SHMEM_COMPLEXD_SUM_TO_ALL(3)

📦
version 5.0.10 · 4 versions
, in ubuntu stonking

✨ SHMEM_COMPLEXD_SUM_TO_ALL(3) ✨

okay bestie, buckle up 🫶 this is the Open MPI page for shmem_complexd_sum_to_all(3) and its whole extremely large friend group. it's giving "sum reduction across a set of processing elements (PEs)" and honestly? iconic.

the squad (all of them live on this page, no cap):

and what do they do? 💅 Performs a sum reduction across a set of processing elements (PEs). periodt.

🌸 SYNOPSIS 🌸

🎀 C or C++

#include <mpp/shmem.h>

void shmem_complexd_sum_to_all(double complex *target,
  const double complex *source, int nreduce, int PE_start,
  int logPE_stride, int PE_size, double complex *pWrk,
  long *pSync)

void shmem_complexf_sum_to_all(float complex *target,
  const float complex *source, int nreduce, int PE_start,
  int logPE_stride, int PE_size, float complex *pWrk,
  long *pSync)

void shmem_double_sum_to_all(double *target,
  const double *source, int nreduce, int PE_start, int logPE_stride,
  int PE_size, double *pWrk, long *pSync)

void shmem_float_sum_to_all(float *target, const float *source,
  int nreduce, int PE_start, int logPE_stride, int PE_size,
  float *pWrk, long *pSync)

void shmem_int_sum_to_all(int *target, const int *source,
  int nreduce, int PE_start, int logPE_stride, int PE_size,
  int *pWrk, long *pSync)

void shmem_long_sum_to_all(long *target, const long *source,
  int nreduce, int PE_start, int logPE_stride, int PE_size,
  long *pWrk, long *pSync)

void shmem_longdouble_sum_to_all(long double *target,
  const long double *source, int nreduce, int PE_start, int
  logPE_stride, int PE_size, long double *pWrk, long *pSync)

void shmem_longlong_sum_to_all(long long *target,
  const long long *source, int nreduce, int PE_start,
  int logPE_stride, int PE_size, long long *pWrk,
  long *pSync)

void shmem_short_sum_to_all(short *target, const short *source,
  int nreduce, int PE_start, int logPE_stride, int PE_size,
  short *pWrk, long *pSync)

🦋 Fortran

INCLUDE "mpp/shmem.fh"

INTEGER pSync(SHMEM_REDUCE_SYNC_SIZE)
INTEGER nreduce, PE_start, logPE_stride, PE_size

CALL SHMEM_COMP4_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_COMP8_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_INT4_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_INT8_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_REAL4_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_REAL8_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

CALL SHMEM_REAL16_SUM_TO_ALL(target, source, nreduce,
& PE_start, logPE_stride, PE_size, pWrk, pSync)

💖 DESCRIPTION 💖

so. the shared memory (SHMEM) reduction routines compute one or more reductions across symmetric arrays on multiple virtual PEs. and a reduction? it performs an associative binary operation across a set of values. for the whole list of other SHMEM reduction routines, go peek at intro_shmem(3). iykyk 📚

and like 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. 😭 not it. don't do it.

the nreduce argument determines the number of separate reductions to perform. the source array on all PEs in the active set provides one element for each reduction. the results of the reductions get placed in the target array on all PEs in the active set. and the active set is defined by the PE_start, logPE_stride, PE_size triplet. that trio is the moment, fr fr. 👑

the source and target arrays may be the same array, but they may not be overlapping arrays. read that again bestie.

the arguments are as follows:

  • target — the remotely accessible integer data object to be updated on the remote PE. if you're using C/C++, the type of target should match that implied in the SYNOPSIS section. if you're using the Fortran compiler, it must be of type integer with an element size of 4 bytes for SHMEM_INT4_ADD and 8 bytes for SHMEM_INT8_ADD.
  • value — the value to be atomically added to target. if you're using C/C++, the type of value should match that implied in the SYNOPSIS section. if you're using Fortran, it must be of type integer with an element size of target.
  • pe — an integer that indicates the PE number upon which target is to be updated. if you're using Fortran, it must be a default integer value.
  • target — a symmetric array of length nreduce elements to receive the results of the reduction operations. the data type of target varies with the version of the reduction routine being called and the language used. when calling from C/C++, refer to the SYNOPSIS section for data type information. when calling from Fortran, the target data types are as follows:
    • shmem_comp4_sum_to_all: COMPLEX(KIND=4).
    • shmem_comp8_sum_to_all: Complex. if you're using Fortran, it must be a default complex value.
    • shmem_int4_sum_to_all: INTEGER(KIND=4).
    • shmem_int8_sum_to_all: Integer. if you're using Fortran, it must be a default integer value.
    • shmem_real4_sum_to_all: REAL(KIND=4).
    • shmem_real8_sum_to_all: Real. if you're using Fortran, it must be a default real value.
    • shmem_real16_sum_to_all: Real. if you're using Fortran, it must be a default real value.
  • source — a symmetric array, of length nreduce elements, that contains one element for each separate reduction operation. the source argument must have the same data type as target.
  • nreduce — the number of elements in the target and source arrays. nreduce 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.
  • pWrk — a symmetric work array. the pWrk argument must have the same data type as target. in C/C++, this contains max(nreduce/2 + 1, _SHMEM_REDUCE_MIN_WRKDATA_SIZE) elements. in Fortran, this contains max(nreduce/2 + 1, SHMEM_REDUCE_MIN_WRKDATA_SIZE) elements.
  • pSync — a symmetric work array. in C/C++, pSync is of type long and size _SHMEM_REDUCE_SYNC_SIZE. in Fortran, pSync is of type integer and size SHMEM_REDUCE_SYNC_SIZE. 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 the reduction routine. ✨

