[rocm_regression] Return errors when HSA_NO_SCRATCH_RECLAIM=1 even for rocm>=6.4.0 (#1867)
* [rocm_regression] Return errors when HSA_NO_SCRATCH_RECLAIM=1 even for rocm >= 6.4.0
* [rocm_regression] Check firmware version
* [rocm_regression] Resolve review comments
* [rocm_regression] Move hsa env checking into init once func
* [rocm_regression] Prevent hot fix version in firmware
* [rocm_regression] Improve unit tests
[ROCm/rccl commit: 361d596229]
Tento commit je obsažen v:
@@ -91,4 +91,6 @@ void rcclSetPxn(struct ncclComm* comm, int& rcclPxnDisable);
|
||||
void rcclSetP2pNetChunkSize(struct ncclComm* comm, int& rcclP2pNetChunkSize);
|
||||
ncclResult_t rcclFuncMaxSendRecvCount(ncclFunc_t func, int nRanks, size_t count, size_t& maxCount);
|
||||
ncclResult_t commSetUnrollFactor(struct ncclComm* comm);
|
||||
bool validHsaScratchEnvSetting(const char*hsaScratchEnv, int hipRuntimeVersion, int firmwareVersion, const char* archName);
|
||||
int parseFirmwareVersion(const char* command);
|
||||
#endif
|
||||
|
||||
Odkázat v novém úkolu
Zablokovat Uživatele