dstPtr, including any padding added to the end of each row. This function performs fastest when the pitch is one that has been passed back by cudaMallocPitch().
cudaMemset2DAsync() is asynchronous with respect to the host, so the call may return before the memset is complete. The operation can optionally be associated to a stream by passing a non-zero stream argument. If stream is non-zero, the operation may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- devPtrAny
Pointer to 2D device memory
- pitchsize_t
Pitch in bytes of 2D device memory(Unused if height is 1)
- valueint
Value to set for each byte of specified memory
- widthsize_t
Width of matrix set (columns in bytes)
- heightsize_t
Height of matrix set (rows)
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemset
cudaMemset2D
cudaMemset3D
cudaMemsetAsync
cudaMemset3DAsync
cuMemsetD2D8Async
cuMemsetD2D16Async
cuMemsetD2D32Async
- cuda.cudart.cudaMemset3DAsync(cudaPitchedPtr pitchedDevPtr: cudaPitchedPtr, int value, cudaExtent extent: cudaExtent, stream)¶
Initializes or sets device memory to a value.
Initializes each element of a 3D array to the specified value value. The object to initialize is defined by pitchedDevPtr. The pitch field of pitchedDevPtr is the width in memory in bytes of the 3D array pointed to by pitchedDevPtr, including any padding added to the end of each row. The xsize field specifies the logical width of each row in bytes, while the ysize field specifies the height of each 2D slice in rows. The pitch field of pitchedDevPtr is ignored when height and depth are both equal to 1.
The extents of the initialized region are specified as a width in bytes, a height in rows, and a depth in slices.
Extents with width greater than or equal to the xsize of pitchedDevPtr may perform significantly faster than extents narrower than the xsize. Secondarily, extents with height equal to the ysize of pitchedDevPtr will perform faster than when the height is shorter than the ysize.
This function performs fastest when the pitchedDevPtr has been allocated by cudaMalloc3D().
cudaMemset3DAsync() is asynchronous with respect to the host, so the call may return before the memset is complete. The operation can optionally be associated to a stream by passing a non-zero stream argument. If stream is non-zero, the operation may overlap with operations in other streams.
The device version of this function only handles device to device copies and cannot be given local or shared pointers.
- Parameters
- pitchedDevPtrcudaPitchedPtr
Pointer to pitched device memory
- valueint
Value to set for each byte of specified memory
- extentcudaExtent
Size parameters for where to set device memory (width field in bytes)
- streamCUstream or cudaStream_t
Stream identifier
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemset
cudaMemset2D
cudaMemset3D
cudaMemsetAsync
cudaMemset2DAsync
cudaMalloc3D
make_cudaPitchedPtr
make_cudaExtent
- cuda.cudart.cudaMemPrefetchAsync(devPtr, size_t count, int dstDevice, stream)¶
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. stream is the stream in which the operation is enqueued. The memory range must refer to managed memory allocated via cudaMallocManaged or declared via managed variables.
Passing in cudaCpuDeviceId for dstDevice will prefetch the data to host memory. If dstDevice is a GPU, then the device attribute cudaDevAttrConcurrentManagedAccess must be non-zero. Additionally, stream must be associated with a device that has a non-zero value for the device attribute cudaDevAttrConcurrentManagedAccess.
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 cudaMallocManaged allocations to host memory in order to make room. Device memory allocated using cudaMalloc or cudaMallocArray 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 cudaMemAdvise as described below:
If cudaMemAdviseSetReadMostly was set on any subset of this memory range, then that subset will create a read-only copy of the pages on dstDevice.
If cudaMemAdviseSetPreferredLocation 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 cudaMemAdviseSetAccessedBy 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
- devPtrAny
Pointer to be prefetched
- countsize_t
Size in bytes
- dstDeviceint
Destination device to prefetch to
- streamCUstream or cudaStream_t
Stream to enqueue prefetch operation
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
cudaMemcpy
cudaMemcpyPeer
cudaMemcpyAsync
cudaMemcpy3DPeerAsync
cudaMemAdvise
cuMemPrefetchAsync
- cuda.cudart.cudaMemAdvise(devPtr, size_t count, advice: cudaMemoryAdvise, 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 cudaMallocManaged 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: - cudaMemAdviseSetReadMostly: 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 cudaMemPrefetchAsync 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 cudaDevAttrConcurrentManagedAccess. Also, if a context is created on a device that does not have the device attribute cudaDevAttrConcurrentManagedAccess 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 cudaDevAttrPageableMemoryAccess 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 cudaDevAttrPageableMemoryAccessUsesHostPageTables, then setting this advice will not create a read-only copy when that device accesses this memory region. - cudaMemAdviceUnsetReadMostly: Undoes the effect of cudaMemAdviceReadMostly 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. - cudaMemAdviseSetPreferredLocation: This advice sets the preferred location for the data to be the memory belonging to device. Passing in cudaCpuDeviceId 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 cudaDevAttrConcurrentManagedAccess. 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 cudaMemPrefetchAsync. 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 cudaMemAdviseSetReadMostly 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 cudaMemAdviseSetReadMostly. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute cudaDevAttrPageableMemoryAccess. Additionally, if device has a non-zero value for the device attribute cudaDevAttrPageableMemoryAccessUsesHostPageTables, then this call has no effect. Note however that this behavior may change in the future. - cudaMemAdviseUnsetPreferredLocation: Undoes the effect of cudaMemAdviseSetPreferredLocation and changes the preferred location to none. - cudaMemAdviseSetAccessedBy: This advice implies that the data will be accessed by device. Passing in cudaCpuDeviceId for device will set the advice for the CPU. If device is a GPU, then the device attribute cudaDevAttrConcurrentManagedAccess 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 cudaMemAdviceSetAccessedBy flag set for this data will now have its mapping updated to point to the page in host memory. If cudaMemAdviseSetReadMostly 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 cudaMemAdviseSetPreferredLocation 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 cudaDevAttrPageableMemoryAccess. Additionally, if device has a non- zero value for the device attribute cudaDevAttrPageableMemoryAccessUsesHostPageTables, then this call has no effect. - cudaMemAdviseUnsetAccessedBy: Undoes the effect of cudaMemAdviseSetAccessedBy. 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 cudaDevAttrPageableMemoryAccess. Additionally, if device has a non-zero value for the device attribute cudaDevAttrPageableMemoryAccessUsesHostPageTables, then this call has no effect.
- Parameters
- devPtrAny
Pointer to memory to set the advice for
- countsize_t
Size in bytes of the memory range
- advicecudaMemoryAdvise
Advice to be applied for the specified memory range
- deviceint
Device to apply the advice for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- None
None
See also
- cuda.cudart.cudaMemRangeGetAttribute(size_t dataSize, attribute: cudaMemRangeAttribute, devPtr, size_t 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 cudaMallocManaged or declared via managed variables.
The attribute parameter can take the following values: - cudaMemRangeAttributeReadMostly: 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. - cudaMemRangeAttributePreferredLocation: 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 cudaCpuDeviceId if all pages in the memory range have the CPU as their preferred location, or it will be cudaInvalidDeviceId 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. - cudaMemRangeAttributeAccessedBy: 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 cudaMemAdviceSetAccessedBy 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, cudaInvalidDeviceId 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, cudaInvalidDeviceId, cudaInvalidDeviceId }. 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. - cudaMemRangeAttributeLastPrefetchLocation: 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 cudaMemPrefetchAsync. This will either be a GPU id or cudaCpuDeviceId 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, cudaInvalidDeviceId 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
- dataSizesize_t
Array containing the size of data
- attributecudaMemRangeAttribute
The attribute to query
- devPtrAny
Start of the range to query
- countsize_t
Size of the range to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- dataAny
A pointers to a memory location where the result of each attribute query will be written to.
See also
cudaMemRangeGetAttributes
cudaMemPrefetchAsync
cudaMemAdvise
cuMemRangeGetAttribute
- cuda.cudart.cudaMemRangeGetAttributes(dataSizes: List[int], attributes: List[cudaMemRangeAttribute], size_t numAttributes, devPtr, size_t count)¶
Query attributes of a given memory range.
Query attributes of the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via cudaMallocManaged or declared via managed variables. The attributes array will be interpreted to have numAttributes entries. The dataSizes array will also be interpreted to have numAttributes entries. The results of the query will be stored in data.
The list of supported attributes are given below. Please refer to cudaMemRangeGetAttribute for attribute descriptions and restrictions.
cudaMemRangeAttributeReadMostly -
cudaMemRangeAttributePreferredLocation - cudaMemRangeAttributeAccessedBy - cudaMemRangeAttributeLastPrefetchLocation
- Parameters
- dataSizesList[int]
Array containing the sizes of each result
- attributesList[cudaMemRangeAttribute]
An array of attributes to query (numAttributes and the number of attributes in this array should match)
- numAttributessize_t
Number of attributes to query
- devPtrAny
Start of the range to query
- countsize_t
Size of the range to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- dataList[Any]
A two-dimensional array containing pointers to memory locations where the result of each attribute query will be written to.
See also
cudaMemRangeGetAttribute
cudaMemAdvise
cudaMemPrefetchAsync
cuMemRangeGetAttributes
Stream Ordered Memory Allocator¶
overview
The asynchronous allocator allows the user to allocate and free in stream order. All asynchronous accesses of the allocation must happen between the stream executions of the allocation and the free. If the memory is accessed outside of the promised stream order, a use before allocation / use after free error will cause undefined behavior. The allocator is free to reallocate the memory as long as it can guarantee that compliant memory accesses will not overlap temporally. The allocator may refer to internal stream ordering as well as inter-stream dependencies (such as CUDA events and null stream dependencies) when establishing the temporal guarantee. The allocator may also insert inter-stream dependencies to establish the temporal guarantee.
Supported Platforms
Whether or not a device supports the integrated stream ordered memory allocator may be queried by calling cudaDeviceGetAttribute() with the device attribute ::cudaDevAttrMemoryPoolsSupported.
- cuda.cudart.cudaMallocAsync(size_t size, 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 associated with the stream’s device.
- Parameters
- sizesize_t
Number of bytes to allocate
- hStreamCUstream or cudaStream_t
The stream establishing the stream ordering contract and the memory pool to allocate from
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported cudaErrorOutOfMemory
- devPtrint
Returned device pointer
See also
Notes
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.
- cuda.cudart.cudaFreeAsync(devPtr, 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.
- Parameters
- dptrAny
memory to free
- hStreamCUstream or cudaStream_t
The stream establishing the stream ordering promise
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported
- None
None
See also
Notes
During stream capture, this function results in the creation of a free node and must therefore be passed the address of a graph allocation.
- cuda.cudart.cudaMemPoolTrimTo(memPool, size_t 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.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
The memory pool to trim
- minBytesToKeepsize_t
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.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
Notes
: Allocations that have been asynchronously freed but whose completion has not been observed on the host (eg. by a synchronize) can count as outstanding.
- cuda.cudart.cudaMemPoolSetAttribute(memPool, attr: cudaMemPoolAttr, value)¶
Sets attributes of a memory pool.
Supported attributes are: - cudaMemPoolAttrReleaseThreshold: (value type = cuuint64_t) Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS. When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize. (default 0) - cudaMemPoolReuseFollowEventDependencies: (value type = int) Allow cudaMallocAsync to use memory asynchronously freed in another stream as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies. (default enabled) - cudaMemPoolReuseAllowOpportunistic: (value type = int) Allow reuse of already completed frees when there is no dependency between the free and allocation. (default enabled) - cudaMemPoolReuseAllowInternalDependencies: (value type = int) Allow cudaMallocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by cudaFreeAsync (default enabled). - cudaMemPoolAttrReservedMemHigh: (value type = cuuint64_t) Reset the high watermark that tracks the amount of backing memory that was allocated for the memory pool. It is illegal to set this attribute to a non-zero value. - cudaMemPoolAttrUsedMemHigh: (value type = cuuint64_t) Reset the high watermark that tracks the amount of used memory that was allocated for the memory pool. It is illegal to set this attribute to a non-zero value.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
The memory pool to modify
- attrcudaMemPoolAttr
The attribute to modify
- valueAny
Pointer to the value to assign
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaMemPoolGetAttribute(memPool, attr: cudaMemPoolAttr)¶
Gets attributes of a memory pool.
Supported attributes are: - cudaMemPoolAttrReleaseThreshold: (value type = cuuint64_t) Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS. When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize. (default 0) - cudaMemPoolReuseFollowEventDependencies: (value type = int) Allow cudaMallocAsync to use memory asynchronously freed in another stream as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies. (default enabled) - cudaMemPoolReuseAllowOpportunistic: (value type = int) Allow reuse of already completed frees when there is no dependency between the free and allocation. (default enabled) - cudaMemPoolReuseAllowInternalDependencies: (value type = int) Allow cudaMallocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by cudaFreeAsync (default enabled). - cudaMemPoolAttrReservedMemCurrent: (value type = cuuint64_t) Amount of backing memory currently allocated for the mempool. - cudaMemPoolAttrReservedMemHigh: (value type = cuuint64_t) High watermark of backing memory allocated for the mempool since the last time it was reset. - cudaMemPoolAttrUsedMemCurrent: (value type = cuuint64_t) Amount of memory from the pool that is currently in use by the application. - cudaMemPoolAttrUsedMemHigh: (value type = cuuint64_t) High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
The memory pool to get attributes of
- attrcudaMemPoolAttr
The attribute to get
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- valueAny
Retrieved value
- cuda.cudart.cudaMemPoolSetAccess(memPool, descList: List[cudaMemAccessDesc], size_t count)¶
Controls visibility of pools between devices.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
The pool being modified
- mapList[cudaMemAccessDesc]
Array of access descriptors. Each descriptor instructs the access to enable for a single gpu
- countsize_t
Number of descriptors in the map array.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaMemPoolGetAccess(memPool, cudaMemLocation location: cudaMemLocation)¶
Returns the accessibility of a pool from a device.
Returns the accessibility of the pool’s memory from the specified location.
