int MPIDI_Accumulate(void *origin_addr, int origin_count, MPI_Datatype origin_datatype, int target_rank, MPI_Aint target_disp, int target_count, MPI_Datatype target_datatype, MPI_Op op, MPID_Win *win_ptr) { int mpi_errno=MPI_SUCCESS; MPIDI_msg_sz_t data_sz; int dt_contig, rank, origin_predefined, target_predefined; MPI_Aint dt_true_lb; MPIDI_RMA_ops *new_ptr; MPID_Datatype *dtp; MPIU_CHKLMEM_DECL(2); MPIU_CHKPMEM_DECL(1); MPIDI_STATE_DECL(MPID_STATE_MPIDI_ACCUMULATE); MPIDI_RMA_FUNC_ENTER(MPID_STATE_MPIDI_ACCUMULATE); MPIDI_Datatype_get_info(origin_count, origin_datatype, dt_contig, data_sz, dtp, dt_true_lb); if ((data_sz == 0) || (target_rank == MPI_PROC_NULL)) { goto fn_exit; } rank = win_ptr->myrank; MPIDI_CH3I_DATATYPE_IS_PREDEFINED(origin_datatype, origin_predefined); MPIDI_CH3I_DATATYPE_IS_PREDEFINED(target_datatype, target_predefined); /* Do =! rank first (most likely branch?) */ if (target_rank == rank) { MPI_User_function *uop; if (op == MPI_REPLACE) { mpi_errno = MPIR_Localcopy(origin_addr, origin_count, origin_datatype, (char *) win_ptr->base + win_ptr->disp_unit * target_disp, target_count, target_datatype); goto fn_exit; } MPIU_ERR_CHKANDJUMP1((HANDLE_GET_KIND(op) != HANDLE_KIND_BUILTIN), mpi_errno, MPI_ERR_OP, "**opnotpredefined", "**opnotpredefined %d", op ); /* get the function by indexing into the op table */ uop = MPIR_Op_table[((op)&0xf) - 1]; if (origin_predefined && target_predefined) { (*uop)(origin_addr, (char *) win_ptr->base + win_ptr->disp_unit * target_disp, &target_count, &target_datatype); } else { /* derived datatype */ MPID_Segment *segp; DLOOP_VECTOR *dloop_vec; MPI_Aint first, last; int vec_len, i, type_size, count; MPI_Datatype type; MPI_Aint true_lb, true_extent, extent; void *tmp_buf=NULL, *source_buf, *target_buf; if (origin_datatype != target_datatype) { /* first copy the data into a temporary buffer with the same datatype as the target. Then do the accumulate operation. */ MPIR_Type_get_true_extent_impl(target_datatype, &true_lb, &true_extent); MPID_Datatype_get_extent_macro(target_datatype, extent); MPIU_CHKLMEM_MALLOC(tmp_buf, void *, target_count * (MPIR_MAX(extent,true_extent)), mpi_errno, "temporary buffer"); /* adjust for potential negative lower bound in datatype */ tmp_buf = (void *)((char*)tmp_buf - true_lb); mpi_errno = MPIR_Localcopy(origin_addr, origin_count, origin_datatype, tmp_buf, target_count, target_datatype); if (mpi_errno) { MPIU_ERR_POP(mpi_errno); } } if (target_predefined) { /* target predefined type, origin derived datatype */ (*uop)(tmp_buf, (char *) win_ptr->base + win_ptr->disp_unit * target_disp, &target_count, &target_datatype); } else { segp = MPID_Segment_alloc(); MPIU_ERR_CHKANDJUMP1((!segp), mpi_errno, MPI_ERR_OTHER, "**nomem","**nomem %s","MPID_Segment_alloc"); MPID_Segment_init(NULL, target_count, target_datatype, segp, 0); first = 0; last = SEGMENT_IGNORE_LAST; MPID_Datatype_get_ptr(target_datatype, dtp); vec_len = dtp->max_contig_blocks * target_count + 1; /* +1 needed because Rob says so */ MPIU_CHKLMEM_MALLOC(dloop_vec, DLOOP_VECTOR *, vec_len * sizeof(DLOOP_VECTOR), mpi_errno, "dloop vector"); MPID_Segment_pack_vector(segp, first, &last, dloop_vec, &vec_len); source_buf = (tmp_buf != NULL) ? tmp_buf : origin_addr; target_buf = (char *) win_ptr->base + win_ptr->disp_unit * target_disp; type = dtp->eltype; type_size = MPID_Datatype_get_basic_size(type); for (i=0; i<vec_len; i++) { count = (dloop_vec[i].DLOOP_VECTOR_LEN)/type_size; (*uop)((char *)source_buf + MPIU_PtrToAint(dloop_vec[i].DLOOP_VECTOR_BUF), (char *)target_buf + MPIU_PtrToAint(dloop_vec[i].DLOOP_VECTOR_BUF), &count, &type); } MPID_Segment_free(segp); } }
