Stanley Tsang
d00b7d17bd
* Fixing temp file creation/deletion for Clique kernel mode. * Refactoring of MP unit tests; include bugfixes and general support for any number of GPUs * GroupCall MP UT properly quits when too many devices specified * MP UT will programmatically set NCCL_COMM_ID if not specified; updated install script
68 líneas
2.5 KiB
C++
68 líneas
2.5 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2019-2021 Advanced Micro Devices, Inc. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#include "test_BroadcastMultiProcess.hpp"
|
|
|
|
#include <stdio.h>
|
|
#include <unistd.h>
|
|
#include <sys/mman.h>
|
|
#include <sys/types.h>
|
|
#include <sys/wait.h>
|
|
#include <iostream>
|
|
|
|
namespace CorrectnessTests
|
|
{
|
|
TEST_P(BroadcastMultiProcessCorrectnessTest, Correctness)
|
|
{
|
|
dataset->InitializeRootProcess(numDevices, numElements, dataType, inPlace, ncclCollBroadcast);
|
|
std::vector<int> pids(numDevices);
|
|
|
|
int gpu = -1;
|
|
for (int i = 0; i < numDevices; i++)
|
|
{
|
|
gpu++;
|
|
int pid = fork();
|
|
if (pid == 0)
|
|
{
|
|
bool pass;
|
|
TestBroadcast(gpu, *dataset, pass);
|
|
TerminateChildProcess(pass);
|
|
}
|
|
else
|
|
{
|
|
pids[gpu] = pid;
|
|
}
|
|
}
|
|
|
|
ValidateProcesses(pids);
|
|
}
|
|
|
|
INSTANTIATE_TEST_SUITE_P(BroadcastMultiProcessCorrectnessSweep,
|
|
BroadcastMultiProcessCorrectnessTest,
|
|
testing::Combine(
|
|
// Reduction operator is not used
|
|
testing::Values(ncclSum),
|
|
// Data types
|
|
testing::Values(ncclInt8,
|
|
ncclUint8,
|
|
ncclInt32,
|
|
ncclUint32,
|
|
ncclInt64,
|
|
ncclUint64,
|
|
//ncclFloat16,
|
|
ncclFloat32,
|
|
ncclFloat64,
|
|
ncclBfloat16),
|
|
// Number of elements
|
|
testing::Values(1024, 1048576),
|
|
// Number of devices
|
|
testing::Values(2,3,4,8),
|
|
// In-place or not
|
|
testing::Values(false, true),
|
|
testing::Values("")),
|
|
CorrectnessTest::PrintToStringParamName());
|
|
} // namespace
|