- Parameters
- memPoolCUmemoryPool or cudaMemPool_t
the pool being queried
- locationcudaMemLocation
the location accessing the pool
- Returns
- cudaError_t
- flagscudaMemAccessFlags
the accessibility of the pool from the specified location
See also
- cuda.cudart.cudaMemPoolCreate(cudaMemPoolProps poolProps: cudaMemPoolProps)¶
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.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported
- None
None
See also
Notes
Specifying cudaMemHandleTypeNone creates a memory pool that will not support IPC.
- cuda.cudart.cudaMemPoolDestroy(memPool)¶
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 cudaMemPoolDestroy 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.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
Notes
A device’s default memory pool cannot be destroyed.
- cuda.cudart.cudaMallocFromPoolAsync(size_t size, memPool, stream)¶
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.
- Parameters
- bytesizesize_t
Number of bytes to allocate
- memPoolCUmemoryPool or cudaMemPool_t
The pool to allocate from
- streamCUstream or cudaStream_t
The stream establishing the stream ordering semantic
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported cudaErrorOutOfMemory
- ptrint
Returned device pointer
See also
Notes
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.
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 cudaMemPoolImportFromShareableHandle. Individual pointers can then be shared with the cudaMemPoolExportPointer and cudaMemPoolImportPointer APIs. The implementation of what the shareable handle is and how it can be transferred is defined by the requested handle type.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
pool to export
- handleTypecudaMemAllocationHandleType
the type of handle to create
- flagsunsigned int
must be 0
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorOutOfMemory
- handle_outint
pointer to the location in which to store the requested handle
Notes
: To create an IPC capable mempool, create a mempool with a CUmemAllocationHandleType other than cudaMemHandleTypeNone.
imports a memory pool from a shared handle.
Specific allocations can be imported from the imported pool with cudaMemPoolImportPointer.
- Parameters
- handleAny
OS handle of the pool to open
- handleTypecudaMemAllocationHandleType
The type of handle being imported
- flagsunsigned int
must be 0
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorOutOfMemory
- pool_outcudaMemPool_t
Returned memory pool
Notes
Imported memory pools do not support creating new allocations. As such imported memory pools may not be used in cudaDeviceSetMemPool or cudaMallocFromPoolAsync calls.
- cuda.cudart.cudaMemPoolExportPointer(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 cudaMemPoolImportPointer api. The data is not a handle and may be shared through any IPC mechanism.
- Parameters
- ptrAny
pointer to memory being exported
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorOutOfMemory
- shareData_outcudaMemPoolPtrExportData
Returned export data
- cuda.cudart.cudaMemPoolImportPointer(memPool, cudaMemPoolPtrExportData exportData: cudaMemPoolPtrExportData)¶
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 cudaFree or cudaFreeAsync. If cudaFreeAsync is used, the free must be completed on the importing process before the free operation on the exporting process.
- Parameters
- poolCUmemoryPool or cudaMemPool_t
pool from which to import
- shareDatacudaMemPoolPtrExportData
data specifying the memory to import
- Returns
- cudaError_t
CUDA_SUCCESS CUDA_ERROR_INVALID_VALUE CUDA_ERROR_NOT_INITIALIZED CUDA_ERROR_OUT_OF_MEMORY
- ptr_outint
pointer to imported memory
See also
Notes
The cudaFreeAsync api may be used in the exporting process before the cudaFreeAsync operation completes in its stream as long as the cudaFreeAsync in the exporting process specifies a stream with a stream dependency on the importing process’s cudaFreeAsync.
Unified Addressing¶
This section describes the unified addressing functions of the CUDA runtime application programming interface.
Overview
- CUDA devices can share a unified address space with the host.
For these devices there is no distinction between a device pointer and a host pointer – the same pointer value may be used to access memory from the host program and from a kernel running on the device (with exceptions enumerated below).
Supported Platforms
Whether or not a device supports unified addressing may be queried by calling cudaGetDeviceProperties() with the device property cudaDeviceProp::unifiedAddressing. Unified addressing is automatically enabled in 64-bit processes .
Looking Up Information from Pointer Values
It is possible to look up information about the memory which backs a pointer value. For instance, one may want to know if a pointer points to host or device memory. As another example, in the case of device memory, one may want to know on which CUDA device the memory resides. These properties may be queried using the function cudaPointerGetAttributes() Since pointers are unique, it is not necessary to specify information about the pointers specified to cudaMemcpy() and other copy functions.
The copy direction ::cudaMemcpyDefault may be used to specify that the CUDA runtime should infer the location of the pointer from its value.
Automatic Mapping of Host Allocated Host Memory
All host memory allocated through all devices using cudaMallocHost() and cudaHostAlloc() is always directly accessible from all devices that support unified addressing. This is the case regardless of whether or not the flags cudaHostAllocPortable and cudaHostAllocMapped are specified. The pointer value through which allocated host memory may be accessed in kernels on all devices that support unified addressing is the same as the pointer value through which that memory is accessed on the host. It is not necessary to call cudaHostGetDevicePointer() to get the device pointer for these allocations.
Note that this is not the case for memory allocated using the flag cudaHostAllocWriteCombined, as discussed below.
Direct Access of Peer Memory
Upon enabling direct access from a device that supports unified addressing to another peer device that supports unified addressing using cudaDeviceEnablePeerAccess() all memory allocated in the peer device using cudaMalloc() and cudaMallocPitch() will immediately be accessible by the current device. The device pointer value through which any peer’s memory may be accessed in the current device is the same pointer value through which that memory may be accessed from the peer device.
Exceptions, Disjoint Addressing
Not all memory may be accessed on devices through the same pointer value through which they are accessed on the host. These exceptions are host memory registered using cudaHostRegister() and host memory allocated using the flag cudaHostAllocWriteCombined. For these exceptions, there exists a distinct host and device address for the memory. The device address is guaranteed to not overlap any valid host pointer range and is guaranteed to have the same value across all devices that support unified addressing.
This device address may be queried using cudaHostGetDevicePointer() when a device using unified addressing is current. Either the host or the unified device pointer value may be used to refer to this memory in cudaMemcpy() and similar functions using the ::cudaMemcpyDefault memory direction.
- cuda.cudart.cudaPointerGetAttributes(ptr)¶
Returns attributes about a specified pointer.
Returns in *attributes the attributes of the pointer ptr. If pointer was not allocated in, mapped by or registered with context supporting unified addressing cudaErrorInvalidValue is returned.
cudaPointerAttributes::type identifies type of memory. It can be
cudaMemoryTypeUnregistered for unregistered host memory, cudaMemoryTypeHost for registered host memory, cudaMemoryTypeDevice for device memory or cudaMemoryTypeManaged for managed memory. - device is the device against which ptr was allocated. If ptr has memory type cudaMemoryTypeDevice then this identifies the device on which the memory referred to by ptr physically resides. If ptr has memory type cudaMemoryTypeHost then this identifies the device which was current when the allocation was made (and if that device is deinitialized then this allocation will vanish with that device’s state). - devicePointer is the device pointer alias through which the memory referred to by ptr may be accessed on the current device. If the memory referred to by ptr cannot be accessed directly by the current device then this is NULL. - hostPointer is the host pointer alias through which the memory referred to by ptr may be accessed on the host. If the memory referred to by ptr cannot be accessed directly by the host then this is NULL.
- Parameters
- ptrAny
Pointer to get attributes for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue
- attributescudaPointerAttributes
Attributes for the specified pointer
See also
cudaGetDeviceCount
cudaGetDevice
cudaSetDevice
cudaChooseDevice
cuPointerGetAttributes
Notes
In CUDA 11.0 forward passing host pointer will return cudaMemoryTypeUnregistered in cudaPointerAttributestype and call will return cudaSuccess.
Peer Device Memory Access¶
This section describes the peer device memory access functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaDeviceCanAccessPeer(int device, int peerDevice)¶
Queries if a device may directly access a peer device’s memory.
Returns in *canAccessPeer a value of 1 if device device is capable of directly accessing memory from peerDevice and 0 otherwise. If direct access of peerDevice from device is possible, then access may be enabled by calling cudaDeviceEnablePeerAccess().
- Parameters
- deviceint
Device from which allocations on peerDevice are to be directly accessed.
- peerDeviceint
Device on which the allocations to be directly accessed by device reside.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice
- canAccessPeerint
Returned access capability
See also
cudaDeviceEnablePeerAccess
cudaDeviceDisablePeerAccess
cuDeviceCanAccessPeer
- cuda.cudart.cudaDeviceEnablePeerAccess(int peerDevice, unsigned int flags)¶
Enables direct access to memory allocations on a peer device.
On success, all allocations from peerDevice will immediately be accessible by the current device. They will remain accessible until access is explicitly disabled using cudaDeviceDisablePeerAccess() or either device is reset using cudaDeviceReset().
Note that access granted by this call is unidirectional and that in order to access memory on the current device from peerDevice, a separate symmetric call to cudaDeviceEnablePeerAccess() 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 cudaErrorInvalidDevice if cudaDeviceCanAccessPeer() indicates that the current device cannot directly access memory from peerDevice.
Returns cudaErrorPeerAccessAlreadyEnabled if direct access of peerDevice from the current device has already been enabled.
Returns cudaErrorInvalidValue if flags is not 0.
- Parameters
- peerDeviceint
Peer device to enable direct access to from the current device
- flagsunsigned int
Reserved for future use and must be set to 0
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorPeerAccessAlreadyEnabled cudaErrorInvalidValue
- None
None
See also
cudaDeviceCanAccessPeer
cudaDeviceDisablePeerAccess
cuCtxEnablePeerAccess
- cuda.cudart.cudaDeviceDisablePeerAccess(int peerDevice)¶
Disables direct access to memory allocations on a peer device.
Returns cudaErrorPeerAccessNotEnabled if direct access to memory on peerDevice has not yet been enabled from the current device.
- Parameters
- peerDeviceint
Peer device to disable direct access to
- Returns
- cudaError_t
cudaSuccess cudaErrorPeerAccessNotEnabled cudaErrorInvalidDevice
- None
None
See also
cudaDeviceCanAccessPeer
cudaDeviceEnablePeerAccess
cuCtxDisablePeerAccess
OpenGL Interoperability¶
impl_private
This section describes the OpenGL interoperability functions of the CUDA runtime application programming interface. Note that mapping of OpenGL resources is performed with the graphics API agnostic, resource mapping interface described in Graphics Interopability.
- enum cuda.cudart.cudaGLDeviceList(value)¶
CUDA devices corresponding to the current OpenGL context
- Member Type
int
Valid values are as follows:
- cudaGLDeviceListAll¶
- cudaGLDeviceListCurrentFrame¶
- cudaGLDeviceListNextFrame¶
- cuda.cudart.cudaGLGetDevices(unsigned int cudaDeviceCount, deviceList: cudaGLDeviceList)¶
Gets the CUDA devices associated with the current OpenGL context.
Returns in *pCudaDeviceCount the number of CUDA-compatible devices corresponding to the current OpenGL context. Also returns in *pCudaDevices at most cudaDeviceCount of the CUDA-compatible devices corresponding to the current OpenGL context. If any of the GPUs being used by the current OpenGL context are not CUDA capable then the call will return cudaErrorNoDevice.
- Parameters
- cudaDeviceCountunsigned int
The size of the output device array pCudaDevices
- deviceListcudaGLDeviceList
The set of devices to return. This set may be cudaGLDeviceListAll for all devices, cudaGLDeviceListCurrentFrame for the devices used to render the current frame (in SLI), or cudaGLDeviceListNextFrame for the devices used to render the next frame (in SLI).
- Returns
- cudaError_t
cudaSuccess cudaErrorNoDevice cudaErrorInvalidGraphicsContext cudaErrorUnknown
- pCudaDeviceCountunsigned int
Returned number of CUDA devices corresponding to the current OpenGL context
- pCudaDevicesList[int]
Returned CUDA devices corresponding to the current OpenGL context
See also
Notes
This function is not supported on Mac OS X.
- cuda.cudart.cudaGraphicsGLRegisterImage(image, target, unsigned int flags)¶
Register an OpenGL texture or renderbuffer object.
Registers the texture or renderbuffer object specified by image for access by CUDA. A handle to the registered object is returned as resource.
target must match the type of the object, and must be one of GL_TEXTURE_2D, GL_TEXTURE_RECTANGLE, GL_TEXTURE_CUBE_MAP, GL_TEXTURE_3D, GL_TEXTURE_2D_ARRAY, or GL_RENDERBUFFER.
The register flags flags specify the intended usage, as follows: - cudaGraphicsRegisterFlagsNone: 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. This is the default value. - cudaGraphicsRegisterFlagsReadOnly: Specifies that CUDA will not write to this resource. - cudaGraphicsRegisterFlagsWriteDiscard: Specifies that CUDA 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. - cudaGraphicsRegisterFlagsSurfaceLoadStore: Specifies that CUDA will bind this resource to a surface reference. - cudaGraphicsRegisterFlagsTextureGather: Specifies that CUDA will perform texture gather operations on this resource.
The following image formats are supported. For brevity’s sake, the list is abbreviated. For ex., {GL_R, GL_RG} X {8, 16} would expand to the following 4 formats {GL_R8, GL_R16, GL_RG8, GL_RG16} : - GL_RED, GL_RG, GL_RGBA, GL_LUMINANCE, GL_ALPHA, GL_LUMINANCE_ALPHA, GL_INTENSITY - {GL_R, GL_RG, GL_RGBA} X {8, 16, 16F, 32F, 8UI, 16UI, 32UI, 8I, 16I, 32I} - {GL_LUMINANCE, GL_ALPHA, GL_LUMINANCE_ALPHA, GL_INTENSITY} X {8, 16, 16F_ARB, 32F_ARB, 8UI_EXT, 16UI_EXT, 32UI_EXT, 8I_EXT, 16I_EXT, 32I_EXT}
The following image classes are currently disallowed: - Textures with borders - Multisampled renderbuffers
- Parameters
- imageAny
name of texture or renderbuffer object to be registered
- targetAny
Identifies the type of object specified by image
- flagsunsigned int
Register flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- resourcecudaGraphicsResource_t
Pointer to the returned object handle
See also
cudaGraphicsUnregisterResource
cudaGraphicsMapResources
cudaGraphicsSubResourceGetMappedArray
cuGraphicsGLRegisterImage
- cuda.cudart.cudaGraphicsGLRegisterBuffer(buffer, unsigned int flags)¶
Registers an OpenGL buffer object.
