1
1
openmpi/ompi/mca/pml/ob1/pml_ob1_isend.c
George Bosilca e361bcb64c Send optimizations.
1. The send path get shorter. The BTL is allowed to return > 0 to specify that the
   descriptor was pushed to the networks, and that the memory attached to it is 
   available again for the upper layer. The MCA_BTL_DES_SEND_ALWAYS_CALLBACK flag
   can be used by the PML to force the BTL to always trigger the callback.
   Unmodified BTL will continue to work as expected, as they will return OMPI_SUCCESS
   which force the PML to have exactly the same behavior as before. Some BTLs have
   been modified: self, sm, tcp, mx.
2. Add send immediate interface to BTL.
   The idea is to have a mechanism of allowing the BTL to take advantage of
   send optimizations such as the ability to deliver data "inline". Some
   network APIs such as Portals allow data to be sent using a "thin" event
   without packing data into a memory descriptor. This interface change
   allows the BTL to use such capabilities and allows for other optimizations
   in the future. All existing BTLs except for Portals and sm have this interface
   set to NULL.

This commit was SVN r18551.
2008-05-30 03:58:39 +00:00

131 строка
4.2 KiB
C

/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2007 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* Copyright (c) 2007 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "ompi_config.h"
#include "pml_ob1.h"
#include "pml_ob1_sendreq.h"
#include "pml_ob1_recvreq.h"
#include "ompi/peruse/peruse-internal.h"
int mca_pml_ob1_isend_init(void *buf,
size_t count,
ompi_datatype_t * datatype,
int dst,
int tag,
mca_pml_base_send_mode_t sendmode,
ompi_communicator_t * comm,
ompi_request_t ** request)
{
int rc;
mca_pml_ob1_send_request_t *sendreq = NULL;
MCA_PML_OB1_SEND_REQUEST_ALLOC(comm, dst, sendreq, rc);
if (rc != OMPI_SUCCESS)
return rc;
MCA_PML_OB1_SEND_REQUEST_INIT(sendreq,
buf,
count,
datatype,
dst, tag,
comm, sendmode, true);
PERUSE_TRACE_COMM_EVENT (PERUSE_COMM_REQ_ACTIVATE,
&(sendreq)->req_send.req_base,
PERUSE_SEND);
*request = (ompi_request_t *) sendreq;
return OMPI_SUCCESS;
}
int mca_pml_ob1_isend(void *buf,
size_t count,
ompi_datatype_t * datatype,
int dst,
int tag,
mca_pml_base_send_mode_t sendmode,
ompi_communicator_t * comm,
ompi_request_t ** request)
{
int rc;
mca_pml_ob1_send_request_t *sendreq = NULL;
MCA_PML_OB1_SEND_REQUEST_ALLOC(comm, dst, sendreq, rc);
if (rc != OMPI_SUCCESS)
return rc;
MCA_PML_OB1_SEND_REQUEST_INIT(sendreq,
buf,
count,
datatype,
dst, tag,
comm, sendmode, false);
PERUSE_TRACE_COMM_EVENT (PERUSE_COMM_REQ_ACTIVATE,
&(sendreq)->req_send.req_base,
PERUSE_SEND);
MCA_PML_OB1_SEND_REQUEST_START(sendreq, rc);
*request = (ompi_request_t *) sendreq;
return rc;
}
int mca_pml_ob1_send(void *buf,
size_t count,
ompi_datatype_t * datatype,
int dst,
int tag,
mca_pml_base_send_mode_t sendmode,
ompi_communicator_t * comm)
{
int rc;
mca_pml_ob1_send_request_t *sendreq;
MCA_PML_OB1_SEND_REQUEST_ALLOC(comm, dst, sendreq, rc);
if (rc != OMPI_SUCCESS)
return rc;
MCA_PML_OB1_SEND_REQUEST_INIT(sendreq,
buf,
count,
datatype,
dst, tag,
comm, sendmode, false);
PERUSE_TRACE_COMM_EVENT (PERUSE_COMM_REQ_ACTIVATE,
&(sendreq)->req_send.req_base,
PERUSE_SEND);
MCA_PML_OB1_SEND_REQUEST_START(sendreq, rc);
if (rc != OMPI_SUCCESS) {
MCA_PML_OB1_SEND_REQUEST_RETURN( sendreq );
return rc;
}
ompi_request_wait_completion(&sendreq->req_send.req_base.req_ompi);
rc = sendreq->req_send.req_base.req_ompi.req_status.MPI_ERROR;
ompi_request_free( (ompi_request_t**)&sendreq );
return rc;
}