int MPIDI_Get_accumulate(const void *origin_addr, int origin_count, MPI_Datatype origin_datatype, void *result_addr, int result_count, MPI_Datatype result_datatype, int target_rank, MPI_Aint target_disp, int target_count, MPI_Datatype target_datatype, MPI_Op op, MPID_Win *win_ptr) { int mpi_errno = MPI_SUCCESS; MPIDI_msg_sz_t data_sz; int rank, origin_predefined, result_predefined, target_predefined; int shm_locked = 0; int dt_contig ATTRIBUTE((unused)); MPI_Aint dt_true_lb ATTRIBUTE((unused)); MPID_Datatype *dtp; MPIU_CHKLMEM_DECL(2); MPIDI_STATE_DECL(MPID_STATE_MPIDI_GET_ACCUMULATE); MPIDI_RMA_FUNC_ENTER(MPID_STATE_MPIDI_GET_ACCUMULATE); if (target_rank == MPI_PROC_NULL) { goto fn_exit; } if (win_ptr->epoch_state == MPIDI_EPOCH_NONE && win_ptr->fence_issued) { win_ptr->epoch_state = MPIDI_EPOCH_FENCE; } MPIU_ERR_CHKANDJUMP(win_ptr->epoch_state == MPIDI_EPOCH_NONE, mpi_errno, MPI_ERR_RMA_SYNC, "**rmasync"); MPIDI_Datatype_get_info(target_count, target_datatype, dt_contig, data_sz, dtp, dt_true_lb); if (data_sz == 0) { goto fn_exit; } rank = win_ptr->myrank; origin_predefined = TRUE; /* quiet uninitialized warnings (b/c goto) */ if (op != MPI_NO_OP) { MPIDI_CH3I_DATATYPE_IS_PREDEFINED(origin_datatype, origin_predefined); } MPIDI_CH3I_DATATYPE_IS_PREDEFINED(result_datatype, result_predefined); MPIDI_CH3I_DATATYPE_IS_PREDEFINED(target_datatype, target_predefined); /* Do =! rank first (most likely branch?) */ if (target_rank == rank || win_ptr->create_flavor == MPI_WIN_FLAVOR_SHARED) { MPI_User_function *uop; void *base; int disp_unit; if (win_ptr->create_flavor == MPI_WIN_FLAVOR_SHARED) { base = win_ptr->shm_base_addrs[target_rank]; disp_unit = win_ptr->disp_units[target_rank]; MPIDI_CH3I_SHM_MUTEX_LOCK(win_ptr); shm_locked = 1; } else { base = win_ptr->base; disp_unit = win_ptr->disp_unit; } /* Perform the local get first, then the accumulate */ mpi_errno = MPIR_Localcopy((char *) base + disp_unit * target_disp, target_count, target_datatype, result_addr, result_count, result_datatype); if (mpi_errno) { MPIU_ERR_POP(mpi_errno); } /* NO_OP: Don't perform the accumulate */ if (op == MPI_NO_OP) { if (shm_locked) { MPIDI_CH3I_SHM_MUTEX_UNLOCK(win_ptr); shm_locked = 0; } goto fn_exit; } if (op == MPI_REPLACE) { mpi_errno = MPIR_Localcopy(origin_addr, origin_count, origin_datatype, (char *) base + disp_unit * target_disp, target_count, target_datatype); if (mpi_errno) { MPIU_ERR_POP(mpi_errno); } if (shm_locked) { MPIDI_CH3I_SHM_MUTEX_UNLOCK(win_ptr); shm_locked = 0; } goto fn_exit; } MPIU_ERR_CHKANDJUMP1((HANDLE_GET_KIND(op) != HANDLE_KIND_BUILTIN), mpi_errno, MPI_ERR_OP, "**opnotpredefined", "**opnotpredefined %d", op ); /* get the function by indexing into the op table */ uop = MPIR_OP_HDL_TO_FN(op); if (origin_predefined && target_predefined) { /* Cast away const'ness for origin_address in order to * avoid changing the prototype for MPI_User_function */ (*uop)((void *) origin_addr, (char *) base + disp_unit*target_disp, &target_count, &target_datatype); } else { /* derived datatype */ MPID_Segment *segp; DLOOP_VECTOR *dloop_vec; MPI_Aint first, last; int vec_len, i, type_size, count; MPI_Datatype type; MPI_Aint true_lb, true_extent, extent; void *tmp_buf=NULL, *target_buf; const void *source_buf; if (origin_datatype != target_datatype) { /* first copy the data into a temporary buffer with the same datatype as the target. Then do the accumulate operation. */ MPIR_Type_get_true_extent_impl(target_datatype, &true_lb, &true_extent); MPID_Datatype_get_extent_macro(target_datatype, extent); MPIU_CHKLMEM_MALLOC(tmp_buf, void *, target_count * (MPIR_MAX(extent,true_extent)), mpi_errno, "temporary