Registers the buffer object specified by buffer for access by CUDA. A handle to the registered object is returned as resource. The register flags flags specify the intended usage, as follows:
cudaGraphicsRegisterFlagsNone: 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. This is the default value. - cudaGraphicsRegisterFlagsReadOnly: Specifies that CUDA will not write to this resource. - cudaGraphicsRegisterFlagsWriteDiscard: Specifies that CUDA 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.
- Parameters
- bufferAny
name of buffer object to be registered
- flagsunsigned int
Register flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- resourcecudaGraphicsResource_t
Pointer to the returned object handle
See also
cudaGraphicsUnregisterResource
cudaGraphicsMapResources
cudaGraphicsResourceGetMappedPointer
cuGraphicsGLRegisterBuffer
Direct3D 9 Interoperability¶
Direct3D 10 Interoperability¶
Direct3D 11 Interoperability¶
VDPAU Interoperability¶
This section describes the VDPAU interoperability functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaVDPAUGetDevice(vdpDevice, vdpGetProcAddress)¶
Gets the CUDA device associated with a VdpDevice.
Returns the CUDA device associated with a VdpDevice, if applicable.
- Parameters
- vdpDeviceAny
A VdpDevice handle
- vdpGetProcAddressAny
VDPAU’s VdpGetProcAddress function pointer
- Returns
- cudaError_t
cudaSuccess
- deviceint
Returns the device associated with vdpDevice, or -1 if the device associated with vdpDevice is not a compute device.
See also
cudaVDPAUSetVDPAUDevice
cuVDPAUGetDevice
- cuda.cudart.cudaVDPAUSetVDPAUDevice(int device, vdpDevice, vdpGetProcAddress)¶
Sets a CUDA device to use VDPAU interoperability.
Records vdpDevice as the VdpDevice for VDPAU interoperability with the CUDA device device and sets device as the current device for the calling host thread.
If device has already been initialized then this call will fail with the error cudaErrorSetOnActiveProcess. In this case it is necessary to reset device using cudaDeviceReset() before VDPAU interoperability on device may be enabled.
- Parameters
- deviceint
Device to use for VDPAU interoperability
- vdpDeviceAny
The VdpDevice to interoperate with
- vdpGetProcAddressAny
VDPAU’s VdpGetProcAddress function pointer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorSetOnActiveProcess
- None
None
- cuda.cudart.cudaGraphicsVDPAURegisterVideoSurface(vdpSurface, unsigned int flags)¶
Register a VdpVideoSurface object.
Registers the VdpVideoSurface specified by vdpSurface for access by CUDA. A handle to the registered object is returned as resource. The surface’s intended usage is specified using flags, as follows:
cudaGraphicsMapFlagsNone: 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. This is the default value. - cudaGraphicsMapFlagsReadOnly: Specifies that CUDA will not write to this resource. - cudaGraphicsMapFlagsWriteDiscard: Specifies that CUDA 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.
- Parameters
- vdpSurfaceAny
VDPAU object to be registered
- flagsunsigned int
Map flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- resourcecudaGraphicsResource_t
Pointer to the returned object handle
See also
cudaVDPAUSetVDPAUDevice
cudaGraphicsUnregisterResource
cudaGraphicsSubResourceGetMappedArray
cuGraphicsVDPAURegisterVideoSurface
- cuda.cudart.cudaGraphicsVDPAURegisterOutputSurface(vdpSurface, unsigned int flags)¶
Register a VdpOutputSurface object.
Registers the VdpOutputSurface specified by vdpSurface for access by CUDA. A handle to the registered object is returned as resource. The surface’s intended usage is specified using flags, as follows:
cudaGraphicsMapFlagsNone: 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. This is the default value. - cudaGraphicsMapFlagsReadOnly: Specifies that CUDA will not write to this resource. - cudaGraphicsMapFlagsWriteDiscard: Specifies that CUDA 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.
- Parameters
- vdpSurfaceAny
VDPAU object to be registered
- flagsunsigned int
Map flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- resourcecudaGraphicsResource_t
Pointer to the returned object handle
See also
cudaVDPAUSetVDPAUDevice
cudaGraphicsUnregisterResource
cudaGraphicsSubResourceGetMappedArray
cuGraphicsVDPAURegisterOutputSurface
EGL Interoperability¶
This section describes the EGL interoperability functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaGraphicsEGLRegisterImage(image, unsigned int flags)¶
Registers an EGL image.
Registers the EGLImageKHR specified by image for access by CUDA. A handle to the registered object is returned as pCudaResource. Additional Mapping/Unmapping is not required for the registered resource and cudaGraphicsResourceGetMappedEglFrame can be directly called on the pCudaResource.
The application will be responsible for synchronizing access to shared objects. The application must ensure that any pending operation which access the objects have completed before passing control to CUDA. This may be accomplished by issuing and waiting for glFinish command on all GLcontexts (for OpenGL and likewise for other APIs). The application will be also responsible for ensuring that any pending operation on the registered CUDA resource has completed prior to executing subsequent commands in other APIs accesing the same memory objects. This can be accomplished by calling cuCtxSynchronize or cuEventSynchronize (preferably).
The surface’s intended usage is specified using flags, as follows:
cudaGraphicsRegisterFlagsNone: 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. This is the default value. - cudaGraphicsRegisterFlagsReadOnly: Specifies that CUDA will not write to this resource. - cudaGraphicsRegisterFlagsWriteDiscard: Specifies that CUDA 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.
The EGLImageKHR is an object which can be used to create EGLImage target resource. It is defined as a void pointer. typedef void* EGLImageKHR
- Parameters
- imageAny
An EGLImageKHR image which can be used to create target resource.
- flagsunsigned int
Map flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorInvalidValue cudaErrorUnknown
- pCudaResourcecudaGraphicsResource_t
Pointer to the returned object handle
See also
cudaGraphicsUnregisterResource
cudaGraphicsResourceGetMappedEglFrame
cuGraphicsEGLRegisterImage
- cuda.cudart.cudaEGLStreamConsumerConnect(eglStream)¶
Connect CUDA to EGLStream as a consumer.
Connect CUDA as a consumer to EGLStreamKHR specified by eglStream.
The EGLStreamKHR is an EGL object that transfers a sequence of image frames from one API to another.
- Parameters
- eglStreamAny
EGLStreamKHR handle
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- conncudaEglStreamConnection
Pointer to the returned connection handle
See also
cudaEGLStreamConsumerDisconnect
cudaEGLStreamConsumerAcquireFrame
cudaEGLStreamConsumerReleaseFrame
cuEGLStreamConsumerConnect
- cuda.cudart.cudaEGLStreamConsumerConnectWithFlags(eglStream, unsigned int flags)¶
Connect CUDA to EGLStream as a consumer with given flags.
Connect CUDA as a consumer to EGLStreamKHR specified by stream with specified flags defined by cudaEglResourceLocationFlags.
The flags specify whether the consumer wants to access frames from system memory or video memory. Default is cudaEglResourceLocationVidmem.
- Parameters
- eglStreamAny
EGLStreamKHR handle
- flagsunsigned int
Flags denote intended location - system or video.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- conncudaEglStreamConnection
Pointer to the returned connection handle
See also
cudaEGLStreamConsumerDisconnect
cudaEGLStreamConsumerAcquireFrame
cudaEGLStreamConsumerReleaseFrame
cuEGLStreamConsumerConnectWithFlags
- cuda.cudart.cudaEGLStreamConsumerDisconnect(conn)¶
Disconnect CUDA as a consumer to EGLStream .
Disconnect CUDA as a consumer to EGLStreamKHR.
- Parameters
- connAny
Conection to disconnect.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- None
None
See also
cudaEGLStreamConsumerConnect
cudaEGLStreamConsumerAcquireFrame
cudaEGLStreamConsumerReleaseFrame
cuEGLStreamConsumerDisconnect
- cuda.cudart.cudaEGLStreamConsumerAcquireFrame(conn, pCudaResource, pStream, unsigned int timeout)¶
Acquire an image frame from the EGLStream with CUDA as a consumer.
Acquire an image frame from EGLStreamKHR. cudaGraphicsResourceGetMappedEglFrame can be called on pCudaResource to get cudaEglFrame.
- Parameters
- connAny
Connection on which to acquire
- pCudaResourceAny
CUDA resource on which the EGLStream frame will be mapped for use.
- pStreamAny
CUDA stream for synchronization and any data migrations implied by cudaEglResourceLocationFlags.
- timeoutunsigned int
Desired timeout in usec.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown cudaErrorLaunchTimeout
- None
None
See also
cudaEGLStreamConsumerConnect
cudaEGLStreamConsumerDisconnect
cudaEGLStreamConsumerReleaseFrame
cuEGLStreamConsumerAcquireFrame
- cuda.cudart.cudaEGLStreamConsumerReleaseFrame(conn, pCudaResource, pStream)¶
Releases the last frame acquired from the EGLStream.
Release the acquired image frame specified by pCudaResource to EGLStreamKHR.
- Parameters
- connAny
Connection on which to release
- pCudaResourceAny
CUDA resource whose corresponding frame is to be released
- pStreamAny
CUDA stream on which release will be done.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- None
None
See also
cudaEGLStreamConsumerConnect
cudaEGLStreamConsumerDisconnect
cudaEGLStreamConsumerAcquireFrame
cuEGLStreamConsumerReleaseFrame
- cuda.cudart.cudaEGLStreamProducerConnect(eglStream, width, height)¶
Connect CUDA to EGLStream as a producer.
Connect CUDA as a producer to EGLStreamKHR specified by stream.
The EGLStreamKHR is an EGL object that transfers a sequence of image frames from one API to another.
- Parameters
- eglStreamAny
EGLStreamKHR handle
- widthAny
width of the image to be submitted to the stream
- heightAny
height of the image to be submitted to the stream
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- conncudaEglStreamConnection
Pointer to the returned connection handle
See also
cudaEGLStreamProducerDisconnect
cudaEGLStreamProducerPresentFrame
cudaEGLStreamProducerReturnFrame
cuEGLStreamProducerConnect
- cuda.cudart.cudaEGLStreamProducerDisconnect(conn)¶
Disconnect CUDA as a producer to EGLStream .
Disconnect CUDA as a producer to EGLStreamKHR.
- Parameters
- connAny
Conection to disconnect.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- None
None
See also
cudaEGLStreamProducerConnect
cudaEGLStreamProducerPresentFrame
cudaEGLStreamProducerReturnFrame
cuEGLStreamProducerDisconnect
- cuda.cudart.cudaEGLStreamProducerPresentFrame(conn, cudaEglFrame eglframe: cudaEglFrame, pStream)¶
Present a CUDA eglFrame to the EGLStream with CUDA as a producer.
The cudaEglFrame is defined as: typedefstructcudaEglFrame_st{ union{ cudaArray_tpArray[CUDA_EGL_MAX_PLANES]; structcudaPitchedPtrpPitch[CUDA_EGL_MAX_PLANES]; }frame; cudaEglPlaneDescplaneDesc[CUDA_EGL_MAX_PLANES]; unsignedintplaneCount; cudaEglFrameTypeframeType; cudaEglColorFormateglColorFormat; }cudaEglFrame;
For cudaEglFrame of type cudaEglFrameTypePitch, the application may present sub-region of a memory allocation. In that case, cudaPitchedPtr::ptr will specify the start address of the sub-region in the allocation and cudaEglPlaneDesc will specify the dimensions of the sub-region.
- Parameters
- connAny
Connection on which to present the CUDA array
- eglframecudaEglFrame
CUDA Eglstream Proucer Frame handle to be sent to the consumer over EglStream.
- pStreamAny
CUDA stream on which to present the frame.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- None
None
See also
cudaEGLStreamProducerConnect
cudaEGLStreamProducerDisconnect
cudaEGLStreamProducerReturnFrame
cuEGLStreamProducerPresentFrame
- cuda.cudart.cudaEGLStreamProducerReturnFrame(conn, cudaEglFrame eglframe: cudaEglFrame, pStream)¶
Return the CUDA eglFrame to the EGLStream last released by the consumer.
This API can potentially return cudaErrorLaunchTimeout if the consumer has not returned a frame to EGL stream. If timeout is returned the application can retry.
- Parameters
- connAny
Connection on which to present the CUDA array
- eglframecudaEglFrame
CUDA Eglstream Proucer Frame handle returned from the consumer over EglStream.
- pStreamAny
CUDA stream on which to return the frame.
- Returns
- cudaError_t
cudaSuccess cudaErrorLaunchTimeout cudaErrorInvalidValue cudaErrorUnknown
- None
None
See also
cudaEGLStreamProducerConnect
cudaEGLStreamProducerDisconnect
cudaEGLStreamProducerPresentFrame
cuEGLStreamProducerReturnFrame
- cuda.cudart.cudaGraphicsResourceGetMappedEglFrame(resource, unsigned int index, unsigned int mipLevel)¶
Get an eglFrame through which to access a registered EGL graphics resource.
Returns in *eglFrame an eglFrame pointer through which the registered graphics resource resource may be accessed. This API can only be called for EGL graphics resources.
The cudaEglFrame is defined as typedefstructcudaEglFrame_st{ union{ cudaArray_tpArray[CUDA_EGL_MAX_PLANES]; structcudaPitchedPtrpPitch[CUDA_EGL_MAX_PLANES]; }frame; cudaEglPlaneDescplaneDesc[CUDA_EGL_MAX_PLANES]; unsignedintplaneCount; cudaEglFrameTypeframeType; cudaEglColorFormateglColorFormat; }cudaEglFrame;
- Parameters
- resourceAny
Registered resource to access.
- indexunsigned int
Index for cubemap surfaces.
- mipLevelunsigned int
Mipmap level for the subresource to access.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorUnknown
- eglFramecudaEglFrame
Returned eglFrame.
See also
cudaGraphicsSubResourceGetMappedArray
cudaGraphicsResourceGetMappedPointer
cuGraphicsResourceGetMappedEglFrame
Notes
Note that in case of multiplanar *eglFrame, pitch of only first plane (unsigned int cudaEglPlaneDescpitch) is to be considered by the application.
