intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-26 07:00:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: add function to calculate number of threads per tg

Browse Source 
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
This commit is contained in:
Cencelewska, Katarzyna
2023-06-12 11:41:13 +00:00
committed by Compute-Runtime-Automation
parent 987394b27c
commit 7cb3278eb3
16 changed files with 71 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
shared/source/kernel/local_ids_cache.cpp
View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2022 Intel Corporation
* Copyright (C) 2022-2023 Intel Corporation
*
* SPDX-License-Identifier: MIT
*
@@ -33,9 +33,9 @@ std::unique_lock<std::mutex> LocalIdsCache::lock() {
}
size_t LocalIdsCache::getLocalIdsSizeForGroup(const Vec3<uint16_t> &group) const {
const auto numElementsInGroup = Math::computeTotalElementsCount({group[0], group[1], group[2]});
const auto numElementsInGroup = static_cast<uint32_t>(Math::computeTotalElementsCount({group[0], group[1], group[2]}));
const auto numberOfThreads = getThreadsPerWG(simdSize, numElementsInGroup);
return numberOfThreads * static_cast<size_t>(localIdsSizePerThread);
return static_cast<size_t>(numberOfThreads * localIdsSizePerThread);
}
size_t LocalIdsCache::getLocalIdsSizePerThread() const {