Wenkai Du
6021329af0
* 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>
21 líneas
1.0 KiB
C++
21 líneas
1.0 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2020, 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, ncclReduceScatter, const void* sendbuff, void* recvbuff, size_t recvcount,
|
|
ncclDataType_t datatype, ncclRedOp_t op, ncclComm* comm, hipStream_t stream);
|
|
ncclResult_t ncclReduceScatter(const void* sendbuff, void* recvbuff, size_t recvcount,
|
|
ncclDataType_t datatype, ncclRedOp_t op, ncclComm* comm, hipStream_t stream) {
|
|
NVTX3_FUNC_RANGE_IN(nccl_domain);
|
|
struct ncclInfo info = { ncclFuncReduceScatter, "ReduceScatter",
|
|
sendbuff, recvbuff, recvcount, datatype, op, 0, comm, stream, /* Args */
|
|
REDUCESCATTER_CHUNKSTEPS, REDUCESCATTER_SLICESTEPS };
|
|
return ncclEnqueueCheck(&info);
|
|
}
|