123456789101112131415161718192021222324 |
- #include <starpu.h>
- static __global__ void vector_mult_cuda(float *val, unsigned n,
- float factor)
- @{
- unsigned i;
- for(i = 0 ; i < n ; i++)
- 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]);
- vector_mult_cuda<<<1,1>>>(val, n, *factor);
- cudaThreadSynchronize();
- @}
|