AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement RCCL Replayer (#817)

Browse Source 
* Implement RCCL Replayer
This commit is contained in:
Bertan Dogancay
2023-07-24 16:26:22 -06:00
committed by GitHub
parent a7fcd58a97
commit 8bab4f04b7
5 changed files with 666 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/enqueue.cc
+5 -3
View File
@@ -1616,9 +1616,11 @@ ncclResult_t ncclEnqueueCheck(struct ncclInfo* info) {
}
NCCLCHECKGOTO(ArgsCheck(info), ret, fail);
INFO(NCCL_COLL,"%s: opCount %lx sendbuff %p recvbuff %p count %zi datatype %d op %d root %d comm %p [nranks=%d] stream %p",
info->opName, info->comm->opCount, info->sendbuff, info->recvbuff, info->count,
info->datatype, info->op, info->root, info->comm, info->comm->nRanks, info->stream);
INFO(NCCL_COLL,"%s: opCount %lx sendbuff %p recvbuff %p count %zi datatype %d op %d root %d comm %p [nranks=%d] stream %p task %d globalrank %d",
info->opName, info->comm->opCount, info->sendbuff, info->recvbuff, info->count,
info->datatype, info->op, info->root, info->comm, info->comm->nRanks, info->stream,
info->comm->tasks.nTasksP2p + info->comm->tasks.nTasksColl,
info->comm->localRankToRank[info->comm->localRank]);
TRACE_CALL("nccl%s(%" PRIx64 ",%" PRIx64 ",%zi,%d,%d,%d,%p,%p)", info->opName, reinterpret_cast<int64_t>(info->sendbuff), reinterpret_cast<int64_t>(info->recvbuff), info->count, info->datatype, info->op, info->root, info->comm, info->stream);
NCCLCHECKGOTO(taskAppend(info->comm, info), ret, fail);