46b6db1a4c
* Submitting jobs to cdash * Fail on submit * submit url env * submit url env * try passing submit url as arg * fix submit url * Updated default URL * Add submissions for remaining ubuntu focal workflow jobs * Replace g++ with gcc in dashboard build name * Add --ctest-args to run-ci.sh * Add cdash support for bionic, jammy, and opensuse workflows * Decrease CTEST_CUSTOM_MAXIMUM_PASSED_TEST_OUTPUT_SIZE * OMNITRACE_BUILD_CODECOV option * Support code coverage in CDash script * CI dyninst built with debug info * Update ci-containers - cron schedule moved 4 hours later to UTC+5 * Update implementation of config::configure_signal_handler - using lambdas failed to compile with codecov flags * Add codecov job to ubuntu focal workflow * Fix support for --ctest-args in run-ci script * Fix ubuntu workflows * Fix quotation handling in run-ci script * git safe directory for codecov * New MPI examples * Remove --stop-on-failure * dynamic_library update - find_library_path checks procfs maps - invoke find_library_path with no additional args to resolve to mapped file * RCCLP uses dynamic_library * check if file exists for memory_map_files metadata * Testing updates - include new mpi examples in tests - fix test labels - test critical-trace exe * Update MPI C examples tests (needed arg) * Remove try/catch block from critical-trace * Fix sampling max wait when shutting down * Fix test env for critical-trace * Fix settings for critical-trace - disable time output: data is deterministic - disable PID suffixes: not multiprocess * Update critical-trace ctest * Update critical-trace exe - throw error if input cannot be opened - throw error if input has no data * Update lulesh example with more kokkos tools usage * Fix tasking issue with critical_trace and roctracer - were not setting pools to active - also sync before critical_trace::get_entries * Increase verbosity of critical-trace tests * Update code coverage tests - skip code coverage + preload - code-coverage python example and test * Remove duplication omnitrace.initialize function * Skip python3.6 for ubuntu jammy * Update MPI examples - use MPI_Isend and MPI_Irecv - explicitly use MPI_Bcast * Update Formatting.cmake - include C files in examples * run-ci script does not check return of coverage * mpi-allreduce link to libm * Update ctest args in run-ci script * Update dyninst submodule - safety improvements in BinaryEdit::openResolvedLibraryName * capture cmake error for ctest_coverage
108 lignes
3.2 KiB
C
108 lignes
3.2 KiB
C
// Author: Wes Kendall
|
|
// Copyright 2012 www.mpitutorial.com
|
|
// This code is provided freely with the tutorials on mpitutorial.com. Feel
|
|
// free to modify it for your own use. Any distribution of the code must
|
|
// either provide a link to www.mpitutorial.com or keep this header intact.
|
|
//
|
|
// Program that computes the average of an array of elements in parallel using
|
|
// MPI_Scatter and MPI_Allgather
|
|
//
|
|
#include <assert.h>
|
|
#include <mpi.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <time.h>
|
|
|
|
// Creates an array of random numbers. Each number has a value from 0 - 1
|
|
float*
|
|
create_rand_nums(int num_elements)
|
|
{
|
|
float* rand_nums = (float*) malloc(sizeof(float) * num_elements);
|
|
assert(rand_nums != NULL);
|
|
int i;
|
|
for(i = 0; i < num_elements; i++)
|
|
{
|
|
rand_nums[i] = (rand() / (float) RAND_MAX);
|
|
}
|
|
return rand_nums;
|
|
}
|
|
|
|
// Computes the average of an array of numbers
|
|
float
|
|
compute_avg(float* array, int num_elements)
|
|
{
|
|
float sum = 0.f;
|
|
int i;
|
|
for(i = 0; i < num_elements; i++)
|
|
{
|
|
sum += array[i];
|
|
}
|
|
return sum / num_elements;
|
|
}
|
|
|
|
int
|
|
main(int argc, char** argv)
|
|
{
|
|
if(argc != 2)
|
|
{
|
|
fprintf(stderr, "Usage: avg num_elements_per_proc\n");
|
|
exit(1);
|
|
}
|
|
|
|
int num_elements_per_proc = atoi(argv[1]);
|
|
// Seed the random number generator to get different results each time
|
|
srand(time(NULL));
|
|
|
|
MPI_Init(NULL, NULL);
|
|
|
|
int world_rank;
|
|
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
|
|
int world_size;
|
|
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
|
|
|
|
// Create a random array of elements on the root process. Its total
|
|
// size will be the number of elements per process times the number
|
|
// of processes
|
|
float* rand_nums = NULL;
|
|
if(world_rank == 0)
|
|
{
|
|
rand_nums = create_rand_nums(num_elements_per_proc * world_size);
|
|
}
|
|
|
|
// For each process, create a buffer that will hold a subset of the entire
|
|
// array
|
|
float* sub_rand_nums = (float*) malloc(sizeof(float) * num_elements_per_proc);
|
|
assert(sub_rand_nums != NULL);
|
|
|
|
// Scatter the random numbers from the root process to all processes in
|
|
// the MPI world
|
|
MPI_Scatter(rand_nums, num_elements_per_proc, MPI_FLOAT, sub_rand_nums,
|
|
num_elements_per_proc, MPI_FLOAT, 0, MPI_COMM_WORLD);
|
|
|
|
// Compute the average of your subset
|
|
float sub_avg = compute_avg(sub_rand_nums, num_elements_per_proc);
|
|
|
|
// Gather all partial averages down to all the processes
|
|
float* sub_avgs = (float*) malloc(sizeof(float) * world_size);
|
|
assert(sub_avgs != NULL);
|
|
MPI_Allgather(&sub_avg, 1, MPI_FLOAT, sub_avgs, 1, MPI_FLOAT, MPI_COMM_WORLD);
|
|
|
|
// Now that we have all of the partial averages, compute the
|
|
// total average of all numbers. Since we are assuming each process computed
|
|
// an average across an equal amount of elements, this computation will
|
|
// produce the correct answer.
|
|
float avg = compute_avg(sub_avgs, world_size);
|
|
printf("Avg of all elements from proc %d is %f\n", world_rank, avg);
|
|
|
|
// Clean up
|
|
if(world_rank == 0)
|
|
{
|
|
free(rand_nums);
|
|
}
|
|
free(sub_avgs);
|
|
free(sub_rand_nums);
|
|
|
|
MPI_Barrier(MPI_COMM_WORLD);
|
|
MPI_Finalize();
|
|
}
|