/* StarPU --- Runtime system for heterogeneous multicore architectures.
 *
 * Copyright (C) 2010, 2011, 2012  Centre National de la Recherche Scientifique
 * Copyright (C) 2010, 2011  Université de Bordeaux 1
 *
 * Redistribution  and  use  in  source and binary forms, with or without
 * modification,  are  permitted  provided  that the following conditions
 * are met:
 *
 * * Redistributions  of  source  code  must  retain  the above copyright
 *   notice,  this  list  of  conditions  and  the  following  disclaimer.
 * * Redistributions  in  binary  form must reproduce the above copyright
 *   notice,  this list of conditions and the following disclaimer in the
 *   documentation  and/or other materials provided with the distribution.
 * * The name of the author may not be used to endorse or promote products
 *   derived from this software without specific prior written permission.
 *
 * THIS  SOFTWARE  IS  PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * ``AS IS''  AND  ANY  EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED  TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A  PARTICULAR  PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * HOLDERS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL
 * SPECIAL,  EXEMPLARY,  OR  CONSEQUENTIAL  DAMAGES  (INCLUDING,  BUT NOT
 * LIMITED  TO,  PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE
 * DATA,  OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY  OF  LIABILITY,  WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF  THIS  SOFTWARE,  EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <starpu.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());
}