Skip to content

GPU: Tentative workaround for MI100 serialization bug #14327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
davidrohr merged 1 commit into from
May 26, 2025
Merged

GPU: Tentative workaround for MI100 serialization bug #14327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions GPU/GPUTracking/Definitions/GPUSettingsList.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,6 +370,7 @@ AddOption(debugOnFailureMaxN, uint32_t, 1, "", 0, "Max number of times to run th
AddOption(debugOnFailureMaxFiles, uint32_t, 0, "", 0, "Max number of files to have in the target folder")
AddOption(debugOnFailureMaxSize, uint32_t, 0, "", 0, "Max size of existing dumps in the target folder in GB")
AddOption(debugOnFailureDirectory, std::string, ".", "", 0, "Target folder for debug / dump")
AddOption(amdMI100SerializationWorkaround, bool, false, "", 0, "Enable workaround that mitigates MI100 serialization bug")
AddVariable(eventDisplay, o2::gpu::GPUDisplayFrontendInterface*, nullptr)
AddSubConfig(GPUSettingsProcessingRTC, rtc)
AddSubConfig(GPUSettingsProcessingRTCtechnical, rtctech)
Expand Down
3 changes: 3 additions & 0 deletions GPU/GPUTracking/Global/GPUChainTrackingSectorTracker.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,6 +161,9 @@ int32_t GPUChainTracking::RunTPCTrackingSectors_internal()
GPUTPCTracker& trk = processors()->tpcTrackers[iSector];
GPUTPCTracker& trkShadow = doGPU ? processorsShadow()->tpcTrackers[iSector] : trk;
int32_t useStream = StreamForSector(iSector);
if (GetProcessingSettings().amdMI100SerializationWorkaround) {
SynchronizeStream(useStream); // TODO: Remove this workaround once fixed on MI100
}

if (GetProcessingSettings().debugLevel >= 3) {
GPUInfo("Creating Sector Data (Sector %d)", iSector);
Expand Down
Loading