2.8.4-1
Fix hang in corner cases of alltoallv using point to point send/recv. Harmonize error messages. Fix missing NVTX section in the license. Update README.
This commit is contained in:
+2
-2
@@ -581,7 +581,7 @@ static ncclResult_t initTransportsRank(struct ncclComm* comm, ncclUniqueId* comm
|
||||
for (int i = 0; i < nranks; i++) {
|
||||
memcpy(comm->peerInfo+i, &allGather1Data[i].peerInfo, sizeof(struct ncclPeerInfo));
|
||||
if ((i != rank) && (comm->peerInfo[i].hostHash == myInfo->hostHash) && (comm->peerInfo[i].busId == myInfo->busId)) {
|
||||
WARN("Duplicate GPU detected : rank %d and rank %d both on CUDA device %x", rank, i, myInfo->busId);
|
||||
WARN("Duplicate GPU detected : rank %d and rank %d both on CUDA device %lx", rank, i, myInfo->busId);
|
||||
return ncclInvalidUsage;
|
||||
}
|
||||
}
|
||||
@@ -878,7 +878,7 @@ ncclResult_t ncclCommInitRankSync(ncclComm_t* newcomm, int nranks, ncclUniqueId
|
||||
NCCLCHECKGOTO(initTransportsRank(*newcomm, &commId), res, cleanup);
|
||||
NCCLCHECKGOTO(devCommSetup(*newcomm), res, cleanup);
|
||||
|
||||
INFO(NCCL_INIT,"comm %p rank %d nranks %d cudaDev %d busId %x - Init COMPLETE", *newcomm, myrank, nranks, (*newcomm)->cudaDev, (*newcomm)->busId);
|
||||
INFO(NCCL_INIT,"comm %p rank %d nranks %d cudaDev %d busId %lx - Init COMPLETE", *newcomm, myrank, nranks, (*newcomm)->cudaDev, (*newcomm)->busId);
|
||||
|
||||
return ncclSuccess;
|
||||
cleanup:
|
||||
|
||||
Reference in New Issue
Block a user