12.07.2015 Views

NVIDIA CUDA

NVIDIA CUDA

NVIDIA CUDA

SHOW MORE
SHOW LESS
  • No tags were found...

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

3.8 Memory Management 45count - Size in bytes to copyoffset - Offset from start of symbol in byteskind - Type of transferReturns:Note:cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidDevicePointer, cudaErrorInvalidMemcpyDirectionSee also:Note that this function may also return error codes from previous, asynchronous launches.cudaMemcpy, cudaMemcpy2D, cudaMemcpyToArray, cudaMemcpy2DToArray, cudaMemcpyFromArray, cudaMemcpy2DFromArray,cudaMemcpyArrayToArray, cudaMemcpy2DArrayToArray, cudaMemcpyToSymbol,cudaMemcpyAsync, cudaMemcpy2DAsync, cudaMemcpyToArrayAsync, cudaMemcpy2DToArrayAsync,cudaMemcpyFromArrayAsync, cudaMemcpy2DFromArrayAsync, cudaMemcpyToSymbolAsync, cudaMemcpyFromSymbolAsync3.8.2.29 cudaError_t cudaMemcpyFromSymbolAsync (void ∗ dst, const char ∗ symbol, size_t count, size_toffset, enum cudaMemcpyKind kind, cudaStream_t stream)Copies count bytes from the memory area pointed to by offset bytes from the start of symbol symbol to thememory area pointed to by dst. The memory areas may not overlap. symbol can either be a variable that resides inglobal or constant memory space, or it can be a character string, naming a variable that resides in global or constantmemory space. kind can be either cudaMemcpyDeviceToHost or cudaMemcpyDeviceToDevice.cudaMemcpyFromSymbolAsync() is asynchronous with respect to the host, so the call may return before the copy iscomplete. It only works on page-locked host memory and returns an error if a pointer to pageable memory is passedas input. The copy can optionally be associated to a stream by passing a non-zero stream argument. If kind iscudaMemcpyDeviceToHost and stream is non-zero, the copy may overlap with operations in other streams.IMPORTANT NOTE: Copies with kind == cudaMemcpyDeviceToDevice are asynchronous with respect to thehost, but never overlap with kernel execution.Parameters:dst - Destination memory addresssymbol - Symbol source from devicecount - Size in bytes to copyoffset - Offset from start of symbol in byteskind - Type of transferstream - Stream identifierReturns:Note:cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidSymbol, cudaErrorInvalidDevicePointer, cudaErrorInvalidMemcpyDirectionNote that this function may also return error codes from previous, asynchronous launches.Generated on Wed Apr 1 16:11:42 2009 for <strong>NVIDIA</strong> <strong>CUDA</strong> Library by Doxygen

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!