File: shmem_alltoall32.3

package info (click to toggle)
openmpi 5.0.8-4
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 201,684 kB
  • sloc: ansic: 613,078; makefile: 42,353; sh: 11,194; javascript: 9,244; f90: 7,052; java: 6,404; perl: 5,179; python: 1,859; lex: 740; fortran: 61; cpp: 20; tcl: 12
file content (286 lines) | stat: -rw-r--r-- 9,487 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
.\" Man page generated from reStructuredText.
.
.TH "SHMEM_ALLTOALL32" "3" "May 30, 2025" "" "Open MPI"
.
.nr rst2man-indent-level 0
.
.de1 rstReportMargin
\\$1 \\n[an-margin]
level \\n[rst2man-indent-level]
level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
-
\\n[rst2man-indent0]
\\n[rst2man-indent1]
\\n[rst2man-indent2]
..
.de1 INDENT
.\" .rstReportMargin pre:
. RS \\$1
. nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
. nr rst2man-indent-level +1
.\" .rstReportMargin post:
..
.de UNINDENT
. RE
.\" indent \\n[an-margin]
.\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
.nr rst2man-indent-level -1
.\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
.in \\n[rst2man-indent\\n[rst2man-indent-level]]u
..
.sp
\fI\%shmem_alltoall32\fP(3), \fI\%shmem_alltoall64\fP(3),
\fI\%shmem_alltoalls32\fP(3), \fI\%shmem_alltoalls64\fP(3) \- collective routine
where each PE exchanges a fixed amount of data with all other PEs in the
Active set
.SH SYNOPSIS
.sp
C or C++:
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
#include <mpp/shmem.h>

void shmem_alltoall32(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride,
  int PE_size, long *pSync)

void shmem_alltoall64(void *target, const void *source,
  size_t nelems, int PE_start, int logPE_stride,
  int PE_size, long *pSync)

void shmem_alltoalls32(void *target, const void *source,
  ptrdiff_t dst, ptrdiff_t sst,
  size_t nelems, int PE_start, int logPE_stride,
  int PE_size, long *pSync)

void shmem_alltoalls64(void *target, const void *source,
  ptrdiff_t dst, ptrdiff_t sst,
  size_t nelems, int PE_start, int logPE_stride,
  int PE_size, long *pSync)
.ft P
.fi
.UNINDENT
.UNINDENT
.sp
Fortran:
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
INCLUDE "mpp/shmem.fh"

INTEGER dst, sst, nelems, PE_root, PE_start, logPE_stride, PE_size
INTEGER pSync(SHMEM_ALLTOALL_SYNC_SIZE)

CALL SHMEM_ALLTOALL32(target, source, nelems,
& PE_start, logPE_stride, PE_size, fIpSync)

CALL SHMEM_ALLTOALL64(target, source, nelems,
& PE_start, logPE_stride, PE_size, pSync)

CALL SHMEM_ALLTOALLS32(target, source, dst, sst, nelems,
& PE_start, logPE_stride, PE_size, pSync)

