f40ce73e89
Added detection of IBM/Power NVLink bridge device.
Add NUMA support to PCI distance calculations.
Added NCCL_IGNORE_CPU_AFFINITY env var.
Fix memory leaks; GithubIssue#180
Compiler warning fix; GithubIssue#178
Replace non-standard variable length arrays. GithubIssue#171
Fix Tree+Shared Memory crash. GithubPR#185
Fix LL cleanup hang during long running DL jobs.
Fix NCCL_RINGS environment variable handling.
Added extra checks to catch repeat calls to ncclCommDestroy() GithubIssue#191
Improve bootstrap socket connection reliability at scale.
Fix hostname hashing issue. GithubIssue#187
Code cleanup to rename all non device files from *.cu to *.cc
19 lines
854 B
C++
19 lines
854 B
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2019, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#include "enqueue.h"
|
|
#include "collectives.h"
|
|
|
|
NCCL_API(ncclResult_t, ncclAllGather, const void* sendbuff, void* recvbuff, size_t sendcount,
|
|
ncclDataType_t datatype, ncclComm_t comm, cudaStream_t stream);
|
|
ncclResult_t ncclAllGather(const void* sendbuff, void* recvbuff, size_t sendcount,
|
|
ncclDataType_t datatype, ncclComm_t comm, cudaStream_t stream) {
|
|
struct ncclInfo info = { ncclCollAllGather, "AllGather",
|
|
sendbuff, recvbuff, sendcount, datatype, ncclSum, 0, comm, stream, /* Args */
|
|
ALLGATHER_CHUNKSTEPS, ALLGATHER_SLICESTEPS };
|
|
return ncclEnqueueCheck(&info);
|
|
}
|