- cuda.cudart.cudaEventCreateFromEGLSync(eglSync, unsigned int flags)¶
Creates an event from EGLSync object.
Creates an event *phEvent from an EGLSyncKHR eglSync with the flages specified via flags. Valid flags include: - cudaEventDefault: Default event creation flag. - cudaEventBlockingSync: Specifies that the created event should use blocking synchronization. A CPU thread that uses cudaEventSynchronize() to wait on an event created with this flag will block until the event has actually been completed.
cudaEventRecord and TimingData are not supported for events created from EGLSync.
The EGLSyncKHR is an opaque handle to an EGL sync object. typedef void* EGLSyncKHR
- Parameters
- eglSyncAny
Opaque handle to EGLSync object
- flagsunsigned int
Event creation flags
- Returns
- cudaError_t
cudaSuccess cudaErrorInitializationError cudaErrorInvalidValue cudaErrorLaunchFailure cudaErrorMemoryAllocation
- phEventcudaEvent_t
Returns newly created event
Graphics Interoperability¶
This section describes the graphics interoperability functions of the CUDA runtime application programming interface.
- cuda.cudart.cudaGraphicsUnregisterResource(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 cudaErrorInvalidResourceHandle is returned.
- Parameters
- resourceAny
Resource to unregister
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorUnknown
- None
None
See also
cudaGraphicsGLRegisterBuffer
cudaGraphicsGLRegisterImage
cuGraphicsUnregisterResource
- cuda.cudart.cudaGraphicsResourceSetMapFlags(resource, unsigned 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: - cudaGraphicsMapFlagsNone: Specifies no hints about how resource will be used. It is therefore assumed that CUDA may read from or write to resource. - cudaGraphicsMapFlagsReadOnly: Specifies that CUDA will not write to resource. - cudaGraphicsMapFlagsWriteDiscard: Specifies CUDA will not read from resource and will write over the entire contents of resource, so none of the data previously stored in resource will be preserved.
If resource is presently mapped for access by CUDA then cudaErrorUnknown is returned. If flags is not one of the above values then cudaErrorInvalidValue is returned.
- Parameters
- resourceAny
Registered resource to set flags for
- flagsunsigned int
Parameters for resource mapping
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- None
None
See also
cudaGraphicsMapResources
cuGraphicsResourceSetMapFlags
- cuda.cudart.cudaGraphicsMapResources(int count, resources, stream)¶
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 cudaGraphicsMapResources() will complete before any subsequent CUDA work issued in stream begins.
If resources contains any duplicate entries then cudaErrorInvalidResourceHandle is returned. If any of resources are presently mapped for access by CUDA then cudaErrorUnknown is returned.
- Parameters
- countint
Number of resources to map
- resourcesAny
Resources to map for CUDA
- streamCUstream or cudaStream_t
Stream for synchronization
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorUnknown
- None
None
See also
cudaGraphicsResourceGetMappedPointer
cudaGraphicsSubResourceGetMappedArray
cudaGraphicsUnmapResources
cuGraphicsMapResources
- cuda.cudart.cudaGraphicsUnmapResources(int count, resources, stream)¶
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 cudaGraphicsUnmapResources() will complete before any subsequently issued graphics work begins.
If resources contains any duplicate entries then cudaErrorInvalidResourceHandle is returned. If any of resources are not presently mapped for access by CUDA then cudaErrorUnknown is returned.
- Parameters
- countint
Number of resources to unmap
- resourcesAny
Resources to unmap
- streamCUstream or cudaStream_t
Stream for synchronization
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidResourceHandle cudaErrorUnknown
- None
None
See also
cudaGraphicsMapResources
cuGraphicsUnmapResources
- cuda.cudart.cudaGraphicsResourceGetMappedPointer(resource)¶
Get an device pointer through which to access a mapped graphics resource.
Returns in *devPtr a pointer through which the mapped graphics resource resource may be accessed. Returns in *size the size of the memory in bytes which may be accessed from that pointer. The value set in devPtr may change every time that resource is mapped.
If resource is not a buffer then it cannot be accessed via a pointer and cudaErrorUnknown is returned. If resource is not mapped then cudaErrorUnknown is returned. - devPtr - Returned pointer through which resource may be accessed size - Returned size of the buffer accessible starting at *devPtr resource - Mapped resource to access ::cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidResourceHandle, cudaErrorUnknown
otefnerr
ote_init_rt ote_callback cudaGraphicsMapResources,
cudaGraphicsSubResourceGetMappedArray, cuGraphicsResourceGetMappedPointer
- Returns
- cudaError_t
- None
None
- cuda.cudart.cudaGraphicsSubResourceGetMappedArray(resource, unsigned int arrayIndex, unsigned int mipLevel)¶
Get an array through which to access a subresource of a mapped graphics resource.
Returns in *array 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 array may change every time that resource is mapped.
If resource is not a texture then it cannot be accessed via an array and cudaErrorUnknown is returned. If arrayIndex is not a valid array index for resource then cudaErrorInvalidValue is returned. If mipLevel is not a valid mipmap level for resource then cudaErrorInvalidValue is returned. If resource is not mapped then cudaErrorUnknown is returned.
- Parameters
- resourceAny
Mapped resource to access
- arrayIndexunsigned int
Array index for array textures or cubemap face index as defined by cudaGraphicsCubeFace for cubemap textures for the subresource to access
- mipLevelunsigned int
Mipmap level for the subresource to access
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- arraycudaArray_t
Returned array through which a subresource of resource may be accessed
See also
cudaGraphicsResourceGetMappedPointer
cuGraphicsSubResourceGetMappedArray
- cuda.cudart.cudaGraphicsResourceGetMappedMipmappedArray(resource)¶
Get a mipmapped array through which to access a mapped graphics resource.
Returns in *mipmappedArray a mipmapped array through which the mapped graphics resource resource may be accessed. The value set in mipmappedArray may change every time that resource is mapped.
If resource is not a texture then it cannot be accessed via an array and cudaErrorUnknown is returned. If resource is not mapped then cudaErrorUnknown is returned.
- Parameters
- resourceAny
Mapped resource to access
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorUnknown
- mipmappedArraycudaMipmappedArray_t
Returned mipmapped array through which resource may be accessed
See also
cudaGraphicsResourceGetMappedPointer
cuGraphicsResourceGetMappedMipmappedArray
Texture Object Management¶
This section describes the low level texture object management functions of the CUDA runtime application programming interface. The texture object API is only supported on devices of compute capability 3.0 or higher.
- cuda.cudart.cudaGetChannelDesc(array)¶
Get the channel descriptor of an array.
Returns in *desc the channel descriptor of the CUDA array array.
- Parameters
- arrayAny
Memory array on device
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- desccudaChannelFormatDesc
Channel format
- cuda.cudart.cudaCreateChannelDesc(int x, int y, int z, int w, f: cudaChannelFormatKind)¶
Returns a channel descriptor using the specified format.
Returns a channel descriptor with format f and number of bits of each component x, y, z, and w. The cudaChannelFormatDesc is defined as: structcudaChannelFormatDesc{ intx,y,z,w; enumcudaChannelFormatKindf; };
where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or cudaChannelFormatKindFloat.
- Parameters
- xint
X component
- yint
Y component
- zint
Z component
- wint
W component
- fcudaChannelFormatKind
Channel format
- Returns
- cudaError_t
Channel descriptor with format f
- None
None
- cuda.cudart.cudaCreateTextureObject(cudaResourceDesc pResDesc: cudaResourceDesc, cudaTextureDesc pTexDesc: cudaTextureDesc, cudaResourceViewDesc pResViewDesc: cudaResourceViewDesc)¶
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.
The cudaResourceDesc structure is defined as: structcudaResourceDesc{ enumcudaResourceTyperesType; union{ struct{ cudaArray_tarray; }array; struct{ cudaMipmappedArray_tmipmap; }mipmap; struct{ void*devPtr; structcudaChannelFormatDescdesc; size_tsizeInBytes; }linear; struct{ void*devPtr; structcudaChannelFormatDescdesc; size_twidth; size_theight; size_tpitchInBytes; }pitch2D; }res; }; where: - cudaResourceDesc::resType specifies the type of resource to texture from. CUresourceType is defined as: enumcudaResourceType{ cudaResourceTypeArray=0x00, cudaResourceTypeMipmappedArray=0x01, cudaResourceTypeLinear=0x02, cudaResourceTypePitch2D=0x03 };
If cudaResourceDesc::resType is set to cudaResourceTypeArray, cudaResourceDesc::res::array::array must be set to a valid CUDA array handle.
If cudaResourceDesc::resType is set to cudaResourceTypeMipmappedArray, cudaResourceDesc::res::mipmap::mipmap must be set to a valid CUDA mipmapped array handle and cudaTextureDesc::normalizedCoords must be set to true.
If cudaResourceDesc::resType is set to cudaResourceTypeLinear, cudaResourceDesc::res::linear::devPtr must be set to a valid device pointer, that is aligned to cudaDeviceProp::textureAlignment. cudaResourceDesc::res::linear::desc describes the format and the number of components per array element. cudaResourceDesc::res::linear::sizeInBytes specifies the size of the array in bytes. The total number of elements in the linear address range cannot exceed cudaDeviceProp::maxTexture1DLinear. The number of elements is computed as (sizeInBytes / sizeof(desc)).
If cudaResourceDesc::resType is set to cudaResourceTypePitch2D, cudaResourceDesc::res::pitch2D::devPtr must be set to a valid device pointer, that is aligned to cudaDeviceProp::textureAlignment. cudaResourceDesc::res::pitch2D::desc describes the format and the number of components per array element. cudaResourceDesc::res::pitch2D::width and cudaResourceDesc::res::pitch2D::height specify the width and height of the array in elements, and cannot exceed cudaDeviceProp::maxTexture2DLinear[0] and cudaDeviceProp::maxTexture2DLinear[1] respectively. cudaResourceDesc::res::pitch2D::pitchInBytes specifies the pitch between two rows in bytes and has to be aligned to cudaDeviceProp::texturePitchAlignment. Pitch cannot exceed cudaDeviceProp::maxTexture2DLinear[2].
The cudaResourceViewDesc struct is defined as structcudaResourceViewDesc{ enumcudaResourceViewFormatformat; size_twidth; size_theight; size_tdepth; unsignedintfirstMipmapLevel; unsignedintlastMipmapLevel; unsignedintfirstLayer; unsignedintlastLayer; }; where: - cudaResourceViewDesc::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 32-bit unsigned integer format with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have a 32-bit unsigned int with 2 channels. The other BC formats require the underlying resource to have the same 32-bit unsigned int format but with 4 channels. - cudaResourceViewDesc::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. - cudaResourceViewDesc::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. - cudaResourceViewDesc::depth specifies the new depth of the texture data. This value has to be equal to that of the original resource. - cudaResourceViewDesc::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.cudaTextureDesc::minMipmapLevelClamp and cudaTextureDesc::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. - cudaResourceViewDesc::lastMipmapLevel specifies the least detailed mipmap level. For non-mipmapped resources, this value has to be zero. - cudaResourceViewDesc::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. - cudaResourceViewDesc::lastLayer specifies the last layer index for layered textures. For non-layered resources, this value has to be zero.
- Parameters
- pResDesccudaResourceDesc
Resource descriptor
- pTexDesccudaTextureDesc
Texture descriptor
- pResViewDesccudaResourceViewDesc
Resource view descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pTexObjectcudaTextureObject_t
Texture object to create
See also
cudaDestroyTextureObject
cuTexObjectCreate
- cuda.cudart.cudaDestroyTextureObject(texObject)¶
Destroys a texture object.
Destroys the texture object specified by texObject.
- Parameters
- texObjectAny
Texture object to destroy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaCreateTextureObject
cuTexObjectDestroy
- cuda.cudart.cudaGetTextureObjectResourceDesc(texObject)¶
Returns a texture object’s resource descriptor.
Returns the resource descriptor for the texture object specified by texObject.
- Parameters
- texObjectAny
Texture object
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pResDesccudaResourceDesc
Resource descriptor
See also
cudaCreateTextureObject
cuTexObjectGetResourceDesc
- cuda.cudart.cudaGetTextureObjectTextureDesc(texObject)¶
Returns a texture object’s texture descriptor.
Returns the texture descriptor for the texture object specified by texObject.
- Parameters
- texObjectAny
Texture object
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pTexDesccudaTextureDesc
Texture descriptor
See also
cudaCreateTextureObject
cuTexObjectGetTextureDesc
- cuda.cudart.cudaGetTextureObjectResourceViewDesc(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 specified, cudaErrorInvalidValue is returned.
- Parameters
- texObjectAny
Texture object
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pResViewDesccudaResourceViewDesc
Resource view descriptor
See also
cudaCreateTextureObject
cuTexObjectGetResourceViewDesc
Surface Object Management¶
This section describes the low level texture object management functions of the CUDA runtime application programming interface. The surface object API is only supported on devices of compute capability 3.0 or higher.
- cuda.cudart.cudaCreateSurfaceObject(cudaResourceDesc pResDesc: cudaResourceDesc)¶
Creates a surface object.
Creates a surface object and returns it in pSurfObject. pResDesc describes the data to perform surface load/stores on. cudaResourceDesc::resType must be cudaResourceTypeArray and cudaResourceDesc::res::array::array must be set to a valid CUDA array handle.
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
- pResDesccudaResourceDesc
Resource descriptor
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidChannelDescriptor cudaErrorInvalidResourceHandle
- pSurfObjectcudaSurfaceObject_t
Surface object to create
See also
cudaDestroySurfaceObject
cuSurfObjectCreate
- cuda.cudart.cudaDestroySurfaceObject(surfObject)¶
Destroys a surface object.
Destroys the surface object specified by surfObject.
- Parameters
- surfObjectAny
Surface object to destroy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaCreateSurfaceObject
cuSurfObjectDestroy
- cuda.cudart.cudaGetSurfaceObjectResourceDesc(surfObject)¶
Returns a surface object’s resource descriptor Returns the resource descriptor for the surface object specified by surfObject.