CALL SHMEM_ALLTOALLS64(target, source, dst, sst, nelems,
& PE_start, logPE_stride, PE_size, pSync)
.ft P
.fi
.UNINDENT
.UNINDENT
.SH DESCRIPTION
.sp
The shmem_alltoalls routines are collective routines. Each PE in the
Active set exchanges nelems strided data elements of size 32 bits (for
shmem_alltoalls32) or 64 bits (for shmem_alltoalls64) with all other PEs
in the set. Both strides, dst and sst, must be greater than or equal to
1. The sst*jth block sent from PE i to PE j is placed in the dst*ith
block of the dest data object on PE j. As with all OpenSHMEM collective
routines, these routines assume that only PEs in the Active set call the
routine. If a PE not in the Active set calls an OpenSHMEM collective
routine, undefined behavior results. The values of arguments dst, sst,
nelems, PE_start, logPE_stride, and PE_size must be equal on all PEs in
the Active set. The same dest and source data objects, and the same
pSync work array must be passed to all PEs in the Active set. Before any
PE calls to a shmem_alltoalls routine, the following conditions must
exist (synchronization via a barrier or some other method is often
needed to ensure this): The pSync array on all PEs in the Active set is
not still in use from a prior call to a shmem_alltoalls routine. The
dest data object on all PEs in the Active set is ready to accept the
shmem_alltoalls data. Upon return from a shmem_alltoalls routine, the
following is true for the local PE: Its dest symmetric data object is
completely updated and the data has been copied out of the source data
object. The values in the pSync array are restored to the original
values.
.sp
The arguments are as follows:
.sp
A symmetric data object with one of the following data types:
.INDENT 0.0
.INDENT 3.5
.INDENT 0.0
.TP
.B \fI\%shmem_alltoall32\fP: Any noncharacter type that
has an element size of 32 bits. No Fortran derived types or C/C++
structures are allowed.
.TP
.B \fI\%shmem_alltoall64\fP: Any noncharacter type that has an element size
of 64 bits. No Fortran derived types or C/C++ structures are
allowed.
.UNINDENT
.UNINDENT
.UNINDENT
.sp
target A symmetric data object large enough to receive the combined
total of nelems elements from each PE in the Active set.
.INDENT 0.0
.TP
.B source
A symmetric data object that contains nelems elements of data for
each PE in the Active set, ordered according to destination PE.
.TP
.B dst
The stride between consecutive elements of the dest data object. The
stride is scaled by the element size. A value of 1 indicates
contiguous data. dst must be of type ptrdiff_t. If you are using
Fortran, it must be a default integer value.
.TP
.B sst
The stride between consecutive elements of the source data object.
The stride is scaled by the element size. A value of 1 indicates
contiguous data. sst must be of type ptrdiff_t. If you are using
Fortran, it must be a default integer value.
.TP
.B nelems
The number of elements to exchange for each PE. nelems must be of
type size_t for C/C++. If you are using Fortran, it must be a default
integer value
.TP
.B PE_start
The lowest virtual PE number of the active set of PEs. PE_start must
be of type integer. If you are using Fortran, it must be a default
integer value.
.TP
.B logPE_stride
The log (base 2) of the stride between consecutive virtual PE numbers
in the active set. log_PE_stride must be of type integer. If you are
using Fortran, it must be a default integer value.
.TP
.B PE_size
The number of PEs in the active set. PE_size must be of type integer.
If you are using Fortran, it must be a default integer value.
.TP
.B pSync
A symmetric work array. In C/C++, pSync must be of type long and size
_SHMEM_ALLTOALL_SYNC_SIZE. In Fortran, pSync must be of type integer
and size SHMEM_ALLTOALL_SYNC_SIZE. 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().
.UNINDENT
.sp
Upon return from a shmem_alltoalls routine, the following is true for
the local PE: Its dest symmetric data object is completely updated and
the data has been copied out of the source data object. The values in
the pSync array are restored to the original values.
.sp
The values of arguments PE_root, PE_start, logPE_stride, and PE_size
must be equal on all PEs in the active set. The same target and source
data objects and the same pSync work array must be passed to all PEs in
the active set.
.sp
Before any PE calls a alltoall routine, you must ensure that the
following conditions exist (synchronization via a barrier or some other
method is often needed to ensure this): The pSync array on all PEs in
the active set is not still in use from a prior call to a alltoall
routine. The target array on all PEs in the active set is ready to
accept the alltoall data.
.SH NOTES
.sp
The terms collective and symmetric are defined in \fIintro_shmem\fP(3).
.sp
All SHMEM alltoall routines restore pSync to its original contents.
Multiple calls to SHMEM routines that use the same pSync array do not
require that pSync be reinitialized after the first call.
.sp
You must ensure the that the pSync array is not being updated by any PE
in the active set while any of the PEs participates in processing of a
SHMEM broadcast 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 may be reused on a subsequent SHMEM
broadcast routine only if none of the PEs in the active set are still
processing a prior SHMEM alltoall routine call that used the same pSync
array. In general, this can 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.
.SH EXAMPLES
.sp
C/C++ example:
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
#include <shmem.h>
#include <stdio.h>

long pSync[SHMEM_ALLTOALL_SYNC_SIZE];
int main(void)
{
int64_t *source, *dest;
int i, count, pe;
shmem_init();
count = 2;
dest = (int64_t*) shmem_malloc(count * shmem_n_pes() * sizeof(int64_t));
source = (int64_t*) shmem_malloc(count * shmem_n_pes() * sizeof(int64_t));
/* assign source values */
for (pe=0; pe <shmem_n_pes(); pe++){
for (i=0; i<count; i++){
source[(pe*count)+i] = shmem_my_pe() + pe;
dest[(pe*count)+i] = 9999;
}
}
for (i=0; i< SHMEM_ALLTOALLS_SYNC_SIZE; i++) {
pSync[i] = SHMEM_SYNC_VALUE;
}
/* wait for all PEs to initialize pSync */
shmem_barrier_all();
/* alltoalls on all PES */
shmem_alltoalls64(dest, source, 1, 1, count, 0, 0, shmem_n_pes(), pSync);
/* verify results */
for (pe=0; pe<shmem_n_pes(); pe++) {
for (i=0; i<count; i++){
if (dest[(pe*count)+i] != shmem_my_pe() + pe) {
printf("[%d] ERROR: dest[%d]=%ld, should be %d,
shmem_my_pe(),(pe*count)+i,dest[(pe*count)+i],
shmem_n_pes() + pe);
}
}
}
shmem_barrier_all();
shmem_free(dest);
shmem_free(source);
shmem_finalize();
return 0;
}
.ft P
.fi
.UNINDENT
.UNINDENT
.sp
\fBSEE ALSO:\fP
.INDENT 0.0
.INDENT 3.5
\fIintro_shmem\fP(3)
.UNINDENT
.UNINDENT
.SH COPYRIGHT
2003-2025, The Open MPI Community
.\" Generated by docutils manpage writer.
.