yezhengmao/nccl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[bugfix]save undo plans in some case

Browse Source
This commit is contained in:
FrankJ 2024-03-12 00:00:16 +08:00
parent 48bb7fec79
commit 9ef920a77b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/group.cc
View File

@ -142,7 +142,7 @@ static ncclResult_t doLaunches(struct ncclComm* head) {
} }
while (true) { // Iterate rounds of launches for clique. while (true) { // Iterate rounds of launches for clique.
bool moreRounds; bool moreRounds = false;
comm = cliqueHead; comm = cliqueHead;
do { // Iterate clique members. do { // Iterate clique members.
struct ncclComm* next = comm->groupNext; struct ncclComm* next = comm->groupNext;
@ -150,7 +150,7 @@ static ncclResult_t doLaunches(struct ncclComm* head) {
// Barrier reduction result tells us if this was the final round. // Barrier reduction result tells us if this was the final round.
moreRounds = 0 != ncclCommIntraBarrierOut(comm); moreRounds = 0 != ncclCommIntraBarrierOut(comm);
} else { } else {
moreRounds = comm->unlaunchedPlansHead != nullptr; moreRounds |= comm->unlaunchedPlansHead != nullptr;
} }
if (moreRounds) { if (moreRounds) {
// Pop next unlaunched kernel // Pop next unlaunched kernel