intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-20 08:53:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Unify logic calculating threads per work group part 2

Browse Source 
- use calculateNumThreadsPerThreadGroup instead of getThreadsPerWG to
have same flow and proper values of threads per work groups

Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
This commit is contained in:
Cencelewska, Katarzyna
2023-06-29 15:51:43 +00:00
committed by Compute-Runtime-Automation
parent c294ef48ce
commit 1e8a53bd53
19 changed files with 90 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
shared/source/kernel/implicit_args_helper.cpp
View File

@@ -62,7 +62,7 @@ uint32_t getSizeForImplicitArgsPatching(const ImplicitArgs *pImplicitArgs, const
}
}
void *patchImplicitArgs(void *ptrToPatch, const ImplicitArgs &implicitArgs, const KernelDescriptor &kernelDescriptor, std::optional<std::pair<bool, uint32_t>> hwGenerationOfLocalIdsParams) {
void *patchImplicitArgs(void *ptrToPatch, const ImplicitArgs &implicitArgs, const KernelDescriptor &kernelDescriptor, std::optional<std::pair<bool, uint32_t>> hwGenerationOfLocalIdsParams, const GfxCoreHelper &gfxCoreHelper) {
auto totalSizeToProgram = getSizeForImplicitArgsPatching(&implicitArgs, kernelDescriptor);
auto retVal = ptrOffset(ptrToPatch, totalSizeToProgram);
@@ -80,7 +80,7 @@ void *patchImplicitArgs(void *ptrToPatch, const ImplicitArgs &implicitArgs, cons
static_cast<uint16_t>(implicitArgs.localSizeY),
static_cast<uint16_t>(implicitArgs.localSizeZ)}},
dimensionOrder,
false, grfSize);
false, grfSize, gfxCoreHelper);
auto sizeForLocalIdsProgramming = totalSizeToProgram - sizeof(NEO::ImplicitArgs);
ptrToPatch = ptrOffset(ptrToPatch, sizeForLocalIdsProgramming);
}