[DEVICE] Add unroll=2 for gfx950 multi-node (#1824)

[ROCm/rccl commit: bd55f876e9]

projects/rccl/src/init.cc

@@ -612,8 +612,7 @@ static ncclResult_t commAlloc(struct ncclComm* comm, struct ncclComm* parent, in
 
   // RCCL: create persistent stream for calloc
   CUDACHECK(hipStreamCreateWithFlags(&comm->sideStream, hipStreamNonBlocking));
-  // RCCL: determine and set unroll factor for comm
-  NCCLCHECK(commSetUnrollFactor(comm));
+
   comm->checkPointers = ncclParamCheckPointers() == 1 ? true : false;
   comm->dmaBufSupport = (dmaBufSupported(comm) == ncclSuccess) ? true : false;
 
@@ -1965,6 +1964,9 @@ static ncclResult_t ncclCommInitRankFunc(struct ncclAsyncJob* job_) {
 
   NCCLCHECKGOTO(initTransportsRank(comm, job->parent, timers), res, fail);
 
+  // RCCL: determine and set unroll factor for comm
+  NCCLCHECK(commSetUnrollFactor(comm));
+
 #ifdef ENABLE_MSCCLPP
   if (job->parent) {
     if (job->parent->mscclppCompatible) {