intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-03 06:49:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "fix: Correct logic for SIMD1"

Browse Source 
This reverts commit fc099ead2e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
This commit is contained in:
Compute-Runtime-Validation
2023-09-13 08:04:36 +02:00
committed by Compute-Runtime-Automation
parent fc099ead2e
commit 413365a7bf
4 changed files with 17 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
shared/source/helpers/per_thread_data.h
View File

@@ -8,7 +8,6 @@
#pragma once
#include "shared/source/helpers/gfx_core_helper.h"
#include "shared/source/helpers/local_id_gen.h"
#include "shared/source/helpers/simd_helper.h"
#include <cstddef>
#include <cstdint>
@@ -24,11 +23,7 @@ struct PerThreadDataHelper {
size_t localWorkSize,
bool isHwLocalIdGeneration,
const GfxCoreHelper &gfxCoreHelper) {
auto perThreadSizeLocalIDs = static_cast<size_t>(getPerThreadSizeLocalIDs(simd, grfSize, numChannels));
if (isSimd1(simd)) {
return perThreadSizeLocalIDs * localWorkSize;
}
return perThreadSizeLocalIDs * gfxCoreHelper.calculateNumThreadsPerThreadGroup(simd, static_cast<uint32_t>(localWorkSize), grfSize, isHwLocalIdGeneration);
return gfxCoreHelper.calculateNumThreadsPerThreadGroup(simd, static_cast<uint32_t>(localWorkSize), grfSize, isHwLocalIdGeneration) * getPerThreadSizeLocalIDs(simd, grfSize, numChannels);
}
}; // namespace PerThreadDataHelper
} // namespace NEO