MPI_Reduce 是否需要接收缓冲区的现有指针?
Does MPI_Reduce need an existing pointer for the receive buffer?
MPI documentation asserts that the adress of address of the receive buffer (recvbuf
) is significant only at root. Meaning that the memory may not be allocated in the other processes. This is confirmed by this question.
int MPI_Reduce(const void *sendbuf, void *recvbuf, int count, MPI_Datatype datatype,
MPI_Op op, int root, MPI_Comm comm)
起初我认为 recvbuf
甚至不必存在:recvbuf
本身的内存不必分配(例如通过动态分配)。不幸的是(我花了很多时间才明白我的错误!),似乎即使它指向的内存无效,指针本身也必须存在。
请参阅下面的代码,其中一个版本会出现段错误,而另一个版本不会。
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
int main(int argc, char **argv) {
// MPI initialization
int world_rank, world_size;
MPI_Init(NULL, NULL);
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
int n1 = 3, n2 = 10; // Sizes of the 2d arrays
long **observables = (long **) malloc(n1 * sizeof(long *));
for (int k = 0 ; k < n1 ; ++k) {
observables[k] = (long *) calloc(n2, sizeof(long));
for (long i = 0 ; i < n2 ; ++i) {
observables[k][i] = k * i * world_rank; // Whatever
}
}
long **obs_sum; // This will hold the sum on process 0
#ifdef OLD // Version that gives a segfault
if (world_rank == 0) {
obs_sum = (long **) malloc(n2 * sizeof(long *));
for (int k = 0 ; k < n2 ; ++k) {
obs_sum[k] = (long *) calloc(n2, sizeof(long));
}
}
#else // Correct version
// We define all the pointers in all the processes.
obs_sum = (long **) malloc(n2 * sizeof(long *));
if (world_rank == 0) {
for (int k = 0 ; k < n2 ; ++k) {
obs_sum[k] = (long *) calloc(n2, sizeof(long));
}
}
#endif
for (int k = 0 ; k < n1 ; ++k) {
// This is the line that results in a segfault if OLD is defined
MPI_Reduce(observables[k], obs_sum[k], n2, MPI_LONG, MPI_SUM, 0,
MPI_COMM_WORLD);
}
MPI_Barrier(MPI_COMM_WORLD);
MPI_Finalize();
// You may free memory here
return 0;
}
我的解释正确吗?这种行为背后的基本原理是什么?
问题不是 MPI,而是您正在通过 obs_sum[k]
,但您根本没有 defined/allocated。
for (int k = 0 ; k < n1 ; ++k) {
// This is the line that results in a segfault if OLD is defined
MPI_Reduce(observables[k], obs_sum[k], n2, MPI_LONG, MPI_SUM, 0,
MPI_COMM_WORLD);
}
即使 MPI_Reduce()
没有得到它的值,生成的代码也会得到 obs_sum
(未定义且未分配),向其添加 k
并尝试读取此指针(段错误)传递给 MPI_Reduce()
.
例如,行的分配应该足以使其工作:
#else // Correct version
// We define all the pointers in all the processes.
obs_sum = (long **) malloc(n2 * sizeof(long *));
// try commenting out the following lines
// if (world_rank == 0) {
// for (int k = 0 ; k < n2 ; ++k) {
// obs_sum[k] = (long *) calloc(n2, sizeof(long));
// }
// }
#endif
我会将二维数组分配为平面数组 - 我真的讨厌这种数组表示法。这样不是更好吗?
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
int main(int argc, char **argv) {
// MPI initialization
int world_rank, world_size;
MPI_Init(NULL, NULL);
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
int n1 = 3, n2 = 10; // Sizes of the 2d arrays
long *observables = (long *) malloc(n1*n2*sizeof(long));
for (int k = 0 ; k < n1 ; ++k) {
for (long i = 0 ; i < n2 ; ++i) {
observables[k*n2+i] = k * i * world_rank; // Whatever
}
}
long *obs_sum = nullptr; // This will hold the sum on process 0
if (world_rank == 0) {
obs_sum = (long *) malloc(n1*n2*sizeof(long));
}
MPI_Reduce(observables, obs_sum, n1*n2, MPI_LONG, MPI_SUM, 0, MPI_COMM_WORLD);
MPI_Barrier(MPI_COMM_WORLD);
MPI_Finalize();
// You may free memory here
return 0;
}
MPI documentation asserts that the adress of address of the receive buffer (recvbuf
) is significant only at root. Meaning that the memory may not be allocated in the other processes. This is confirmed by this question.