- Parameters
- surfObjectAny
Surface object
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pResDesccudaResourceDesc
Resource descriptor
See also
cudaCreateSurfaceObject
cuSurfObjectGetResourceDesc
Version Management¶
- cuda.cudart.cudaDriverGetVersion()¶
Returns the latest version of CUDA supported by the driver.
Returns in *driverVersion the latest 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. If no driver is installed, then 0 is returned as the driver version.
This function automatically returns cudaErrorInvalidValue if driverVersion is NULL.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- driverVersionint
Returns the CUDA driver version.
See also
cudaRuntimeGetVersion
cuDriverGetVersion
- cuda.cudart.cudaRuntimeGetVersion()¶
Returns the CUDA Runtime version.
Returns in *runtimeVersion the version number of the current CUDA Runtime instance. The version is returned as (1000 * major + 10 * minor). For example, CUDA 9.2 would be represented by 9020.
This function automatically returns cudaErrorInvalidValue if the runtimeVersion argument is NULL.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- runtimeVersionint
Returns the CUDA Runtime version.
See also
cudaDriverGetVersion
cuDriverGetVersion
Graph Management¶
This section describes the graph management functions of CUDA runtime application programming interface.
- cuda.cudart.cudaGraphCreate(unsigned int flags)¶
Creates a graph.
Creates an empty graph, which is returned via pGraph.
- Parameters
- flagsunsigned int
Graph creation flags, must be 0
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- pGraphcudaGraph_t
Returns newly created graph
- cuda.cudart.cudaGraphAddKernelNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaKernelNodeParams pNodeParams: cudaKernelNodeParams)¶
Creates a kernel execution node and adds it to a graph.
Creates a new kernel execution node and adds it to graph with numDependencies dependencies specified via pDependencies and arguments specified in pNodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
The cudaKernelNodeParams structure is defined as:
structcudaKernelNodeParams { void*func; dim3gridDim; dim3blockDim; unsignedintsharedMemBytes; void**kernelParams; void**extra; };
When the graph is launched, the node will invoke kernel func on a (gridDim.x x gridDim.y x gridDim.z) grid of blocks. Each block contains (blockDim.x x blockDim.y x blockDim.z) threads.
sharedMem 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 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 CU_LAUNCH_PARAM_END.
CU_LAUNCH_PARAM_END, which indicates the end of the extra array;
CU_LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value
in extra will be a pointer to a buffer containing all the kernel parameters for launching kernel func; - CU_LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a pointer to a size_t containing the size of the buffer specified with CU_LAUNCH_PARAM_BUFFER_POINTER;
The error cudaErrorInvalidValue will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL).
The kernelParams or extra array, as well as the argument values it points to, are copied during this call.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- pNodeParamscudaKernelNodeParams
Parameters for the GPU execution node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDeviceFunction
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
Notes
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.
- cuda.cudart.cudaGraphKernelNodeGetParams(node)¶
Returns a kernel node’s parameters.
Returns the parameters of kernel node node in pNodeParams. The kernelParams or extra array returned in pNodeParams, 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 cudaGraphKernelNodeSetParams 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
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDeviceFunction
- pNodeParamscudaKernelNodeParams
Pointer to return the parameters
See also
cudaLaunchKernel
cudaGraphAddKernelNode
cudaGraphKernelNodeSetParams
- cuda.cudart.cudaGraphKernelNodeSetParams(node, cudaKernelNodeParams pNodeParams: cudaKernelNodeParams)¶
Sets a kernel node’s parameters.
Sets the parameters of kernel node node to pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- pNodeParamscudaKernelNodeParams
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle cudaErrorMemoryAllocation
- None
None
See also
cudaLaunchKernel
cudaGraphAddKernelNode
cudaGraphKernelNodeGetParams
- cuda.cudart.cudaGraphKernelNodeCopyAttributes(hSrc, hDst)¶
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
- dstAny
Destination node
- srcAny
Source node For list of attributes see cudaKernelNodeAttrID
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidContext
- None
None
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaGraphKernelNodeGetAttribute(hNode, attr: cudaKernelNodeAttrID)¶
Queries node attribute.
Queries attribute attr from node hNode and stores it in corresponding member of value_out.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
- attrcudaKernelNodeAttrID
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- value_outcudaKernelNodeAttrValue
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaGraphKernelNodeSetAttribute(hNode, attr: cudaKernelNodeAttrID, cudaKernelNodeAttrValue value: cudaKernelNodeAttrValue)¶
Sets node attribute.
Sets attribute attr on node hNode from corresponding attribute of value.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
- attrcudaKernelNodeAttrID
- valuecudaKernelNodeAttrValue
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidResourceHandle
- None
None
See also
cudaAccessPolicyWindow
- cuda.cudart.cudaGraphAddMemcpyNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaMemcpy3DParms pCopyParams: cudaMemcpy3DParms)¶
Creates a memcpy node and adds it to a graph.
Creates a new memcpy node and adds it to graph with numDependencies dependencies specified via pDependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
When the graph is launched, the node will perform the memcpy described by pCopyParams. See cudaMemcpy3D() 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 cudaDevAttrConcurrentManagedAccess.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- pCopyParamscudaMemcpy3DParms
Parameters for the memory copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
cudaMemcpy3D
cudaGraphAddMemcpyNodeToSymbol
cudaGraphAddMemcpyNodeFromSymbol
cudaGraphAddMemcpyNode1D
cudaGraphMemcpyNodeGetParams
cudaGraphMemcpyNodeSetParams
cudaGraphCreate
cudaGraphDestroyNode
cudaGraphAddChildGraphNode
cudaGraphAddEmptyNode
cudaGraphAddKernelNode
cudaGraphAddHostNode
cudaGraphAddMemsetNode
- cuda.cudart.cudaGraphAddMemcpyNode1D(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, dst, src, size_t count, kind: cudaMemcpyKind)¶
Creates a 1D memcpy node and adds it to a graph.
Creates a new 1D memcpy node and adds it to graph with numDependencies dependencies specified via pDependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
When the graph is launched, the node will copy count bytes from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. Launching a memcpy node with dst and src pointers that do not match the direction of the copy results in an undefined behavior.
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 cudaDevAttrConcurrentManagedAccess.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- dstAny
Destination memory address
- srcAny
Source memory address
- countsize_t
Size in bytes to copy
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphMemcpyNodeGetParams(node)¶
Returns a memcpy node’s parameters.
Returns the parameters of memcpy node node in pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pNodeParamscudaMemcpy3DParms
Pointer to return the parameters
- cuda.cudart.cudaGraphMemcpyNodeSetParams(node, cudaMemcpy3DParms pNodeParams: cudaMemcpy3DParms)¶
Sets a memcpy node’s parameters.
Sets the parameters of memcpy node node to pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- pNodeParamscudaMemcpy3DParms
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaMemcpy3D
cudaGraphMemcpyNodeSetParamsToSymbol
cudaGraphMemcpyNodeSetParamsFromSymbol
cudaGraphMemcpyNodeSetParams1D
cudaGraphAddMemcpyNode
cudaGraphMemcpyNodeGetParams
- cuda.cudart.cudaGraphMemcpyNodeSetParams1D(node, dst, src, size_t count, kind: cudaMemcpyKind)¶
Sets a memcpy node’s parameters to perform a 1-dimensional copy.
Sets the parameters of memcpy node node to the copy described by the provided parameters.
When the graph is launched, the node will copy count bytes from the memory area pointed to by src to the memory area pointed to by dst, where kind specifies the direction of the copy, and must be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToDevice, or cudaMemcpyDefault. Passing cudaMemcpyDefault is recommended, in which case the type of transfer is inferred from the pointer values. However, cudaMemcpyDefault is only allowed on systems that support unified virtual addressing. Launching a memcpy node with dst and src pointers that do not match the direction of the copy results in an undefined behavior.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- dstAny
Destination memory address
- srcAny
Source memory address
- countsize_t
Size in bytes to copy
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddMemsetNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaMemsetParams pMemsetParams: cudaMemsetParams)¶
Creates a memset node and adds it to a graph.
Creates a new memset node and adds it to graph with numDependencies dependencies specified via pDependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by pMemsetParams.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- pMemsetParamscudaMemsetParams
Parameters for the memory set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorInvalidDevice
- pGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphMemsetNodeGetParams(node)¶
Returns a memset node’s parameters.
Returns the parameters of memset node node in pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pNodeParamscudaMemsetParams
Pointer to return the parameters
- cuda.cudart.cudaGraphMemsetNodeSetParams(node, cudaMemsetParams pNodeParams: cudaMemsetParams)¶
Sets a memset node’s parameters.
Sets the parameters of memset node node to pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- pNodeParamscudaMemsetParams
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddHostNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaHostNodeParams pNodeParams: cudaHostNodeParams)¶
Creates a host execution node and adds it to a graph.
Creates a new CPU execution node and adds it to graph with numDependencies dependencies specified via pDependencies and arguments specified in pNodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- pNodeParamscudaHostNodeParams
Parameters for the host node
- Returns
- cudaError_t
cudaSuccess cudaErrorNotSupported cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphHostNodeGetParams(node)¶
Returns a host node’s parameters.
Returns the parameters of host node node in pNodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pNodeParamscudaHostNodeParams
Pointer to return the parameters
- cuda.cudart.cudaGraphHostNodeSetParams(node, cudaHostNodeParams pNodeParams: cudaHostNodeParams)¶
Sets a host node’s parameters.
Sets the parameters of host node node to nodeParams.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- pNodeParamscudaHostNodeParams
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddChildGraphNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, 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 graph with numDependencies dependencies specified via pDependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- childGraphCUgraph or cudaGraph_t
The graph to clone into this node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphChildGraphNodeGetGraph(node)¶
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
- nodeCUgraphNode or cudaGraphNode_t
Node to get the embedded graph for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphcudaGraph_t
Location to store a handle to the graph
- cuda.cudart.cudaGraphAddEmptyNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies)¶
Creates an empty node and adds it to a graph.
Creates a new node which performs no operation, and adds it to graph with numDependencies dependencies specified via pDependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphAddEventRecordNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, 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.
These nodes may not be used in loops or conditionals.
- Parameters
- hGraphCUgraph or cudaGraph_t
Graph to which to add the node
- dependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- eventCUevent or cudaEvent_t
Event for the node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- phGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphEventRecordNodeGetEvent(node)¶
Returns the event associated with an event record node.
Returns the event of event record node hNode in event_out.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to get the event for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- event_outcudaEvent_t
Pointer to return the event
- cuda.cudart.cudaGraphEventRecordNodeSetEvent(node, event)¶
Sets an event record node’s event.
Sets the event of event record node hNode to event.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to set the event for
- eventCUevent or cudaEvent_t
Event to use
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddEventWaitNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, 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 cuEventRecord() for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. event may be from a different context or device than the launch stream.
These nodes may not be used in loops or conditionals.
- Parameters
- hGraphCUgraph or cudaGraph_t
Graph to which to add the node
- dependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- eventCUevent or cudaEvent_t
Event for the node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- phGraphNodecudaGraphNode_t
Returns newly created node
- cuda.cudart.cudaGraphEventWaitNodeGetEvent(node)¶
Returns the event associated with an event wait node.
Returns the event of event wait node hNode in event_out.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to get the event for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- event_outcudaEvent_t
Pointer to return the event
- cuda.cudart.cudaGraphEventWaitNodeSetEvent(node, event)¶
Sets an event wait node’s event.
Sets the event of event wait node hNode to event.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to set the event for
- eventCUevent or cudaEvent_t
Event to use
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddExternalSemaphoresSignalNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaExternalSemaphoreSignalNodeParams nodeParams: cudaExternalSemaphoreSignalNodeParams)¶
Creates an external semaphore signal node and adds it to a graph.
Creates a new external semaphore signal node and adds it to graph 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 pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- nodeParamscudaExternalSemaphoreSignalNodeParams
Parameters for the node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
cudaGraphExternalSemaphoresSignalNodeGetParams
cudaGraphExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphAddExternalSemaphoresWaitNode
cudaImportExternalSemaphore
cudaSignalExternalSemaphoresAsync
cudaWaitExternalSemaphoresAsync
cudaGraphCreate
cudaGraphDestroyNode
cudaGraphAddEventRecordNode
cudaGraphAddEventWaitNode
cudaGraphAddChildGraphNode
cudaGraphAddEmptyNode
cudaGraphAddKernelNode
cudaGraphAddMemcpyNode
cudaGraphAddMemsetNode
- cuda.cudart.cudaGraphExternalSemaphoresSignalNodeGetParams(hNode)¶
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 cudaGraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- params_outcudaExternalSemaphoreSignalNodeParams
Pointer to return the parameters
- cuda.cudart.cudaGraphExternalSemaphoresSignalNodeSetParams(hNode, cudaExternalSemaphoreSignalNodeParams nodeParams: cudaExternalSemaphoreSignalNodeParams)¶
Sets an external semaphore signal node’s parameters.
Sets the parameters of an external semaphore signal node hNode to nodeParams.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- nodeParamscudaExternalSemaphoreSignalNodeParams
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddExternalSemaphoresWaitNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaExternalSemaphoreWaitNodeParams nodeParams: cudaExternalSemaphoreWaitNodeParams)¶
Creates an external semaphore wait node and adds it to a graph.
Creates a new external semaphore wait node and adds it to graph 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 pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- nodeParamscudaExternalSemaphoreWaitNodeParams
Parameters for the node
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
cudaGraphExternalSemaphoresWaitNodeGetParams
cudaGraphExternalSemaphoresWaitNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphAddExternalSemaphoresSignalNode
cudaImportExternalSemaphore
cudaSignalExternalSemaphoresAsync
cudaWaitExternalSemaphoresAsync
cudaGraphCreate
cudaGraphDestroyNode
cudaGraphAddEventRecordNode
cudaGraphAddEventWaitNode
cudaGraphAddChildGraphNode
cudaGraphAddEmptyNode
cudaGraphAddKernelNode
cudaGraphAddMemcpyNode
cudaGraphAddMemsetNode
- cuda.cudart.cudaGraphExternalSemaphoresWaitNodeGetParams(hNode)¶
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 cudaGraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- params_outcudaExternalSemaphoreWaitNodeParams
Pointer to return the parameters
- cuda.cudart.cudaGraphExternalSemaphoresWaitNodeSetParams(hNode, cudaExternalSemaphoreWaitNodeParams nodeParams: cudaExternalSemaphoreWaitNodeParams)¶
Sets an external semaphore wait node’s parameters.
