scal_cuda.cu 1.2 KB

123456789101112131415161718192021222324252627282930313233343536
  1. /* StarPU --- Runtime system for heterogeneous multicore architectures.
  2. *
  3. * Copyright (C) 2010-2020 Université de Bordeaux, CNRS (LaBRI UMR 5800), Inria
  4. *
  5. * StarPU is free software; you can redistribute it and/or modify
  6. * it under the terms of the GNU Lesser General Public License as published by
  7. * the Free Software Foundation; either version 2.1 of the License, or (at
  8. * your option) any later version.
  9. *
  10. * StarPU is distributed in the hope that it will be useful, but
  11. * WITHOUT ANY WARRANTY; without even the implied warranty of
  12. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  13. *
  14. * See the GNU Lesser General Public License in COPYING.LGPL for more details.
  15. */
  16. #include <starpu.h>
  17. static __global__ void vector_mult_cuda(unsigned *val, unsigned n)
  18. {
  19. unsigned i = blockIdx.x*blockDim.x + threadIdx.x;
  20. if (i < n)
  21. val[i] *= 2;
  22. }
  23. extern "C" void scal_func_cuda(void *buffers[], void *_args)
  24. {
  25. unsigned n = STARPU_VECTOR_GET_NX(buffers[0]);
  26. unsigned *val = (unsigned *)STARPU_VECTOR_GET_PTR(buffers[0]);
  27. unsigned threads_per_block = 64;
  28. unsigned nblocks = (n + threads_per_block-1) / threads_per_block;
  29. vector_mult_cuda<<<nblocks,threads_per_block,0,starpu_cuda_get_local_stream()>>>(val, n);
  30. }