starpu-max/doc/tutorial/vector_scal_cuda.cu

/* StarPU --- Runtime system for heterogeneous multicore architectures.
 *
 * Copyright (C) 2010-2020  Université de Bordeaux, CNRS (LaBRI UMR 5800), Inria
 *
 * StarPU is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as published by
 * the Free Software Foundation; either version 2.1 of the License, or (at
 * your option) any later version.
 *
 * StarPU is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 *
 * See the GNU Lesser General Public License in COPYING.LGPL for more details.
 */

#include <starpu.h>

static __global__ void vector_mult_cuda(float *val, unsigned int n, float factor)
{
        unsigned i =  blockIdx.x*blockDim.x + threadIdx.x;
        if (i < n)
               val[i] *= factor;
}

extern "C" void vector_scal_cuda(void *buffers[], void *_args)
{
        float *factor = (float *)_args;

        /* length of the vector */
        unsigned int 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);
        cudaError_t status = cudaGetLastError();
        if (status != cudaSuccess) STARPU_CUDA_REPORT_ERROR(status);

        cudaStreamSynchronize(starpu_cuda_get_local_stream());
}