Sets the parameters of an external semaphore wait node hNode to nodeParams.
- Parameters
- hNodeCUgraphNode or cudaGraphNode_t
Node to set the parameters for
- nodeParamscudaExternalSemaphoreWaitNodeParams
Parameters to copy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphAddMemAllocNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, cudaMemAllocNodeParams nodeParams: cudaMemAllocNodeParams)¶
Creates an allocation node and adds it to a graph.
Creates a new allocation node and adds it to graph with numDependencies dependencies specified via pDependencies 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. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
If the allocation is freed in the same graph, by creating a free node using cudaGraphAddMemFreeNode, 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: - passing the allocation to cudaMemFreeAsync or cudaMemFree; - launching a graph with a free node for that allocation; or - specifying cudaGraphInstantiateFlagAutoFreeOnLaunch during instantiation, which makes each launch behave as though it called cudaMemFreeAsync for every unfreed allocation.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- nodeParamscudaMemAllocNodeParams
Parameters for the node
- Returns
- cudaError_t
cudaSuccess cudaErrorCudartUnloading cudaErrorInitializationError cudaErrorNotSupported cudaErrorInvalidValue cudaErrorOutOfMemory
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
cudaGraphAddMemFreeNode
cudaGraphMemAllocNodeGetParams
cudaDeviceGraphMemTrim
cudaDeviceGetGraphMemAttribute
cudaDeviceSetGraphMemAttribute
cudaMallocAsync
cudaFreeAsync
cudaGraphCreate
cudaGraphDestroyNode
cudaGraphAddChildGraphNode
cudaGraphAddEmptyNode
cudaGraphAddEventRecordNode
cudaGraphAddEventWaitNode
cudaGraphAddExternalSemaphoresSignalNode
cudaGraphAddExternalSemaphoresWaitNode
cudaGraphAddKernelNode
cudaGraphAddMemcpyNode
cudaGraphAddMemsetNode
- cuda.cudart.cudaGraphMemAllocNodeGetParams(node)¶
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
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- params_outcudaMemAllocNodeParams
Pointer to return the parameters
- cuda.cudart.cudaGraphAddMemFreeNode(graph, pDependencies: List[cudaGraphNode_t], size_t numDependencies, dptr)¶
Creates a memory free node and adds it to a graph.
Creates a new memory free node and adds it to graph with numDependencies dependencies specified via pDependencies and address specified in dptr. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. pDependencies may not have any duplicate entries. A handle to the new node will be returned in pGraphNode.
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
- graphCUgraph or cudaGraph_t
Graph to which to add the node
- pDependenciesList[cudaGraphNode_t]
Dependencies of the node
- numDependenciessize_t
Number of dependencies
- dptrAny
Address of memory to free
- Returns
- cudaError_t
cudaSuccess cudaErrorCudartUnloading cudaErrorInitializationError cudaErrorNotSupported cudaErrorInvalidValue cudaErrorOutOfMemory
- pGraphNodecudaGraphNode_t
Returns newly created node
See also
cudaGraphAddMemAllocNode
cudaGraphMemFreeNodeGetParams
cudaDeviceGraphMemTrim
cudaDeviceGetGraphMemAttribute
cudaDeviceSetGraphMemAttribute
cudaMallocAsync
cudaFreeAsync
cudaGraphCreate
cudaGraphDestroyNode
cudaGraphAddChildGraphNode
cudaGraphAddEmptyNode
cudaGraphAddEventRecordNode
cudaGraphAddEventWaitNode
cudaGraphAddExternalSemaphoresSignalNode
cudaGraphAddExternalSemaphoresWaitNode
cudaGraphAddKernelNode
cudaGraphAddMemcpyNode
cudaGraphAddMemsetNode
- cuda.cudart.cudaGraphMemFreeNodeGetParams(node)¶
Returns a memory free node’s parameters.
Returns the address of a memory free node hNode in dptr_out.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to get the parameters for
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- dptr_outint
Pointer to return the device address
- cuda.cudart.cudaDeviceGraphMemTrim(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
- deviceint
The device for which cached memory should be freed.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaDeviceGetGraphMemAttribute(int device, attr: cudaGraphMemAttributeType)¶
Query asynchronous allocation attributes related to graphs.
Valid attributes are:
cudaGraphMemAttrUsedMemCurrent: Amount of memory, in bytes, currently
associated with graphs - cudaGraphMemAttrUsedMemHigh: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero. - cudaGraphMemAttrReservedMemCurrent: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. - cudaGraphMemAttrReservedMemHigh: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters
- deviceint
Specifies the scope of the query
- attrcudaGraphMemAttributeType
attribute to get
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice
- valueAny
retrieved value
- cuda.cudart.cudaDeviceSetGraphMemAttribute(int device, attr: cudaGraphMemAttributeType, value)¶
Set asynchronous allocation attributes related to graphs.
Valid attributes are:
cudaGraphMemAttrUsedMemHigh: High watermark of memory, in bytes,
associated with graphs since the last time it was reset. High watermark can only be reset to zero. - cudaGraphMemAttrReservedMemHigh: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
- Parameters
- deviceint
Specifies the scope of the query
- attrcudaGraphMemAttributeType
attribute to get
- valueAny
pointer to value to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidDevice
- None
None
- cuda.cudart.cudaGraphClone(originalGraph)¶
Clones a graph.
This function creates a copy of originalGraph and returns it in pGraphClone. 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
- originalGraphCUgraph or cudaGraph_t
Graph to clone
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorMemoryAllocation
- pGraphClonecudaGraph_t
Returns newly created cloned graph
See also
- cuda.cudart.cudaGraphNodeFindInClone(originalNode, clonedGraph)¶
Finds a cloned version of a node.
This function returns the node in clonedGraph corresponding to originalNode in the original graph.
clonedGraph must have been cloned from originalGraph via cudaGraphClone. originalNode must have been in originalGraph at the time of the call to cudaGraphClone, and the corresponding cloned node in clonedGraph must not have been removed. The cloned node is then returned via pClonedNode.
- Parameters
- originalNodeCUgraphNode or cudaGraphNode_t
Handle to the original node
- clonedGraphCUgraph or cudaGraph_t
Cloned graph to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pNodecudaGraphNode_t
Returns handle to the cloned node
See also
- cuda.cudart.cudaGraphNodeGetType(node)¶
Returns a node’s type.
Returns the node type of node in pType.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pTypecudaGraphNodeType
Pointer to return the node type
See also
- cuda.cudart.cudaGraphGetNodes(graph, size_t numNodes=0)¶
Returns a graph’s nodes.
Returns a list of graph’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
- graphCUgraph or cudaGraph_t
Graph to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- nodesList[cudaGraphNode_t]
Pointer to return the nodes
- numNodesint
See description
- cuda.cudart.cudaGraphGetRootNodes(graph, size_t pNumRootNodes=0)¶
Returns a graph’s root nodes.
Returns a list of graph’s root nodes. pRootNodes may be NULL, in which case this function will return the number of root nodes in pNumRootNodes. Otherwise, pNumRootNodes entries will be filled in. If pNumRootNodes is higher than the actual number of root nodes, the remaining entries in pRootNodes will be set to NULL, and the number of nodes actually obtained will be returned in pNumRootNodes.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pRootNodesList[cudaGraphNode_t]
Pointer to return the root nodes
- pNumRootNodesint
See description
- cuda.cudart.cudaGraphGetEdges(graph, size_t numEdges=0)¶
Returns a graph’s dependency edges.
Returns a list of graph’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
- graphCUgraph or cudaGraph_t
Graph to get the edges from
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- fromList[cudaGraphNode_t]
Location to return edge endpoints
- toList[cudaGraphNode_t]
Location to return edge endpoints
- numEdgesint
See description
- cuda.cudart.cudaGraphNodeGetDependencies(node, size_t pNumDependencies=0)¶
Returns a node’s dependencies.
Returns a list of node’s dependencies. pDependencies may be NULL, in which case this function will return the number of dependencies in pNumDependencies. Otherwise, pNumDependencies entries will be filled in. If pNumDependencies is higher than the actual number of dependencies, the remaining entries in pDependencies will be set to NULL, and the number of nodes actually obtained will be returned in pNumDependencies.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pDependenciesList[cudaGraphNode_t]
Pointer to return the dependencies
- pNumDependenciesint
See description
- cuda.cudart.cudaGraphNodeGetDependentNodes(node, size_t pNumDependentNodes=0)¶
Returns a node’s dependent nodes.
Returns a list of node’s dependent nodes. pDependentNodes may be NULL, in which case this function will return the number of dependent nodes in pNumDependentNodes. Otherwise, pNumDependentNodes entries will be filled in. If pNumDependentNodes is higher than the actual number of dependent nodes, the remaining entries in pDependentNodes will be set to NULL, and the number of nodes actually obtained will be returned in pNumDependentNodes.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to query
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pDependentNodesList[cudaGraphNode_t]
Pointer to return the dependent nodes
- pNumDependentNodesint
See description
- cuda.cudart.cudaGraphAddDependencies(graph, from_: List[cudaGraphNode_t], to: List[cudaGraphNode_t], size_t numDependencies)¶
Adds dependency edges to a graph.
The number of dependencies to be added is defined by numDependencies Elements in pFrom and pTo at corresponding indices define a dependency. Each node in pFrom and pTo must belong to graph.
If numDependencies is 0, elements in pFrom and pTo will be ignored. Specifying an existing dependency will return an error.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to which dependencies are added
- from_List[cudaGraphNode_t]
Array of nodes that provide the dependencies
- toList[cudaGraphNode_t]
Array of dependent nodes
- numDependenciessize_t
Number of dependencies to be added
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphRemoveDependencies(graph, from_: List[cudaGraphNode_t], to: List[cudaGraphNode_t], size_t numDependencies)¶
Removes dependency edges from a graph.
The number of pDependencies to be removed is defined by numDependencies. Elements in pFrom and pTo at corresponding indices define a dependency. Each node in pFrom and pTo must belong to graph.
If numDependencies is 0, elements in pFrom and pTo will be ignored. Specifying a non-existing dependency will return an error.
- Parameters
- graphCUgraph or cudaGraph_t
Graph from which to remove dependencies
- from_List[cudaGraphNode_t]
Array of nodes that provide the dependencies
- toList[cudaGraphNode_t]
Array of dependent nodes
- numDependenciessize_t
Number of dependencies to be removed
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphDestroyNode(node)¶
Remove a node from the graph.
Removes node from its graph. This operation also severs any dependencies of other nodes on node and vice versa.
Dependencies cannot be removed from graphs which contain allocation or free nodes. Any attempt to do so will return an error.
- Parameters
- nodeCUgraphNode or cudaGraphNode_t
Node to remove
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphInstantiate(graph, char *pLogBuffer, size_t bufferSize)¶
Creates an executable graph from a graph.
Instantiates graph 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 pGraphExec.
If there are any errors, diagnostic information may be returned in pErrorNode and pLogBuffer. 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
- graphCUgraph or cudaGraph_t
Graph to instantiate
- pLogBufferbytes
A character buffer to store diagnostic messages
- bufferSizesize_t
Size of the log buffer in bytes
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphExeccudaGraphExec_t
Returns instantiated graph
- pErrorNodecudaGraphNode_t
In case of an instantiation error, this may be modified to indicate a node contributing to the error
- cuda.cudart.cudaGraphInstantiateWithFlags(graph, unsigned long long flags)¶
Creates an executable graph from a graph.
Instantiates graph 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 pGraphExec.
The flags parameter controls the behavior of instantiation and subsequent graph launches. Valid flags are:
cudaGraphInstantiateFlagAutoFreeOnLaunch, which configures a graph
containing memory allocation nodes to automatically free any unfreed memory allocations before the graph is relaunched.
If graph 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 cudaGraphExecDestroy will result in an error.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to instantiate
- flagsunsigned long long
Flags to control instantiation. See CUgraphInstantiate_flags.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- pGraphExeccudaGraphExec_t
Returns instantiated graph
- cuda.cudart.cudaGraphExecKernelNodeSetParams(hGraphExec, node, cudaKernelNodeParams pNodeParams: cudaKernelNodeParams)¶
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 node in the non-executable graph, from which the executable graph was instantiated.
node 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 only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. node is also not modified by this call.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
kernel node from the graph from which graphExec was instantiated
- pNodeParamscudaKernelNodeParams
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddKernelNode
cudaGraphKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecMemcpyNodeSetParams(hGraphExec, node, cudaMemcpy3DParms pNodeParams: cudaMemcpy3DParms)¶
Sets the parameters for a memcpy node in the given graphExec.
Updates the work represented by node in hGraphExec as though node had contained pNodeParams at instantiation. node must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from node are ignored.
The source and destination memory in pNodeParams 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 pNodeParams 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. node is also not modified by this call.
Returns cudaErrorInvalidValue if the memory operands’ mappings changed or either the original or new memory operands are multidimensional.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
Memcpy node from the graph which was used to instantiate graphExec
- pNodeParamscudaMemcpy3DParms
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddMemcpyNode
cudaGraphMemcpyNodeSetParams
cudaGraphExecMemcpyNodeSetParamsToSymbol
cudaGraphExecMemcpyNodeSetParamsFromSymbol
cudaGraphExecMemcpyNodeSetParams1D
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecMemcpyNodeSetParams1D(hGraphExec, node, dst, src, size_t count, kind: cudaMemcpyKind)¶
Sets the parameters for a memcpy node in the given graphExec to perform a 1-dimensional copy.
Updates the work represented by node in hGraphExec as though node had contained the given params at instantiation. node must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from node are ignored.
src and dst must be allocated from the same contexts as the original source and destination memory. The instantiation-time memory operands 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. node is also not modified by this call.
