intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-09 22:43:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: add param rootDeviceEnvironment to calculateNumThreadsPerThreadGroup

Browse Source 
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
This commit is contained in:
Katarzyna Cencelewska
2024-03-21 18:54:41 +00:00
committed by Compute-Runtime-Automation
parent ec009cf9e3
commit dd1d52259e
30 changed files with 231 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
shared/source/command_container/command_encoder_bdw_and_later.inl
View File

@@ -181,7 +181,7 @@ void EncodeDispatchKernel<Family>::encode(CommandContainer &container, EncodeDis
uint32_t sizeThreadData = sizePerThreadDataForWholeGroup + sizeCrossThreadData;
bool isHwLocalIdGeneration = false;
uint32_t sizeForImplicitArgsPatching = NEO::ImplicitArgsHelper::getSizeForImplicitArgsPatching(pImplicitArgs, kernelDescriptor, isHwLocalIdGeneration, gfxCoreHelper);
uint32_t sizeForImplicitArgsPatching = NEO::ImplicitArgsHelper::getSizeForImplicitArgsPatching(pImplicitArgs, kernelDescriptor, isHwLocalIdGeneration, rootDeviceEnvironment);
uint32_t iohRequiredSize = sizeThreadData + sizeForImplicitArgsPatching;
uint64_t offsetThreadData = 0u;
{
@@ -203,7 +203,7 @@ void EncodeDispatchKernel<Family>::encode(CommandContainer &container, EncodeDis
auto implicitArgsCrossThreadPtr = ptrOffset(const_cast<uint64_t *>(reinterpret_cast<const uint64_t *>(args.dispatchInterface->getCrossThreadData())), kernelDescriptor.payloadMappings.implicitArgs.implicitArgsBuffer);
*implicitArgsCrossThreadPtr = implicitArgsGpuVA;
ptr = NEO::ImplicitArgsHelper::patchImplicitArgs(ptr, *pImplicitArgs, kernelDescriptor, {}, gfxCoreHelper);
ptr = NEO::ImplicitArgsHelper::patchImplicitArgs(ptr, *pImplicitArgs, kernelDescriptor, {}, rootDeviceEnvironment);
}
memcpy_s(ptr, sizeCrossThreadData,