intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-03 14:55:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use DSS when calculating max wgs on TGLLP and DG1

Browse Source 
Use DualSubSlice count instead of SubSlice count when calculating wgs on
TigerLake LP and DashG1.

Related-To: NEO-5719

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
This commit is contained in:
Krystian Chmielewski
2022-10-17 15:21:37 +00:00
committed by Compute-Runtime-Automation
parent 5bd4b9eb48
commit 510ba12cbc
2 changed files with 30 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
shared/source/gen12lp/os_agnostic_hw_info_config_gen12lp.inl
View File

@@ -23,4 +23,9 @@ void HwInfoConfigHw<gfxProduct>::adjustSamplerState(void *sampler, const Hardwar
if (DebugManager.flags.ForceSamplerLowFilteringPrecision.get()) {
samplerState->setLowQualityFilter(SAMPLER_STATE::LOW_QUALITY_FILTER_ENABLE);
}
}
template <>
uint32_t HwInfoConfigHw<gfxProduct>::getMaxThreadsForWorkgroupInDSSOrSS(const HardwareInfo &hwInfo, uint32_t maxNumEUsPerSubSlice, uint32_t maxNumEUsPerDualSubSlice) const {
return getMaxThreadsForWorkgroup(hwInfo, maxNumEUsPerDualSubSlice);
}