Returns cudaErrorInvalidValue if the memory operands’ mappings changed or the original memory operands are multidimensional.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
Memcpy node from the graph which was used to instantiate graphExec
- dstAny
Destination memory address
- srcAny
Source memory address
- countsize_t
Size in bytes to copy
- kindcudaMemcpyKind
Type of transfer
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddMemcpyNode
cudaGraphAddMemcpyNode1D
cudaGraphMemcpyNodeSetParams
cudaGraphMemcpyNodeSetParams1D
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecMemsetNodeSetParams(hGraphExec, node, cudaMemsetParams pNodeParams: cudaMemsetParams)¶
Sets the parameters for a memset node in the given graphExec.
Updates the work represented by node in hGraphExec as though node had contained pNodeParams at instantiation. node must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from node are ignored.
The destination memory in pNodeParams must be allocated from the same context as the original destination memory. Both the instantiation-time memory operand and the memory operand in pNodeParams 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. node is also not modified by this call.
Returns cudaErrorInvalidValue if the memory operand’s mappings changed or either the original or new memory operand are multidimensional.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
Memset node from the graph which was used to instantiate graphExec
- pNodeParamscudaMemsetParams
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddMemsetNode
cudaGraphMemsetNodeSetParams
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecHostNodeSetParams(hGraphExec, node, cudaHostNodeParams pNodeParams: cudaHostNodeParams)¶
Sets the parameters for a host node in the given graphExec.
Updates the work represented by node in hGraphExec as though node had contained pNodeParams at instantiation. node must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from node are ignored.
The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. node is also not modified by this call.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
Host node from the graph which was used to instantiate graphExec
- pNodeParamscudaHostNodeParams
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddHostNode
cudaGraphHostNodeSetParams
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecChildGraphNodeSetParams(hGraphExec, node, childGraph)¶
Updates node parameters in the child graph node in the given graphExec.
Updates the work represented by node in hGraphExec as though the nodes contained in node’s graph had the parameters contained in childGraph’s nodes at instantiation. node must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from node are ignored.
The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. node 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 node. See cudaGraphExecUpdate() 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
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- nodeCUgraphNode or cudaGraphNode_t
Host node from the graph which was used to instantiate graphExec
- childGraphCUgraph or cudaGraph_t
The graph supplying the updated parameters
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddChildGraphNode
cudaGraphChildGraphNodeGetGraph
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecEventRecordNodeSetEvent(hGraphExec, hNode, 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
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
Event record node from the graph from which graphExec was instantiated
- eventCUevent or cudaEvent_t
Updated event to use
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddEventRecordNode
cudaGraphEventRecordNodeGetEvent
cudaGraphEventWaitNodeSetEvent
cudaEventRecordWithFlags
cudaStreamWaitEvent
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecEventWaitNodeSetEvent(hGraphExec, hNode, 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
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
Event wait node from the graph from which graphExec was instantiated
- eventCUevent or cudaEvent_t
Updated event to use
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddEventWaitNode
cudaGraphEventWaitNodeGetEvent
cudaGraphEventRecordNodeSetEvent
cudaEventRecordWithFlags
cudaStreamWaitEvent
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecExternalSemaphoresSignalNodeSetParams(hGraphExec, hNode, cudaExternalSemaphoreSignalNodeParams nodeParams: cudaExternalSemaphoreSignalNodeParams)¶
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
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
semaphore signal node from the graph from which graphExec was instantiated
- nodeParamscudaExternalSemaphoreSignalNodeParams
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddExternalSemaphoresSignalNode
cudaImportExternalSemaphore
cudaSignalExternalSemaphoresAsync
cudaWaitExternalSemaphoresAsync
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresWaitNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphExecExternalSemaphoresWaitNodeSetParams(hGraphExec, hNode, cudaExternalSemaphoreWaitNodeParams nodeParams: cudaExternalSemaphoreWaitNodeParams)¶
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
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
semaphore wait node from the graph from which graphExec was instantiated
- nodeParamscudaExternalSemaphoreWaitNodeParams
Updated Parameters to set
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
cudaGraphAddExternalSemaphoresWaitNode
cudaImportExternalSemaphore
cudaSignalExternalSemaphoresAsync
cudaWaitExternalSemaphoresAsync
cudaGraphExecKernelNodeSetParams
cudaGraphExecMemcpyNodeSetParams
cudaGraphExecMemsetNodeSetParams
cudaGraphExecHostNodeSetParams
cudaGraphExecChildGraphNodeSetParams
cudaGraphExecEventRecordNodeSetEvent
cudaGraphExecEventWaitNodeSetEvent
cudaGraphExecExternalSemaphoresSignalNodeSetParams
cudaGraphExecUpdate
cudaGraphInstantiate
- cuda.cudart.cudaGraphNodeSetEnabled(hGraphExec, hNode, unsigned int isEnabled)¶
Enables or disables the specified node in the given graphExec.
Sets hNode to be either enabled or disabled. Disabled nodes are functionally equivalent to empty nodes until they are reenabled. Existing node parameters are not affected by disabling/enabling the node.
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.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
Node from the graph from which graphExec was instantiated
- isEnabledunsigned int
Node is enabled if != 0, otherwise the node is disabled
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
Notes
Currently only kernel nodes are supported.
- cuda.cudart.cudaGraphNodeGetEnabled(hGraphExec, hNode)¶
Query whether a node in the given graphExec is enabled.
Sets isEnabled to 1 if hNode is enabled, or 0 if hNode is disabled.
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.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The executable graph in which to set the specified node
- hNodeCUgraphNode or cudaGraphNode_t
Node from the graph from which graphExec was instantiated
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- isEnabledunsigned int
Location to return the enabled status of the node
Notes
Currently only kernel nodes are supported.
- cuda.cudart.cudaGraphExecUpdate(hGraphExec, hGraph)¶
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. - A cooperative node cannot be updated to a non-cooperative node, and vice-versa. - 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.
Note: The API may add further restrictions in future releases. The return code should always be checked.
cudaGraphExecUpdate sets updateResult_out to cudaGraphExecUpdateErrorTopologyChanged 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.
cudaGraphExecUpdate sets updateResult_out to: - cudaGraphExecUpdateError if passed an invalid value. - cudaGraphExecUpdateErrorTopologyChanged if the graph topology changed - cudaGraphExecUpdateErrorNodeTypeChanged if the type of a node changed, in which case hErrorNode_out is set to the node from hGraph. - cudaGraphExecUpdateErrorFunctionChanged if the function of a kernel node changed (CUDA driver < 11.2) - cudaGraphExecUpdateErrorUnsupportedFunctionChange if the func field of a kernel changed in an unsupported way(see note above), in which case hErrorNode_out is set to the node from hGraph - cudaGraphExecUpdateErrorParametersChanged if any parameters to a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph - cudaGraphExecUpdateErrorAttributesChanged if any attributes of a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph - cudaGraphExecUpdateErrorNotSupported if something about a node is unsupported, like the node’s type or configuration, in which case hErrorNode_out is set to the node from hGraph
If updateResult_out isn’t set in one of the situations described above, the update check passes and cudaGraphExecUpdate updates hGraphExec to match the contents of hGraph. If an error happens during the update, updateResult_out will be set to cudaGraphExecUpdateError; otherwise, updateResult_out is set to cudaGraphExecUpdateSuccess.
cudaGraphExecUpdate returns cudaSuccess when the updated was performed successfully. It returns cudaErrorGraphExecUpdateFailure if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
- Parameters
- hGraphExecCUgraphExec or cudaGraphExec_t
The instantiated graph to be updated
- hGraphAny
The graph containing the updated parameters
- Returns
- cudaError_t
cudaSuccess cudaErrorGraphExecUpdateFailure
- hErrorNode_outcudaGraphNode_t
The node which caused the permissibility check to forbid the update, if any
- updateResult_outcudaGraphExecUpdateResult
Whether the graph update was permitted. If was forbidden, the reason why
See also
- cuda.cudart.cudaGraphUpload(graphExec, stream)¶
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 graphExec.
- Parameters
- hGraphExecAny
Executable graph to upload
- hStreamCUstream or cudaStream_t
Stream in which to upload the graph
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphLaunch(graphExec, stream)¶
Launches an executable graph in a stream.
Executes graphExec in stream. Only one instance of graphExec may be executing at a time. Each launch is ordered behind both any previous work in stream and any previous launches of graphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.
If any allocations created by graphExec remain unfreed (from a previous launch) and graphExec was not instantiated with cudaGraphInstantiateFlagAutoFreeOnLaunch, the launch will fail with cudaErrorInvalidValue.
- Parameters
- graphExecAny
Executable graph to launch
- streamCUstream or cudaStream_t
Stream in which to launch the graph
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphExecDestroy(graphExec)¶
Destroys an executable graph.
Destroys the executable graph specified by graphExec.
- Parameters
- graphExecAny
Executable graph to destroy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphDestroy(graph)¶
Destroys a graph.
Destroys the graph specified by graph, as well as all of its nodes.
- Parameters
- graphCUgraph or cudaGraph_t
Graph to destroy
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
See also
- cuda.cudart.cudaGraphDebugDotPrint(graph, char *path, unsigned int flags)¶
Write a DOT file describing graph structure.
Using the provided graph, 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
- graphCUgraph or cudaGraph_t
The graph to create a DOT file from
- pathbytes
The path to write the DOT file to
- flagsunsigned int
Flags from cudaGraphDebugDotFlags for specifying which additional node information to write
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorOperatingSystem
- None
None
- cuda.cudart.cudaUserObjectCreate(ptr, destroy, unsigned int initialRefcount, unsigned 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
- ptrAny
The pointer to pass to the destroy function
- destroyAny
Callback to free the user object when it is no longer in use
- initialRefcountunsigned int
The initial refcount to create the object with, typically 1. The initial references are owned by the calling thread.
- flagsunsigned int
Currently it is required to pass cudaUserObjectNoDestructorSync, 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.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- object_outcudaUserObject_t
Location to return the user object handle
- cuda.cudart.cudaUserObjectRetain(object, unsigned 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
- objectAny
The object to retain
- countunsigned int
The number of references to retain, typically 1. Must be nonzero and not larger than INT_MAX.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaUserObjectRelease(object, unsigned 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
- objectAny
The object to release
- countunsigned int
The number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphRetainUserObject(graph, object, unsigned int count, unsigned 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
- graphCUgraph or cudaGraph_t
The graph to associate the reference with
- objectAny
The user object to retain a reference for
- countunsigned int
The number of references to add to the graph, typically 1. Must be nonzero and not larger than INT_MAX.
- flagsunsigned int
The optional flag cudaGraphUserObjectMove transfers references from the calling thread, rather than create new references. Pass 0 to create new references.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
- cuda.cudart.cudaGraphReleaseUserObject(graph, object, unsigned 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
- graphCUgraph or cudaGraph_t
The graph that will release the reference
- objectAny
The user object to release a reference for
- countunsigned int
The number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue
- None
None
Driver Entry Point Access¶
This section describes the driver entry point access functions of CUDA runtime application programming interface.
- cuda.cudart.cudaGetDriverEntryPoint(char *symbol, unsigned long long flags)¶
Returns the requested driver API function pointer.
Returns in **funcPtr the address of the CUDA driver function for the requested flags.
For a requested driver symbol, if the CUDA version in which the driver symbol was introduced is less than or equal to the CUDA runtime version, the API will return the function pointer to the corresponding versioned driver 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 cudaErrorSymbolNotFound if the requested driver function is not supported on the platform, no ABI compatible driver function exists for the CUDA runtime version or if the driver symbol is invalid.
The requested flags can be: - cudaEnableDefault: This is the default mode. This is equivalent to cudaEnablePerThreadDefaultStream if the code is compiled with –default-stream per-thread compilation flag or the macro CUDA_API_PER_THREAD_DEFAULT_STREAM is defined; cudaEnableLegacyStream otherwise. - cudaEnableLegacyStream: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions. - cudaEnablePerThreadDefaultStream: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.
- Parameters
- symbolbytes
The base name of the driver API function to look for. As an example, for the driver API cuMemAlloc_v2, symbol would be cuMemAlloc. Note that the API will use the CUDA runtime version to return the address to the most recent ABI compatible driver symbol, cuMemAlloc or cuMemAlloc_v2.
- flagsunsigned long long
Flags to specify search options.
- Returns
- cudaError_t
cudaSuccess cudaErrorInvalidValue cudaErrorNotSupported cudaErrorSymbolNotFound
- funcPtrint
Location to return the function pointer to the requested driver function
C++ API Routines¶
C++-style interface built on top of CUDA runtime API.
impl_private
This section describes the C++ high level API functions of the CUDA runtime application programming interface. To use these functions, your application needs to be compiled with the nvcc
compiler.
Interactions with the CUDA Driver API¶
This section describes the interactions between the CUDA Driver API and the CUDA Runtime API
Primary Contexts
There exists a one to one relationship between CUDA devices in the CUDA Runtime API and ::CUcontext s in the CUDA Driver API within a process. The specific context which the CUDA Runtime API uses for a device is called the device’s primary context. From the perspective of the CUDA Runtime API, a device and its primary context are synonymous.
Initialization and Tear-Down
CUDA Runtime API calls operate on the CUDA Driver API ::CUcontext which is current to to the calling host thread.
The function cudaSetDevice() makes the primary context for the specified device current to the calling thread by calling ::cuCtxSetCurrent(). The CUDA Runtime API will automatically initialize the primary context for a device at the first CUDA Runtime API call which requires an active context. If no ::CUcontext is current to the calling thread when a CUDA Runtime API call which requires an active context is made, then the primary context for a device will be selected, made current to the calling thread, and initialized. The context which the CUDA Runtime API initializes will be initialized using the parameters specified by the CUDA Runtime API functions cudaSetDeviceFlags(), ::cudaD3D9SetDirect3DDevice(), ::cudaD3D10SetDirect3DDevice(), ::cudaD3D11SetDirect3DDevice(), cudaGLSetGLDevice(), and cudaVDPAUSetVDPAUDevice(). Note that these functions will fail with ::cudaErrorSetOnActiveProcess if they are called when the primary context for the specified device has already been initialized. (or if the current device has already been initialized, in the case of cudaSetDeviceFlags()). Primary contexts will remain active until they are explicitly deinitialized using cudaDeviceReset(). The function cudaDeviceReset() will deinitialize the primary context for the calling thread’s current device immediately. The context will remain current to all of the threads that it was current to. The next CUDA Runtime API call on any thread which requires an active context will trigger the reinitialization of that device’s primary context. Note that primary contexts are shared resources. It is recommended that the primary context not be reset except just before exit or to recover from an unspecified launch failure.
