Move MSCCL algorithm loading to initialization to workaround HIP graph conflict (#982)
* MSCCL: pre-specify channels and pre-load algorithms
* add mutex
* fix bug
* clean include
* disable all-gathers temporarily
[ROCm/rccl commit: 4bb0b4a380]
Этот коммит содержится в:
@@ -18,6 +18,8 @@ bool mscclIsCaller();
|
||||
|
||||
bool mscclAvailable();
|
||||
|
||||
ncclResult_t mscclSchedulerInit(ncclComm_t comm, int* numChannelsRequired);
|
||||
|
||||
ncclResult_t mscclInit(ncclComm_t comm);
|
||||
|
||||
ncclResult_t mscclGroupStart();
|
||||
|
||||
@@ -91,6 +91,8 @@ struct mscclAlgoMeta {
|
||||
std::string filePath;
|
||||
// number of chunks of input/output in each MSCCL algorithm loop
|
||||
int nChunksPerLoop;
|
||||
// number of channels needed by MSCCL algorithm
|
||||
int nChannels;
|
||||
// number of ranks required by this algorithm
|
||||
int nRanks;
|
||||
// need to times nRanks for all-gather, reduce-scatter and all-to-all
|
||||
|
||||
Ссылка в новой задаче
Block a user