intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-04 15:53:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

performance: emit fence on immediate copy engine only for blocking calls

Browse Source 
- this change handles level zero immediate command lists on copy engine
- monitor fence will be dispatched for blocking calls
- asynchronous mode will dispatch monitor fence only on host synchronization

Related-To: NEO-8395

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
This commit is contained in:
Zbigniew Zdanowicz
2023-09-22 12:00:37 +00:00
committed by Compute-Runtime-Automation
parent f19898d178
commit d725d454ea
2 changed files with 46 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
shared/source/command_stream/command_stream_receiver_hw_base.inl
View File

@@ -237,7 +237,7 @@ CompletionStamp CommandStreamReceiverHw<GfxFamily>::flushBcsTask(LinearStream &c
BatchBuffer batchBuffer{streamToSubmit.getGraphicsAllocation(), startOffset, 0, taskStartAddress, nullptr,
false, QueueThrottle::MEDIUM, NEO::QueueSliceCount::defaultSliceCount,
streamToSubmit.getUsed(), &streamToSubmit, bbEndLocation, this->getNumClients(), (submitCSR || dispatchBcsFlags.hasStallingCmds),
dispatchBcsFlags.hasRelaxedOrderingDependencies, false};
dispatchBcsFlags.hasRelaxedOrderingDependencies, dispatchBcsFlags.flushTaskCount};
updateStreamTaskCount(streamToSubmit, taskCount + 1);