1
1
openmpi/ompi/mca/pml/csum/pml_csum_rdmafrag.h

72 строки
2.3 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2006 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.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*/
#ifndef MCA_PML_CSUM_RDMAFRAG_H
#define MCA_PML_CSUM_RDMAFRAG_H
#include "ompi/mca/btl/btl.h"
#include "pml_csum_hdr.h"
BEGIN_C_DECLS
typedef enum {
MCA_PML_CSUM_RDMA_PUT,
MCA_PML_CSUM_RDMA_GET
} mca_pml_csum_rdma_state_t;
struct mca_pml_csum_rdma_frag_t {
ompi_free_list_item_t super;
mca_bml_base_btl_t* rdma_bml;
mca_pml_csum_hdr_t rdma_hdr;
mca_pml_csum_rdma_state_t rdma_state;
size_t rdma_length;
uint8_t rdma_segs[MCA_BTL_SEG_MAX_SIZE * MCA_BTL_DES_MAX_SEGMENTS];
void *rdma_req;
struct mca_bml_base_endpoint_t* rdma_ep;
- Split the datatype engine into two parts: an MPI specific part in OMPI and a language agnostic part in OPAL. The convertor is completely moved into OPAL. This offers several benefits as described in RFC http://www.open-mpi.org/community/lists/devel/2009/07/6387.php namely: - Fewer basic types (int* and float* types, boolean and wchar - Fixing naming scheme to ompi-nomenclature. - Usability outside of the ompi-layer. - Due to the fixed nature of simple opal types, their information is completely known at compile time and therefore constified - With fewer datatypes (22), the actual sizes of bit-field types may be reduced from 64 to 32 bits, allowing reorganizing the opal_datatype structure, eliminating holes and keeping data required in convertor (upon send/recv) in one cacheline... This has implications to the convertor-datastructure and other parts of the code. - Several performance tests have been run, the netpipe latency does not change with this patch on Linux/x86-64 on the smoky cluster. - Extensive tests have been done to verify correctness (no new regressions) using: 1. mpi_test_suite on linux/x86-64 using clean ompi-trunk and ompi-ddt: a. running both trunk and ompi-ddt resulted in no differences (except for MPI_SHORT_INT and MPI_TYPE_MIX_LB_UB do now run correctly). b. with --enable-memchecker and running under valgrind (one buglet when run with static found in test-suite, commited) 2. ibm testsuite on linux/x86-64 using clean ompi-trunk and ompi-ddt: all passed (except for the dynamic/ tests failed!! as trunk/MTT) 3. compilation and usage of HDF5 tests on Jaguar using PGI and PathScale compilers. 4. compilation and usage on Scicortex. - Please note, that for the heterogeneous case, (-m32 compiled binaries/ompi), neither ompi-trunk, nor ompi-ddt branch would successfully launch. This commit was SVN r21641.
2009-07-13 08:56:31 +04:00
opal_convertor_t convertor;
mca_mpool_base_registration_t* reg;
uint32_t retries;
};
typedef struct mca_pml_csum_rdma_frag_t mca_pml_csum_rdma_frag_t;
OBJ_CLASS_DECLARATION(mca_pml_csum_rdma_frag_t);
#define MCA_PML_CSUM_RDMA_FRAG_ALLOC(frag,rc) \
do { \
ompi_free_list_item_t* item; \
OMPI_FREE_LIST_WAIT(&mca_pml_csum.rdma_frags, item, rc); \
frag = (mca_pml_csum_rdma_frag_t*)item; \
} while(0)
#define MCA_PML_CSUM_RDMA_FRAG_RETURN(frag) \
do { \
/* return fragment */ \
OMPI_FREE_LIST_RETURN(&mca_pml_csum.rdma_frags, \
(ompi_free_list_item_t*)frag); \
} while(0)
END_C_DECLS
#endif