Я работаю над проблемой MPI и хочу использовать Allreduce. Однако, это вызывает ошибку сегментации.
При работе с valgrind я получаю следующую трассировку стека
==1081== Memcheck, a memory error detector
==1081== Copyright (C) 2002-2017, and GNU GPL'd, by Julian Seward et al.
==1081== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==1081== Command: ./test
==1081==
==1081== Conditional jump or move depends on uninitialised value(s)
==1081== at 0x57D4375: opal_value_unload (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libopen-pal.so.20.10.1)
==1081== by 0x4E7F97A: ompi_proc_complete_init (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x4E838A4: ompi_mpi_init (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x4EA42AA: PMPI_Init (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x108CC2: main (test.c:53)
==1081== Uninitialised value was created by a stack allocation
==1081== at 0x4E7F90D: ompi_proc_complete_init (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081==
==1081== Invalid read of size 8
==1081== at 0x4C367EE: memmove (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x57E163F: ??? (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libopen-pal.so.20.10.1)
==1081== by 0x1170CEEC: mca_coll_self_allreduce_intra (in /usr/lib/x86_64-linux-gnu/openmpi/lib/openmpi/mca_coll_self.so)
==1081== by 0x4E92479: PMPI_Allreduce (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x108EA3: main (test.c:79)
==1081== Address 0xfaeaee8 is 0 bytes after a block of size 216 alloc'd
==1081== at 0x4C2FB0F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x108B4B: initCells (test.c:34)
==1081== by 0x108E4B: main (test.c:76)
==1081==
==1081== Invalid write of size 8
==1081== at 0x4C367E3: memmove (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x57E163F: ??? (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libopen-pal.so.20.10.1)
==1081== by 0x1170CEEC: mca_coll_self_allreduce_intra (in /usr/lib/x86_64-linux-gnu/openmpi/lib/openmpi/mca_coll_self.so)
==1081== by 0x4E92479: PMPI_Allreduce (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x108EA3: main (test.c:79)
==1081== Address 0xfaeadc8 is 0 bytes after a block of size 216 alloc'd
==1081== at 0x4C2FB0F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x108B4B: initCells (test.c:34)
==1081== by 0x108E3A: main (test.c:75)
==1081==
==1081== Invalid read of size 8
==1081== at 0x4C367E0: memmove (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x57E163F: ??? (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libopen-pal.so.20.10.1)
==1081== by 0x1170CEEC: mca_coll_self_allreduce_intra (in /usr/lib/x86_64-linux-gnu/openmpi/lib/openmpi/mca_coll_self.so)
==1081== by 0x4E92479: PMPI_Allreduce (in /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi.so.20.10.1)
==1081== by 0x108EA3: main (test.c:79)
==1081== Address 0xfaeaef8 is 16 bytes after a block of size 216 alloc'd
==1081== at 0x4C2FB0F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1081== by 0x108B4B: initCells (test.c:34)
==1081== by 0x108E4B: main (test.c:76)
==1081==
==1081==
==1081== HEAP SUMMARY:
==1081== in use at exit: 187,536 bytes in 698 blocks
==1081== total heap usage: 21,481 allocs, 20,783 frees, 4,286,585 bytes allocated
==1081==
==1081== LEAK SUMMARY:
==1081== definitely lost: 31,023 bytes in 40 blocks
==1081== indirectly lost: 2,121 bytes in 60 blocks
==1081== possibly lost: 0 bytes in 0 blocks
==1081== still reachable: 154,392 bytes in 598 blocks
==1081== suppressed: 0 bytes in 0 blocks
==1081== Rerun with --leak-check=full to see details of leaked memory
==1081==
==1081== For counts of detected and suppressed errors, rerun with: -v
==1081== ERROR SUMMARY: 19 errors from 4 contexts (suppressed: 0 from 0)
Код следующий
File: test.c
01: #include <stdlib.h>
02: #include <stdio.h>
03: #include <time.h>
04: #include <memory.h>
05: #include <mpi.h>
06: #include <stddef.h>
07: #include <math.h>
08: #include <unistd.h>
09:
10: typedef struct particle_t
11: {
12: double m;
13: double x;
14: double y;
15: double vx;
16: double vy;
17: double fx;
18: double fy;
19:
20: } particle_t;
21:
22: typedef struct centerMass
23: {
24: double x;
25: double y;
26: double totalmass;
27: } centerMass;
28:
29: int numprocs, my_rank;
30: MPI_Datatype particle_type, old_type;
31:
32: centerMass *initCells()
33: {
34: centerMass *gridMasses = (centerMass *)malloc(3 * 3 * sizeof(centerMass));
35: return gridMasses;
36: }
37:
38: void reduceMasses(centerMass *in, centerMass *inout, int *len, MPI_Datatype *dtpr)
39: {
40: for (int i = 0; i < *len; i++)
41: {
42: inout[i].totalmass += in[i].totalmass;
43: inout[i].x += in[i].x;
44: inout[i].y + in[i].y;
45: }
46: }
47:
48: int main(int argc, char *argv[])
49: {
50: // MPI initializations
51: MPI_Status status;
52: MPI_Init(&argc, &argv);
53: MPI_Comm_size(MPI_COMM_WORLD, &numprocs);
54: MPI_Comm_rank(MPI_COMM_WORLD, &my_rank);
55:
56: int count = 7;
57: MPI_Datatype types[] = {MPI_DOUBLE, MPI_DOUBLE, MPI_DOUBLE, MPI_DOUBLE, MPI_DOUBLE, MPI_DOUBLE, MPI_DOUBLE};
58: int blocklengths[] = {1, 1, 1, 1, 1, 1, 1};
59: MPI_Aint displacements[] = {
60: offsetof(particle_t, m),
61: offsetof(particle_t, x),
62: offsetof(particle_t, y),
63: offsetof(particle_t, vx),
64: offsetof(particle_t, vy),
65: offsetof(particle_t, fx),
66: offsetof(particle_t, fy),
67: };
68: MPI_Aint lb, extent;
69: MPI_Type_create_struct(count, blocklengths, displacements, types, &old_type);
70: MPI_Type_get_extent(old_type, &lb, &extent);
71: MPI_Type_create_resized(old_type, lb, extent, &particle_type);
72: MPI_Type_commit(&particle_type);
73:
74: centerMass *newMasses = initCells();
75: centerMass *oldMasses = initCells();
76: MPI_Op rM;
77: MPI_Op_create(reduceMasses, 1, &rM);
78: MPI_Allreduce(oldMasses, newMasses, 3 * 3, particle_type, rM, MPI_COMM_WORLD);
79:
80: MPI_Finalize();
81: }
82:
83:
84:
Я не могу сказать, что я делаю неправильно, потому что, если я прокомментирую предложение Allreduce, это сработает. Я посмотрел онлайн, и эта ошибка обычно связана с нулевыми завершающими строками, которые я вообще не использую.
Спасибо