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

performance(ocl): timestamp packet count per gfx

Browse Source 
Add support for different timestamp packet counts per gfx family.
Change all packet counts to 1 except for xe-hpc.

Related-To: NEO-8154

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
This commit is contained in:
Dominik Dabek
2023-09-25 07:45:36 +00:00
committed by Compute-Runtime-Automation
parent ebc024f0f1
commit eebf2bbd26
26 changed files with 114 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
shared/source/xe_hpg_core/hw_cmds_xe_hpg_core_base.h
View File

@@ -27,6 +27,7 @@ struct XeHpgCore {
static constexpr uint32_t stateComputeModePixelAsyncComputeThreadLimitMask = (0b111u << 7);
static constexpr uint32_t stateComputeModeLargeGrfModeMask = (1u << 15);
static constexpr uint32_t bcsEngineCount = 1u;
static constexpr uint32_t timestampPacketCount = 1u;
static constexpr bool isUsingL3Control = true;
static constexpr bool isUsingMediaSamplerDopClockGate = false;