int MPI_Reduce(const void *sendbuf, void *recvbuf, int count, MPI_Datatype datatype,
MPI_Op op, int root, MPI_Comm comm)
起初我认为 recvbuf
甚至不必存在:recvbuf
本身的内存不必分配(例如通过动态分配)。不幸的是(我花了很多时间才明白我的错误!),似乎即使它指向的内存无效,指针本身也必须存在。
请参阅下面的代码,其中一个版本会出现段错误,而另一个版本不会。
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
int main(int argc, char **argv) {
// MPI initialization
int world_rank, world_size;
MPI_Init(NULL, NULL);
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
int n1 = 3, n2 = 10; // Sizes of the 2d arrays
long **observables = (long **) malloc(n1 * sizeof(long *));
for (int k = 0 ; k < n1 ; ++k) {
observables[k] = (long *) calloc(n2, sizeof(long));
for (long i = 0 ; i < n2 ; ++i) {
observables[k][i] = k * i * world_rank; // Whatever
}
}
long **obs_sum; // This will hold the sum on process 0
#ifdef OLD // Version that gives a segfault
if (world_rank == 0) {
obs_sum = (long **) malloc(n2 * sizeof(long *));
for (int k = 0 ; k < n2 ; ++k) {
obs_sum[k] = (long *) calloc(n2, sizeof(long));
}
}
#else // Correct version
// We define all the pointers in all the processes.
obs_sum = (long **) malloc(n2 * sizeof(long *));
if (world_rank == 0) {
for (int k = 0 ; k < n2 ; ++k) {
obs_sum[k] = (long *) calloc(n2, sizeof(long));
}
}
#endif
for (int k = 0 ; k < n1 ; ++k) {
// This is the line that results in a segfault if OLD is defined
MPI_Reduce(observables[k], obs_sum[k], n2, MPI_LONG, MPI_SUM, 0,
MPI_COMM_WORLD);
}
MPI_Barrier(MPI_COMM_WORLD);
MPI_Finalize();
// You may free memory here
return 0;
}
我的解释正确吗?这种行为背后的基本原理是什么?
问题不是 MPI,而是您正在通过 obs_sum[k]
,但您根本没有 defined/allocated。
for (int k = 0 ; k < n1 ; ++k) {
// This is the line that results in a segfault if OLD is defined
MPI_Reduce(observables[k], obs_sum[k], n2, MPI_LONG, MPI_SUM, 0,
MPI_COMM_WORLD);
}
即使 MPI_Reduce()
没有得到它的值,生成的代码也会得到 obs_sum
(未定义且未分配),向其添加 k
并尝试读取此指针(段错误)传递给 MPI_Reduce()
.
例如,行的分配应该足以使其工作:
#else // Correct version
// We define all the pointers in all the processes.
obs_sum = (long **) malloc(n2 * sizeof(long *));
// try commenting out the following lines
// if (world_rank == 0) {
// for (int k = 0 ; k < n2 ; ++k) {
// obs_sum[k] = (long *) calloc(n2, sizeof(long));
// }
// }
#endif
我会将二维数组分配为平面数组 - 我真的讨厌这种数组表示法。这样不是更好吗?
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
int main(int argc, char **argv) {
// MPI initialization
int world_rank, world_size;
MPI_Init(NULL, NULL);
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
int n1 = 3, n2 = 10; // Sizes of the 2d arrays
long *observables = (long *) malloc(n1*n2*sizeof(long));
for (int k = 0 ; k < n1 ; ++k) {
for (long i = 0 ; i < n2 ; ++i) {
observables[k*n2+i] = k * i * world_rank; // Whatever
}
}
long *obs_sum = nullptr; // This will hold the sum on process 0
if (world_rank == 0) {
obs_sum = (long *) malloc(n1*n2*sizeof(long));
}
MPI_Reduce(observables, obs_sum, n1*n2, MPI_LONG, MPI_SUM, 0, MPI_COMM_WORLD);
MPI_Barrier(MPI_COMM_WORLD);
MPI_Finalize();
// You may free memory here
return 0;
}