the values of arguments nreduce, PE_start, logPE_stride, and PE_size must be equal on all PEs in the active set. the same target and source arrays, and the same pWrk and pSync work arrays, must be passed to all PEs in the active set. everyone matching, no stragglers. 🫶

before any PE calls a reduction routine, you must ensure that the following conditions exist (synchronization via a barrier or some other method is often needed to ensure this):

  • the pWrk and pSync arrays on all PEs in the active set are not still in use from a prior call to a collective SHMEM routine.
  • the target array on all PEs in the active set is ready to accept the results of the reduction.
bestie please actually do this. "often needed" is doing a LOT of heavy lifting in that sentence and it will absolutely humble you. 💀

upon return from a reduction 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, symmetric, and cache aligned are defined in intro_shmem(3). go read it, it's the prequel. 💜

all SHMEM reduction routines reset the values in pSync before they return, so a particular pSync buffer need only be initialized the first time it is used. cute, efficient, we love her. 💅

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 reduction routine. be careful of the following 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 or pWrk array can be reused in a subsequent reduction routine call only if none of the PEs in the active set are still processing a prior reduction routine call that used the same pSync or pWrk arrays.

in general, this can be assured only by doing some type of synchronization. however, in the special case of reduction routines being called with the same active set, you can allocate two pSync and pWrk arrays and alternate between them on successive calls. that's the pro move right there, main character energy. 👑

💫 okay that's part 1 bestie — more of this page is coming, don't go anywhere! ✨

✨ EXAMPLES ✨

Example 1 — the Fortran one 🎀

Bestie, this Fortran example statically initializes the pSync array and finds the sum of the real variable FOO across all even PEs. The way it does that is so cute. 😭

INCLUDE "mpp/shmem.fh"

INTEGER PSYNC(SHMEM_REDUCE_SYNC_SIZE)
DATA PSYNC /SHMEM_REDUCE_SYNC_SIZE*SHMEM_SYNC_VALUE/
PARAMETER (NR=1)
REAL FOO, FOOSUM, PWRK(MAX(NR/2+1,SHMEM_REDUCE_MIN_WRKDATA_SIZE))
COMMON /COM/ FOO, FOOSUM, PWRK
INTRINSIC MY_PE

IF ( MOD(MY_PE(),2) .EQ. 0) THEN
  CALL SHMEM_INT4_SUM_TO_ALL(FOOSUM, FOO, NR, 0, 1, N$PES/2,
  & PWRK, PSYNC)
  PRINT *, 'Result on PE ', MY_PE(), ' is ', FOOSUM
ENDIF

Notice the PSYNC declaration and the DATA PSYNC line — that's the static initialization moment, iconic. ✨

Example 2 — C/C++ being efficient 💅

Now consider the following C/C++ call:

shmem_int_sum_to_all( target, source, 3, 0, 0, 8, pwrk, psync );

The preceding call is more efficient, but semantically equivalent to, the combination of the following calls:

shmem_int_sum_to_all(&(target[0]), &(source[0]), 1, 0, 0, 8,
  pwrk1, psync1);
shmem_int_sum_to_all(&(target[1]), &(source[1]), 1, 0, 0, 8,
  pwrk2, psync2);
shmem_int_sum_to_all(&(target[2]), &(source[2]), 1, 0, 0, 8,
  pwrk1, psync1);
Note that two sets of pWrk and pSync arrays are used alternately because no synchronization is done between calls. 👀

Like, that's the whole reason there's a pwrk1/psync1 and a pwrk2/psync2 — they tag-team. 🔥

See also 🌈

2003-2026, The Open MPI Community

Okay that's the whole page bestie, you made it to the end and you ate. 💅 This little masterpiece lives in Open MPI's docs and the footer says Sep 10, 2026, filed under SHMEM_COMPLEXD_SUM_TO_ALL(3). Go forth and reduce, my icon. 👑🌸

📦 where this page comes from