intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-03 14:55:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Do not apply L0 debugger WA (Disable L3 cache) for highest DG2 steppings

Browse Source 
Related-To: NEO-6320

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
This commit is contained in:
Igor Venevtsev
2022-01-05 12:06:14 +00:00
committed by Compute-Runtime-Automation
parent 03366f11d2
commit d9aae805c7
8 changed files with 41 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
level_zero/core/source/debugger/debugger_l0.cpp
View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2020-2021 Intel Corporation
* Copyright (C) 2020-2022 Intel Corporation
*
* SPDX-License-Identifier: MIT
*
@@ -78,7 +78,7 @@ void DebuggerL0::initialize() {
NEO::MemoryTransferHelper::transferMemoryToAllocation(hwHelper.isBlitCopyRequiredForLocalMemory(hwInfo, *moduleDebugArea),
*device, moduleDebugArea, 0, &debugArea,
sizeof(DebugAreaHeader));
if (hwHelper.disableL3CacheForDebug()) {
if (hwHelper.disableL3CacheForDebug(hwInfo)) {
device->getGmmHelper()->disableL3CacheForDebug();
}
}