/*
* reduce_log_inter
*
* Function: - reduction using O(N) algorithm
* Accepts: - same as MPI_Reduce()
* Returns: - MPI_SUCCESS or error code
*/
int
mca_coll_cuda_reduce(const void *sbuf, void *rbuf, int count,
struct ompi_datatype_t *dtype,
struct ompi_op_t *op,
int root, 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 = NULL;
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 - 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 - lb;
}
rc = s->c_coll.coll_reduce((void *) sbuf, rbuf, count,
dtype, op, root, comm,
s->c_coll.coll_reduce_module);
if (NULL != sbuf1) {
free(sbuf1);
}
if (NULL != rbuf1) {
rbuf = rbuf2;
opal_cuda_memcpy_sync(rbuf, rbuf1, bufsize);
free(rbuf1);
}
return rc;
}
/*
* reduce_scatter_block
*
* Function: - reduce then scatter
* Accepts: - same as MPI_Reduce_scatter_block()
* Returns: - MPI_SUCCESS or error code
*
* Algorithm:
* reduce and scatter (needs to be cleaned
* up at some point)
*/
int
mca_coll_cuda_reduce_scatter_block(const void *sbuf, void *rbuf, int rcount,
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 gap;
char *rbuf1 = NULL, *sbuf1 = NULL, *rbuf2 = NULL;
const char *sbuf2;
size_t sbufsize, rbufsize;
int rc;
rbufsize = opal_datatype_span(&dtype->super, rcount, &gap);
sbufsize = rbufsize * ompi_comm_size(comm);
if ((MPI_IN_PLACE != sbuf) && (opal_cuda_check_bufs((char *)sbuf, NULL))) {
sbuf1 = (char*)malloc(sbufsize);
if (NULL == sbuf1) {
return OMPI_ERR_OUT_OF_RESOURCE;
}
opal_cuda_memcpy_sync(sbuf1, sbuf, sbufsize);
sbuf2 = sbuf; /* save away original buffer */
sbuf = sbuf1 - gap;
}
if (opal_cuda_check_bufs(rbuf, NULL)) {
rbuf1 = (char*)malloc(rbufsize);
if (NULL == rbuf1) {
if (NULL != sbuf1) free(sbuf1);
return OMPI_ERR_OUT_OF_RESOURCE;
}
opal_cuda_memcpy_sync(rbuf1, rbuf, rbufsize);
rbuf2 = rbuf; /* save away original buffer */
rbuf = rbuf1 - gap;
}
rc = s->c_coll.coll_reduce_scatter_block(sbuf, rbuf, rcount, dtype, op, comm,
s->c_coll.coll_reduce_scatter_block_module);
if (NULL != sbuf1) {
free(sbuf1);
}
if (NULL != rbuf1) {
rbuf = rbuf2;
opal_cuda_memcpy_sync(rbuf, rbuf1, rbufsize);
free(rbuf1);
}
return rc;
}
