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

Correct calculating of CL_DEVICE_GLOBAL_MEM_CACHE_SIZE value

Browse Source 
Related-To: NEO-6991, NEO-6993

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
This commit is contained in:
Filip Hazubski
2022-05-23 18:58:36 +00:00
committed by Compute-Runtime-Automation
parent 637767500d
commit 57eb195571
5 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
opencl/source/cl_device/cl_device_caps.cpp
View File

@@ -287,7 +287,7 @@ void ClDevice::initializeCaps() {
//copy system info to prevent misaligned reads
const auto systemInfo = hwInfo.gtSystemInfo;
deviceInfo.globalMemCacheSize = systemInfo.L3BankCount * 128 * KB;
deviceInfo.globalMemCacheSize = systemInfo.L3CacheSizeInKb * KB;
deviceInfo.grfSize = hwInfo.capabilityTable.grfSize;
deviceInfo.globalMemCacheType = CL_READ_WRITE_CACHE;