Home > Cuda Driver > Cuda Driver Api Error Codes

Cuda Driver Api Error Codes


The returned bank configurations can be either: CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: shared memory bank width is four bytes. cudaErrorDevicesUnavailable This indicates that all CUDA devices are busy or unavailable at the current time. cudaErrorInvalidNormSetting This indicates that an attempt was made to read a non-float texture as a normalized float. cudaErrorSetOnActiveProcess This indicates that the user has called cudaSetDevice(), cudaSetValidDevices(), cudaSetDeviceFlags(), cudaD3D9SetDirect3DDevice(), cudaD3D10SetDirect3DDevice, cudaD3D11SetDirect3DDevice(), * or cudaVDPAUSetVDPAUDevice() after initializing the CUDA runtime by calling non-device management operations (allocating memory and launching navigate here

Functions CUresult cuFuncSetBlockShape ( CUfunctionhfunc, int x, int y, int z ) Sets the block-dimensions for the function. However, on low power devices like Tegra, it always defaults to CU_CTX_SCHED_BLOCKING_SYNC. You signed in with another tab or window. Note:Note that this function may also return error codes from previous, asynchronous launches. http://docs.nvidia.com/cuda/cuda-driver-api/

Cuda Runtime Api

CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH controls the maximum nesting depth of a grid at which a thread can safely call cudaDeviceSynchronize(). CUresultcuDeviceTotalMem ( size_t*bytes, CUdevicedev ) Returns the total amount of memory on the device. template device_vector(const command_queue &q, size_t n, const H *host = 0, mem_flags flags = MEM_READ_WRITE) : n(n) { (void)flags; if (n) { q.context().set_current(); CUdeviceptr ptr; cuda_check( cuMemAlloc(&ptr, n * sizeof(T)) ); Note:Note that this function may also return error codes from previous, asynchronous launches.

We recommend upgrading to the latest Safari, Google Chrome, or Firefox. cudaErrorInvalidKernelImage This indicates that the device kernel image is invalid. Error 700 could mean e.g. Cudaerrorlaunchoutofresources Requesting more shared memory per block than the device supports will trigger this error, as will requesting too many threads or blocks.

See Unified Addressing for additional details. Cuda Driver Api Vs Runtime Api CUresultcuParamSetTexRef ( CUfunctionhfunc, int texunit, CUtexrefhTexRef ) Adds a texture-reference to the function's argument list. cudaErrorInvalidDeviceFunction The requested device function does not exist or is not compiled for the proper device architecture. See also: cuCtxCreate, cuCtxDestroy, cuCtxDetach, cuCtxGetApiVersion, cuCtxGetCacheConfig, cuCtxGetDevice, cuCtxGetFlags, cuCtxGetLimit, cuCtxPopCurrent, cuCtxPushCurrent, cuCtxSetCacheConfig, cuCtxSetLimit, cuCtxSynchronize CUresult cuCtxDetach ( CUcontextctx ) Decrement a context's usage-count.

Note:Note that this function may also return error codes from previous, asynchronous launches. Cudeviceprimaryctxretain Note that access granted by this call is unidirectional and that in order to access memory from the current context in peerContext, a separate symmetric call to cuCtxEnablePeerAccess() is required. For example, it is valid for the API version to be 3020 while the driver version is 4020. See also: cuD3D11GetDevice CUresult cuGraphicsD3D11RegisterResource ( CUgraphicsResource*pCudaResource, ID3D11Resource*pD3DResource, unsigned int Flags ) Register a Direct3D 11 resource for access by CUDA.

Cuda Driver Api Vs Runtime Api

CUresultcuDeviceGetName ( char*name, int len, CUdevicedev ) Returns an identifer string for the device. http://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__CTX__DEPRECATED.html Parameters hfunc - Kernel to specify dimensions of x - X dimension y - Y dimension z - Z dimension Returns CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_HANDLE, CUDA_ERROR_INVALID_VALUE Deprecated DescriptionSpecifies the x, Cuda Runtime Api Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CU_CTX_SCHED_BLOCKING_SYNC. Cuda Error Code List See also: cuFuncSetBlockShape, cuFuncSetSharedSize, cuFuncGetAttribute, cuParamSetSize, cuParamSetf, cuParamSeti, cuParamSetv, cuLaunch, cuLaunchGridAsync, cuLaunchKernel CUresult cuLaunchGridAsync ( CUfunctionf, int grid_width, int grid_height, CUstreamhStream ) Launches a CUDA function.

Note:Note that this function may also return error codes from previous, asynchronous launches. check over here Note:Note that this function may also return error codes from previous, asynchronous launches. CUresultcuParamSeti ( CUfunctionhfunc, int offset, unsigned int value ) Adds an integer parameter to the function's argument list. cudaErrorInvalidDevicePointer This indicates that at least one device pointer passed to the API call is not a valid device pointer. Cumoduleload

cudaErrorMissingConfiguration The device function being invoked (usually via cudaLaunch()) was not previously configured via the cudaConfigureCall() function. CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work. cudaErrorSharedObjectInitFailed This indicates that initialization of a shared object failed. his comment is here Btw, you should be able to use cuda runtime to launch your kernels.

See also: cuCtxEnablePeerAccess, cuCtxDisablePeerAccess, cuCtxCanAccessPeer GPULib 1.6.0 API Tech-X Corporation Overview Directory File Etc Categories Search Index Help User documentation lib/ CUDA error codes The error codes returned through the Cuctxcreate This is only a preference. See also: cuCtxGetCurrent, cuCtxCreate, cuCtxDestroy CUresult cuCtxSetLimit ( CUlimitlimit, size_tvalue ) Set resource limits.

CU_LIMIT_MALLOC_HEAP_SIZE controls the size in bytes of the heap used by the malloc() and free() device system calls.

CU_LIMIT_STACK_SIZE controls the stack size in bytes of each GPU thread. cudaErrorUnmapBufferObjectFailed This indicates that the buffer object could not be unmapped. This was previously used for device emulation of texture operations. Cumoduleloaddataex On Dec 18, 2013 7:02 AM, "Denis Demidov" [email protected] wrote: Usually this kind of error comes from the previous kernel launch.

Device emulation mode was removed with the CUDA 3.1 release. See also: cuCtxCreate, cuCtxDestroy, cuCtxGetApiVersion, cuCtxGetCacheConfig, cuCtxGetDevice, cuCtxGetFlags, cuCtxPopCurrent, cuCtxPushCurrent, cuCtxSetCacheConfig, cuCtxSetLimit, cuCtxSynchronize CUresult cuCtxGetSharedMemConfig ( CUsharedconfig*pConfig ) Returns the current shared memory configuration for the current context. A NULL may be passed in for *leastPriority or *greatestPriority if the value is not desired. weblink If pD3DResource cannot be registered then CUDA_ERROR_UNKNOWN is returned.

This function uses standard default stream semantics. CUresultcuCtxSetSharedMemConfig ( CUsharedconfigconfig ) Sets the shared memory configuration for the current context.