123456789101112131415161718192021222324252627282930313233343536 |
- @c -*-texinfo-*-
- @c This file is part of the StarPU Handbook.
- @c Copyright (C) 2009-2011 Université de Bordeaux 1
- @c Copyright (C) 2010, 2011 Centre National de la Recherche Scientifique
- @c See the file starpu.texi for copying conditions.
- @smallexample
- #include <starpu.h>
- #include <starpu_cuda.h>
- static __global__ void vector_mult_cuda(float *val, unsigned n,
- float factor)
- @{
- unsigned i = blockIdx.x*blockDim.x + threadIdx.x;
- if (i < n)
- val[i] *= factor;
- @}
- extern "C" void scal_cuda_func(void *buffers[], void *_args)
- @{
- float *factor = (float *)_args;
- /* length of the vector */
- unsigned n = STARPU_VECTOR_GET_NX(buffers[0]);
- /* local copy of the vector pointer */
- float *val = (float *)STARPU_VECTOR_GET_PTR(buffers[0]);
- unsigned threads_per_block = 64;
- unsigned nblocks = (n + threads_per_block-1) / threads_per_block;
- vector_mult_cuda<<<nblocks,threads_per_block, 0, starpu_cuda_get_local_stream()>>>(val, n, *factor);
- cudaStreamSynchronize(starpu_cuda_get_local_stream());
- @}
- @end smallexample
|