buffer"); /* adjust for potential negative lower bound in datatype */ tmp_buf = (void *)((char*)tmp_buf - true_lb); mpi_errno = MPIR_Localcopy(origin_addr, origin_count, origin_datatype, tmp_buf, target_count, target_datatype); if (mpi_errno) { MPIU_ERR_POP(mpi_errno); } } if (target_predefined) { /* target predefined type, origin derived datatype */ (*uop)(tmp_buf, (char *) base + disp_unit * target_disp, &target_count, &target_datatype); } else { segp = MPID_Segment_alloc(); MPIU_ERR_CHKANDJUMP1((!segp), mpi_errno, MPI_ERR_OTHER, "**nomem","**nomem %s","MPID_Segment_alloc"); MPID_Segment_init(NULL, target_count, target_datatype, segp, 0); first = 0; last = SEGMENT_IGNORE_LAST; MPID_Datatype_get_ptr(target_datatype, dtp); vec_len = dtp->max_contig_blocks * target_count + 1; /* +1 needed because Rob says so */ MPIU_CHKLMEM_MALLOC(dloop_vec, DLOOP_VECTOR *, vec_len * sizeof(DLOOP_VECTOR), mpi_errno, "dloop vector"); MPID_Segment_pack_vector(segp, first, &last, dloop_vec, &vec_len); source_buf = (tmp_buf != NULL) ? tmp_buf : origin_addr; target_buf = (char *) base + disp_unit * target_disp; type = dtp->eltype; type_size = MPID_Datatype_get_basic_size(type); for (i=0; i<vec_len; i++) { count = (dloop_vec[i].DLOOP_VECTOR_LEN)/type_size; (*uop)((char *)source_buf + MPIU_PtrToAint(dloop_vec[i].DLOOP_VECTOR_BUF), (char *)target_buf + MPIU_PtrToAint(dloop_vec[i].DLOOP_VECTOR_BUF), &count, &type); } MPID_Segment_free(segp); } }
int MPIDI_Get(void *origin_addr, int origin_count, MPI_Datatype origin_datatype, int target_rank, MPI_Aint target_disp, int target_count, MPI_Datatype target_datatype, MPID_Win *win_ptr) { int mpi_errno = MPI_SUCCESS; MPIDI_msg_sz_t data_sz; int dt_contig, rank, predefined; MPI_Aint dt_true_lb; MPIDI_RMA_ops *new_ptr; MPID_Datatype *dtp; MPIU_CHKPMEM_DECL(1); MPIDI_STATE_DECL(MPID_STATE_MPIDI_GET); MPIDI_RMA_FUNC_ENTER(MPID_STATE_MPIDI_GET); MPIDI_Datatype_get_info(origin_count, origin_datatype, dt_contig, data_sz, dtp, dt_true_lb); if ((data_sz == 0) || (target_rank == MPI_PROC_NULL)) { goto fn_exit; } rank = win_ptr->myrank; /* If the get is a local operation, do it here */ if (target_rank == rank) { mpi_errno = MPIR_Localcopy((char *) win_ptr->base + win_ptr->disp_unit * target_disp, target_count, target_datatype, origin_addr, origin_count, origin_datatype); } else { /* queue it up */ MPIU_INSTR_DURATION_START(rmaqueue_alloc); MPIU_CHKPMEM_MALLOC(new_ptr, MPIDI_RMA_ops *, sizeof(MPIDI_RMA_ops), mpi_errno, "RMA operation entry"); MPIU_INSTR_DURATION_END(rmaqueue_alloc); if (win_ptr->rma_ops_list_tail) win_ptr->rma_ops_list_tail->next = new_ptr; else win_ptr->rma_ops_list_head = new_ptr; win_ptr->rma_ops_list_tail = new_ptr; /* FIXME: For contig and very short operations, use a streamlined op */ new_ptr->next = NULL; new_ptr->type = MPIDI_RMA_GET; new_ptr->origin_addr = origin_addr; new_ptr->origin_count = origin_count; new_ptr->origin_datatype = origin_datatype; new_ptr->target_rank = target_rank; new_ptr->target_disp = target_disp; new_ptr->target_count = target_count; new_ptr->target_datatype = target_datatype; /* if source or target datatypes are derived, increment their reference counts */ MPIDI_CH3I_DATATYPE_IS_PREDEFINED(origin_datatype, predefined); if (!predefined) { MPID_Datatype_get_ptr(origin_datatype, dtp); MPID_Datatype_add_ref(dtp); } MPIDI_CH3I_DATATYPE_IS_PREDEFINED(target_datatype, predefined); if (!predefined) { MPID_Datatype_get_ptr(target_datatype, dtp); MPID_Datatype_add_ref(dtp); } } fn_exit: MPIDI_RMA_FUNC_EXIT(MPID_STATE_MPIDI_GET); return mpi_errno; /* --BEGIN ERROR HANDLING-- */ fn_fail: MPIU_CHKPMEM_REAP(); goto fn_exit; /* --END ERROR HANDLING-- */ }