Support fused all reduce and elementwise operations (#1729)
* Support fused all reduce and elementwise operations Add additional "acc" parameter to RCCL Replayer logs Add flag which indicates availability of new API * Fix Recorder json parsing * Remove unreachable code * Remove extra acc pointer check * . * Revert "[DEVICE] Adding ability to choose unroll factor at runtime (#1734)" This reverts commit4cadf3597c. * Use noinline to reduce kernels linking time * Don't use noinline for gfx942 and gfx950 to avoid perf regression --------- Co-authored-by: AtlantaPepsi <timhu102@amd.com> Co-authored-by: BertanDogancay <bertan.dogancay@gmail.com> [ROCm/rccl commit:9a4213356d]
This commit is contained in:
@@ -610,6 +610,8 @@ 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;
|
||||
|
||||
@@ -1958,9 +1960,6 @@ 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) {
|
||||
|
||||
Reference in New Issue
Block a user