/*
 * Copyright (c) 2014      The University of Tennessee and The University
 *                         of Tennessee Research Foundation.  All rights
 *                         reserved.
 * Copyright (c) 2014      NVIDIA Corporation.  All rights reserved.
 * $COPYRIGHT$
 * 
 * Additional copyrights may follow
 * 
 * $HEADER$
 */

#include "ompi_config.h"
#include "coll_cuda.h"

#include <stdio.h>

#include "ompi/op/op.h"
#include "opal/datatype/opal_convertor.h"
#include "opal/datatype/opal_datatype_cuda.h"

/*
 *	allreduce_intra
 *
 *	Function:	- allreduce using other MPI collectives
 *	Accepts:	- same as MPI_Allreduce()
 *	Returns:	- MPI_SUCCESS or error code
 */
int
mca_coll_cuda_allreduce(void *sbuf, void *rbuf, int count,
                        struct ompi_datatype_t *dtype,
                        struct ompi_op_t *op,
                        struct ompi_communicator_t *comm,
                        mca_coll_base_module_t *module)
{
    mca_coll_cuda_module_t *s = (mca_coll_cuda_module_t*) module;
    ptrdiff_t true_lb, true_extent, lb, extent;
    char *rbuf1 = NULL, *sbuf1 = NULL, *rbuf2;
    const char *sbuf2;
    size_t bufsize;
    int rc;

    ompi_datatype_get_extent(dtype, &lb, &extent);
    ompi_datatype_get_true_extent(dtype, &true_lb, &true_extent);
    bufsize = true_extent + (ptrdiff_t)(count - 1) * extent;
    if ((MPI_IN_PLACE != sbuf) && (opal_cuda_check_bufs((char *)sbuf, NULL))) {
        sbuf1 = (char*)malloc(bufsize);
        if (NULL == sbuf1) {
            return OMPI_ERR_OUT_OF_RESOURCE;
        }
        opal_cuda_memcpy_sync(sbuf1, sbuf, bufsize);
        sbuf2 = sbuf; /* save away original buffer */
        sbuf = sbuf1 - true_lb;
    }

    if (opal_cuda_check_bufs(rbuf, NULL)) {
        rbuf1 = (char*)malloc(bufsize);
        if (NULL == rbuf1) {
            if (NULL != sbuf1) free(sbuf1);
            return OMPI_ERR_OUT_OF_RESOURCE;
        }
        opal_cuda_memcpy_sync(rbuf1, rbuf, bufsize);
        rbuf2 = rbuf; /* save away original buffer */
        rbuf = rbuf1 - true_lb;
    }
    rc = s->c_coll.coll_allreduce(sbuf, rbuf, count, dtype, op, comm, s->c_coll.coll_allreduce_module);
    if (NULL != sbuf1) {
        free(sbuf1);
    }
    if (NULL != rbuf1) {
        rbuf = rbuf2;
        opal_cuda_memcpy_sync(rbuf, rbuf1, bufsize);
        free(rbuf1);
    }
    return rc;
}