Context Interoperability
Note that the use of multiple ::CUcontext s per device within a single process will substantially degrade performance and is strongly discouraged. Instead, it is highly recommended that the implicit one-to-one device-to-context mapping for the process provided by the CUDA Runtime API be used. If a non-primary ::CUcontext created by the CUDA Driver API is current to a thread then the CUDA Runtime API calls to that thread will operate on that ::CUcontext, with some exceptions listed below. Interoperability between data types is discussed in the following sections. The function cudaPointerGetAttributes() will return the error ::cudaErrorIncompatibleDriverContext if the pointer being queried was allocated by a non-primary context. The function cudaDeviceEnablePeerAccess() and the rest of the peer access API may not be called when a non-primary ::CUcontext is current.
To use the pointer query and peer access APIs with a context created using the CUDA Driver API, it is necessary that the CUDA Driver API be used to access these features.
All CUDA Runtime API state (e.g, global variables’ addresses and values) travels with its underlying ::CUcontext. In particular, if a ::CUcontext is moved from one thread to another then all CUDA Runtime API state will move to that thread as well. Please note that attaching to legacy contexts (those with a version of 3010 as returned by ::cuCtxGetApiVersion()) is not possible. The CUDA Runtime will return ::cudaErrorIncompatibleDriverContext in such cases.
Interactions between CUstream and cudaStream_t
The types ::CUstream and cudaStream_t are identical and may be used interchangeably.
Interactions between CUevent and cudaEvent_t
The types ::CUevent and cudaEvent_t are identical and may be used interchangeably.
Interactions between CUarray and cudaArray_t
The types ::CUarray and struct ::cudaArray * represent the same data type and may be used interchangeably by casting the two types between each other. In order to use a ::CUarray in a CUDA Runtime API function which takes a struct ::cudaArray *, it is necessary to explicitly cast the ::CUarray to a struct ::cudaArray *. In order to use a struct ::cudaArray * in a CUDA Driver API function which takes a ::CUarray, it is necessary to explicitly cast the struct ::cudaArray * to a ::CUarray .
Interactions between CUgraphicsResource and cudaGraphicsResource_t
The types ::CUgraphicsResource and cudaGraphicsResource_t represent the same data type and may be used interchangeably by casting the two types between each other. In order to use a ::CUgraphicsResource in a CUDA Runtime API function which takes a cudaGraphicsResource_t, it is necessary to explicitly cast the ::CUgraphicsResource to a cudaGraphicsResource_t. In order to use a cudaGraphicsResource_t in a CUDA Driver API function which takes a ::CUgraphicsResource, it is necessary to explicitly cast the cudaGraphicsResource_t to a ::CUgraphicsResource.
Interactions between CUtexObject * and cudaTextureObject_t
The types ::CUtexObject * and cudaTextureObject_t represent the same data type and may be used interchangeably by casting the two types between each other. In order to use a ::CUtexObject * in a CUDA Runtime API function which takes a cudaTextureObject_t, it is necessary to explicitly cast the ::CUtexObject * to a cudaTextureObject_t. In order to use a cudaTextureObject_t in a CUDA Driver API function which takes a ::CUtexObject *, it is necessary to explicitly cast the cudaTextureObject_t to a ::CUtexObject *.
Interactions between CUsurfObject * and cudaSurfaceObject_t
The types ::CUsurfObject * and cudaSurfaceObject_t represent the same data type and may be used interchangeably by casting the two types between each other. In order to use a ::CUsurfObject * in a CUDA Runtime API function which takes a ::cudaSurfaceObjec_t, it is necessary to explicitly cast the ::CUsurfObject * to a cudaSurfaceObject_t. In order to use a cudaSurfaceObject_t in a CUDA Driver API function which takes a ::CUsurfObject *, it is necessary to explicitly cast the cudaSurfaceObject_t to a ::CUsurfObject *.
Interactions between CUfunction and cudaFunction_t
The types ::CUfunction and cudaFunction_t represent the same data type and may be used interchangeably by casting the two types between each other. In order to use a cudaFunction_t in a CUDA Driver API function which takes a ::CUfunction, it is necessary to explicitly cast the cudaFunction_t to a ::CUfunction.
Data types used by CUDA Runtime¶
- enum cuda.cudart.cudaEglFrameType(value)¶
CUDA EglFrame type - array or pointer
- Member Type
int
Valid values are as follows:
- cudaEglFrameTypeArray¶
- cudaEglFrameTypePitch¶
- enum cuda.cudart.cudaEglResourceLocationFlags(value)¶
Resource location flags- sysmem or vidmem For CUDA context on iGPU, since video and system memory are equivalent - these flags will not have an effect on the execution. For CUDA context on dGPU, applications can use the flag cudaEglResourceLocationFlags to give a hint about the desired location. cudaEglResourceLocationSysmem - the frame data is made resident on the system memory to be accessed by CUDA. cudaEglResourceLocationVidmem - the frame data is made resident on the dedicated video memory to be accessed by CUDA. There may be an additional latency due to new allocation and data migration, if the frame is produced on a different memory.
- Member Type
int
Valid values are as follows:
- cudaEglResourceLocationSysmem¶
- cudaEglResourceLocationVidmem¶
- enum cuda.cudart.cudaEglColorFormat(value)¶
CUDA EGL Color Format - The different planar and multiplanar formats currently supported for CUDA_EGL interops.
- Member Type
int
Valid values are as follows:
- cudaEglColorFormatYUV420Planar¶
- cudaEglColorFormatYUV420SemiPlanar¶
- cudaEglColorFormatYUV422Planar¶
- cudaEglColorFormatYUV422SemiPlanar¶
- cudaEglColorFormatARGB¶
- cudaEglColorFormatRGBA¶
- cudaEglColorFormatL¶
- cudaEglColorFormatR¶
- cudaEglColorFormatYUV444Planar¶
- cudaEglColorFormatYUV444SemiPlanar¶
- cudaEglColorFormatYUYV422¶
- cudaEglColorFormatUYVY422¶
- cudaEglColorFormatABGR¶
- cudaEglColorFormatBGRA¶
- cudaEglColorFormatA¶
- cudaEglColorFormatRG¶
- cudaEglColorFormatAYUV¶
- cudaEglColorFormatYVU444SemiPlanar¶
- cudaEglColorFormatYVU422SemiPlanar¶
- cudaEglColorFormatYVU420SemiPlanar¶
- cudaEglColorFormatY10V10U10_444SemiPlanar¶
- cudaEglColorFormatY10V10U10_420SemiPlanar¶
- cudaEglColorFormatY12V12U12_444SemiPlanar¶
- cudaEglColorFormatY12V12U12_420SemiPlanar¶
- cudaEglColorFormatVYUY_ER¶
- cudaEglColorFormatUYVY_ER¶
- cudaEglColorFormatYUYV_ER¶
- cudaEglColorFormatYVYU_ER¶
- cudaEglColorFormatYUVA_ER¶
- cudaEglColorFormatAYUV_ER¶
- cudaEglColorFormatYUV444Planar_ER¶
- cudaEglColorFormatYUV422Planar_ER¶
- cudaEglColorFormatYUV420Planar_ER¶
- cudaEglColorFormatYUV444SemiPlanar_ER¶
- cudaEglColorFormatYUV422SemiPlanar_ER¶
- cudaEglColorFormatYUV420SemiPlanar_ER¶
- cudaEglColorFormatYVU444Planar_ER¶
- cudaEglColorFormatYVU422Planar_ER¶
- cudaEglColorFormatYVU420Planar_ER¶
- cudaEglColorFormatYVU444SemiPlanar_ER¶
- cudaEglColorFormatYVU422SemiPlanar_ER¶
- cudaEglColorFormatYVU420SemiPlanar_ER¶
- cudaEglColorFormatBayerRGGB¶
- cudaEglColorFormatBayerBGGR¶
- cudaEglColorFormatBayerGRBG¶
- cudaEglColorFormatBayerGBRG¶
- cudaEglColorFormatBayer10RGGB¶
- cudaEglColorFormatBayer10BGGR¶
- cudaEglColorFormatBayer10GRBG¶
- cudaEglColorFormatBayer10GBRG¶
- cudaEglColorFormatBayer12RGGB¶
- cudaEglColorFormatBayer12BGGR¶
- cudaEglColorFormatBayer12GRBG¶
- cudaEglColorFormatBayer12GBRG¶
- cudaEglColorFormatBayer14RGGB¶
- cudaEglColorFormatBayer14BGGR¶
- cudaEglColorFormatBayer14GRBG¶
- cudaEglColorFormatBayer14GBRG¶
- cudaEglColorFormatBayer20RGGB¶
- cudaEglColorFormatBayer20BGGR¶
- cudaEglColorFormatBayer20GRBG¶
- cudaEglColorFormatBayer20GBRG¶
- cudaEglColorFormatYVU444Planar¶
- cudaEglColorFormatYVU422Planar¶
- cudaEglColorFormatYVU420Planar¶
- cudaEglColorFormatBayerIspRGGB¶
- cudaEglColorFormatBayerIspBGGR¶
- cudaEglColorFormatBayerIspGRBG¶
- cudaEglColorFormatBayerIspGBRG¶
- cudaEglColorFormatBayerBCCR¶
- cudaEglColorFormatBayerRCCB¶
- cudaEglColorFormatBayerCRBC¶
- cudaEglColorFormatBayerCBRC¶
- cudaEglColorFormatBayer10CCCC¶
- cudaEglColorFormatBayer12BCCR¶
- cudaEglColorFormatBayer12RCCB¶
- cudaEglColorFormatBayer12CRBC¶
- cudaEglColorFormatBayer12CBRC¶
- cudaEglColorFormatBayer12CCCC¶
- cudaEglColorFormatY¶
- cudaEglColorFormatYUV420SemiPlanar_2020¶
- cudaEglColorFormatYVU420SemiPlanar_2020¶
- cudaEglColorFormatYUV420Planar_2020¶
- cudaEglColorFormatYVU420Planar_2020¶
- cudaEglColorFormatYUV420SemiPlanar_709¶
- cudaEglColorFormatYVU420SemiPlanar_709¶
- cudaEglColorFormatYUV420Planar_709¶
- cudaEglColorFormatYVU420Planar_709¶
- cudaEglColorFormatY10V10U10_420SemiPlanar_709¶
- cudaEglColorFormatY10V10U10_420SemiPlanar_2020¶
- cudaEglColorFormatY10V10U10_422SemiPlanar_2020¶
- cudaEglColorFormatY10V10U10_422SemiPlanar¶
- cudaEglColorFormatY10V10U10_422SemiPlanar_709¶
- cudaEglColorFormatY_ER¶
- cudaEglColorFormatY_709_ER¶
- cudaEglColorFormatY10_ER¶
- cudaEglColorFormatY10_709_ER¶
- cudaEglColorFormatY12_ER¶
- cudaEglColorFormatY12_709_ER¶
- cudaEglColorFormatYUVA¶
- cudaEglColorFormatYVYU¶
- cudaEglColorFormatVYUY¶
- cudaEglColorFormatY10V10U10_420SemiPlanar_ER¶
- cudaEglColorFormatY10V10U10_420SemiPlanar_709_ER¶
- cudaEglColorFormatY10V10U10_444SemiPlanar_ER¶
- cudaEglColorFormatY10V10U10_444SemiPlanar_709_ER¶
- cudaEglColorFormatY12V12U12_420SemiPlanar_ER¶
- cudaEglColorFormatY12V12U12_420SemiPlanar_709_ER¶
- cudaEglColorFormatY12V12U12_444SemiPlanar_ER¶
- cudaEglColorFormatY12V12U12_444SemiPlanar_709_ER¶
- class cuda.cudart.cudaEglPlaneDesc¶
CUDA EGL Plane Descriptor - structure defining each plane of a CUDA EGLFrame
- Attributes
- widthunsigned int
Width of plane
- heightunsigned int
Height of plane
- depthunsigned int
Depth of plane
- pitchunsigned int
Pitch of plane
- numChannelsunsigned int
Number of channels for the plane
- channelDesccudaChannelFormatDesc
Channel Format Descriptor
- reservedList[unsigned int]
Reserved for future use
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaEglFrame¶
CUDA EGLFrame Descriptor - structure defining one frame of EGL. Each frame may contain one or more planes depending on whether the surface is Multiplanar or not. Each plane of EGLFrame is represented by cudaEglPlaneDesc which is defined as: typedefstructcudaEglPlaneDesc_st unsignedintwidth; unsignedintheight; unsignedintdepth; unsignedintpitch; unsignedintnumChannels; structcudaChannelFormatDescchannelDesc; unsignedintreserved[4]; cudaEglPlaneDesc;
- Attributes
- frame_cudaEglFrame_cudaEglFrame_cudaEglFrame_st_frame_u
- planeDescList[cudaEglPlaneDesc]
CUDA EGL Plane Descriptor cudaEglPlaneDesc
- planeCountunsigned int
Number of planes
- frameTypecudaEglFrameType
Array or Pitch
- eglColorFormatcudaEglColorFormat
CUDA EGL Color Format
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaEglStreamConnection¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaArray_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaArray_const_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaMipmappedArray_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaMipmappedArray_const_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaHostFn_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.CUuuid¶
- Attributes
- bytesbytes
< CUDA definition of UUID
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaUUID_t¶
- Attributes
- bytesbytes
< CUDA definition of UUID
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaIpcEventHandle_t¶
CUDA IPC event handle
- Attributes
- reservedbytes
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaIpcMemHandle_t¶
CUDA IPC memory handle
- Attributes
- reservedbytes
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaStream_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaEvent_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaGraphicsResource_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaExternalMemory_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaExternalSemaphore_t(*args, **kwargs)¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaGraph_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaGraphNode_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaUserObject_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaFunction_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaMemPool_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaGraphExec_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaSurfaceObject_t¶
Methods
getPtr()
Get memory address of class instance
- class cuda.cudart.cudaTextureObject_t¶
Methods
getPtr()
Get memory address of class instance