Wenkai Du
4f7d5f85ec
* 2.9.6-1
Add support for CUDA graphs.
Fuse BCM Gen4 switches to avoid suboptimal performance on some platforms. Issue #439.
Fix bootstrap issue caused by connection reordering.
Fix CPU locking block.
Improve CollNet algorithm.
Improve performance on DGX A100 for communicators with only one GPU per node.
* Clique tuning upgrade (#352) (#19)
* Enabling clique for any XGMI-connected topology, adding tuning
* Updating CHANGELOG for clique tuning
* Re-working clique barrier system to work on multi-process / multi-gpu
Co-authored-by: Sylvain Jeaugey <sjeaugey@nvidia.com>
Co-authored-by: gilbertlee-amd <44450918+gilbertlee-amd@users.noreply.github.com>
[ROCm/rccl commit: 6021329af0]
30 lines
1.3 KiB
C++
30 lines
1.3 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2019, NVIDIA CORPORATION. All rights reserved.
|
|
* Modifications Copyright (c) 2019-2021 Advanced Micro Devices, Inc. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#include "enqueue.h"
|
|
#include "collectives.h"
|
|
|
|
NCCL_API(ncclResult_t, ncclGather, const void* sendbuff, void* recvbuff, size_t sendcount,
|
|
ncclDataType_t datatype, int root, ncclComm_t comm, hipStream_t stream);
|
|
ncclResult_t ncclGather(const void* sendbuff, void* recvbuff, size_t sendcount,
|
|
ncclDataType_t datatype, int root, ncclComm_t comm, hipStream_t stream) {
|
|
int nRanks;
|
|
NCCLCHECK(ncclCommCount(comm, &nRanks));
|
|
size_t rankOffset = sendcount * ncclTypeSize(datatype);
|
|
if (sendcount == 0) return ncclSuccess;
|
|
int rank;
|
|
NCCLCHECK(ncclCommUserRank(comm, &rank));
|
|
NCCLCHECK(ncclGroupStart());
|
|
if (rank == root) {
|
|
for (int r=0; r<nRanks; r++)
|
|
NCCLCHECK(ncclRecv(((char*)recvbuff)+r*rankOffset, sendcount, datatype, r, comm, stream));
|
|
}
|
|
NCCLCHECK(ncclSend(sendbuff, sendcount, datatype, root, comm, stream));
|
|
NCCLCHECK(ncclGroupEnd());
|
|
return ncclSuccess;
|
|
}
|