Sylvain Jeaugey
a8908b34ee
Optimization for Tree allreduce on A100.
Improve aggregation performance.
Use shared buffers for inter-node send/recv.
Add NVTX profiling hooks.
Accelerate alltoall connections by merging communication for all
channels.
Add support for one hop communication through NVLink, for faster
send/recv communication on cubemesh topologies like DGX-1.
Improve alltoall scheduling to better balance intra/inter node
communication.
Increase send/recv parallelism by 8x, each warp sending or
receiving to a different peer.
Net: move to v4.
Net: make flush operation asynchronous to accelerate alltoall.
Net: define maximum number of requests.
Fix hang when using LL128 protocol after 2^31 steps.
Fix #379 : topology injection failing when using less GPUs than
described in the XML.
Fix #394 : protocol mismatch causing hangs or crashes when using
one GPU per node.
[ROCm/rccl commit: 920dbe5b35]
28 라인
1.3 KiB
C++
28 라인
1.3 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2020, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#include "enqueue.h"
|
|
#include "collectives.h"
|
|
|
|
NCCL_API(ncclResult_t, ncclBroadcast, const void* sendbuff, void* recvbuff, size_t count, ncclDataType_t datatype, int root,
|
|
ncclComm_t comm, cudaStream_t stream);
|
|
ncclResult_t ncclBroadcast(const void* sendbuff, void* recvbuff, size_t count, ncclDataType_t datatype, int root,
|
|
ncclComm_t comm, cudaStream_t stream) {
|
|
NVTX3_FUNC_RANGE_IN(nccl_domain);
|
|
struct ncclInfo info = { ncclFuncBroadcast, "Broadcast",
|
|
sendbuff, recvbuff, count, datatype, ncclSum, root, comm, stream, /* Args */
|
|
BROADCAST_CHUNKSTEPS, BROADCAST_SLICESTEPS };
|
|
return ncclEnqueueCheck(&info);
|
|
}
|
|
/* Deprecated original "in place" function, similar to MPI */
|
|
NCCL_API(ncclResult_t, ncclBcast, void* buff, size_t count, ncclDataType_t datatype, int root,
|
|
ncclComm_t comm, cudaStream_t stream);
|
|
ncclResult_t ncclBcast(void* buff, size_t count, ncclDataType_t datatype, int root,
|
|
ncclComm_t comm, cudaStream_t stream) {
|
|
return ncclBroadcast(buff, buff, count, datatype, root, comm, stream);
|
|
}
|
|
|