Fix MSCCLPP seg-fault when RCCL_MSCCL_ENABLE_SINGLE_PROCESS is enabled (#1338)

Removing unnecessary changes.

rename unique hosts function

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

use updated function name

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

Missed one instance of `mscclIsMultithreadedComm`.

rename unique hosts function

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

use updated function name

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

Missed one instance of `mscclIsMultithreadedComm`.


[ROCm/rccl commit: 2fe1e9f7db]
Tá an tiomantas seo le fáil i:
Mustafa Abduljabbar
2024-09-18 15:19:33 -05:00
tiomanta ag nileshnegi
tuismitheoir d4094525c8
tiomantas 13f6bbde57
+11 -8
Féach ar an gComhad
@@ -63,12 +63,7 @@ bool mscclAvailable(int rank) {
return mscclEnabled() && mscclInitialized(rank);
}
static bool mscclCommCompatible(ncclComm_t comm) {
if (rcclParamMscclEnableSingleProcess()) {
// Single process usage enabled. No need to guard against multi-thread.
return true;
}
static bool allProcessHostsUnique(ncclComm_t comm) {
std::map<uint64_t, std::set<uint64_t>> hostHashToPidHashes;
for (int i = 0; i < comm->nRanks; i++) {
uint64_t hostHash = comm->peerInfo[i].hostHash;
@@ -84,9 +79,17 @@ static bool mscclCommCompatible(ncclComm_t comm) {
return true;
}
#ifdef ENABLE_MSCCLPP
static bool mscclCommCompatible(ncclComm_t comm) {
if (rcclParamMscclEnableSingleProcess()) {
// Single process usage enabled. No need to guard against multi-thread.
return true;
}
return allProcessHostsUnique(comm);
}
#ifdef ENABLE_MSCCLPP
bool mscclppCommCompatible(ncclComm_t comm) {
return mscclCommCompatible(comm);
return allProcessHostsUnique(comm);
}
#endif