SHMEM_COLLECT32(3)

👑 NAME 👑

shmem_collect4(3), shmem_collect8(3), shmem_collect32(3), shmem_collect64(3), shmem_fcollect(3), shmem_fcollect4(3), shmem_fcollect8(3), shmem_fcollect32(3), shmem_fcollect64(3) — Concatenates blocks of data from multiple processing elements (PEs) to an array in every PE 🫶

no bc we are in the Open MPI manual, section 3, and this is the whole collect/fcollect girl squad. let's go ✨

---

🎀 SYNOPSIS 🎀

C or C++

#include <mpp/shmem.h>

void shmem_collect32(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride, int PE_size,
  long *pSync)

void shmem_collect64(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride, int PE_size,
  long *pSync)

void shmem_fcollect32(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride, int PE_size,
  long *pSync)

void shmem_fcollect64(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride, int PE_size,
  long *pSync)

Fortran

INCLUDE "mpp/shmem.fh"

INTEGER nelems
INTEGER PE_start, logPE_stride, PE_size
INTEGER pSync(SHMEM_COLLECT_SYNC_SIZE)

CALL SHMEM_COLLECT4(target, source, nelems, PE_start,
& logPE_stride, PE_size, pSync)

CALL SHMEM_COLLECT8(target, source, nelems, PE_start,
& logPE_stride, PE_size, pSync)

CALL SHMEM_FCOLLECT4(target, source, nelems, PE_start,
& logPE_stride, PE_size, pSync)

CALL SHMEM_FCOLLECT8(target, source, nelems, PE_start,
& logPE_stride, PE_size, pSync)

---

✨ DESCRIPTION ✨

okay so the shared memory (SHMEM) collect and fcollect routines concatenate nelems 64-bit or 32-bit data items from the source array into the target array, over the set of PEs that you define with PE_start, log2PE_stride, and PE_size — and it happens in processor number order, which is the whole vibe. 💅

the resulting target array is stacked like this: the contribution from PE PE_start comes first, then the contribution from PE PE_start + PE_stride comes second, and so on and so on. and bestie, the collected result gets written to the target array for all PEs in the active set. everyone eats. 🍓

so what's the difference between the two flavors? the fcollect routines require that nelems be the same value in all participating PEs, while the collect routines allow nelems to vary from PE to PE. that's it, that's the tea. ☕

the resulting target array looks like this:

----------------------------------------------------------
   source(1..nelems)
       from PE (PE_start + 0 * (2**logPE_stride))
----------------------------------------------------------
   source(1..nelems)
       from PE (PE_start + 1 * (2**logPE_stride))
----------------------------------------------------------
   ...
----------------------------------------------------------
   source(1..nelems) from
       PE (PE_start + (PE_size - 1) * (2**logPE_stride))
----------------------------------------------------------

now, as with all SHMEM collective routines, each of these routines assumes that only PEs in the active set call the routine. if a PE that is not in the active set calls a SHMEM collective routine, undefined behavior results. so like. don't do that. 😭

the arguments, one by one 🧚

• target — a symmetric array. the target argument must be big enough to accept the concatenation of the source arrays on all PEs. the data types go like this:
  • [shmem_collect8, shmem_collect64, shmem_fcollect8, and shmem_fcollect64] — any data type with an element size of 64 bits. Fortran derived types, Fortran character type, and C/C++ structures are not permitted. 🙈
  • [shmem_collect4, shmem_collect32, shmem_fcollect4, and shmem_fcollect32] — any data type with an element size of 32 bits. Fortran derived types, Fortran character type, and C/C++ structures are not permitted. 🙈
• source — a symmetric data object that can be of any type permissible for the target argument.
• nelems — the number of elements in the source array. nelems must be of type integer. if you're using Fortran, it must be a default integer value.
• PE_start — the lowest virtual PE number of the active set of PEs. PE_start must be of type integer. if you're using Fortran, it must be a default integer value.
• logPE_stride — the log (base 2) of the stride between consecutive virtual PE numbers in the active set. logPE_stride must be of type integer. if you're using Fortran, it must be a default integer value.
• PE_size — the number of PEs in the active set. PE_size must be of type integer. if you're using Fortran, it must be a default integer value.
• pSync — a symmetric work array. in C/C++, pSync must be of type int and size _SHMEM_COLLECT_SYNC_SIZE. in Fortran, pSync must be of type integer and size SHMEM_COLLECT_SYNC_SIZE. if you're using Fortran, it must be a default integer value. every element of this array must be initialized with the value _SHMEM_SYNC_VALUE in C/C++ or SHMEM_SYNC_VALUE in Fortran before any of the PEs in the active set enter shmem_barrier(). yes, every single one. 🎀

---

the values of the arguments PE_start, logPE_stride, and PE_size must be equal on all PEs in the active set. and the same target and source arrays and the same pSync work array must be passed to all PEs in the active set. everybody in sync, no cap. 🦋

upon return from a collective routine, the following are true for the local PE:

• the target array is updated ✅
• the values in the pSync array are restored to the original values ✅

---

💀 NOTES 💀

the terms collective and symmetric are defined in intro_shmem(3). iykyk 💅

all SHMEM collective routines reset the values in pSync before they return, so a particular pSync buffer need only be initialized the first time it is used. iconic behavior honestly.

⚠️ you must ensure that the pSync array is not being updated on any PE in the active set while any of the PEs participate in processing of a SHMEM collective routine. be careful to avoid these situations: if the pSync array is initialized at run time, some type of synchronization is needed to ensure that all PEs in the working set have initialized pSync before any of them enter a SHMEM routine called with the pSync synchronization array. a pSync array can be reused on a subsequent SHMEM collective routine only if none of the PEs in the active set are still processing a prior SHMEM collective routine call that used the same pSync array. in general, this may be ensured only by doing some type of synchronization. however, in the special case of SHMEM routines being called with the same active set, you can allocate two pSync arrays and alternate between them on successive calls.

tldr: share the pSync too early and you're cooked. 💀🍓

and a lil performance note for you: the collective routines operate on active PE sets that have a non-power-of-two PE_size with some performance degradation. they operate with no performance degradation when nelems is a non-power-of-two value. so like, nelems can be weird, PE_size being weird is gonna cost ya a little. 🌸

---

🌈 EXAMPLES 🌈

C/C++

for (i=0; i < _SHMEM_COLLECT_SYNC_SIZE; i++) {
  pSync[i] = _SHMEM_SYNC_VALUE;
}
shmem_barrier_all(); /* Wait for all PEs to initialize pSync */
shmem_collect32(target, source, 64, pe_start, logPE_stride,
   pe_size, pSync);

Fortran

INTEGER PSYNC(SHMEM_COLLECT_SYNC_SIZE)
DATA PSYNC /SHMEM_COLLECT_SYNC_SIZE*SHMEM_SYNC_VALUE/

CALL SHMEM_COLLECT4(TARGET, SOURCE, 64, PE_START,
& LOGPE_STRIDE, PE_SIZE, PSYNC)

see also:

• intro_shmem(3)

---

📜 Copyright 📜

2003-2026, The Open MPI Community

---

and that's the whole page bestie, periodt 💅✨ this one dropped Sep 10, 2026, straight from Open MPI — go forth and collect responsibly, ily, mwah 🫶💖🎀