intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-25 21:42:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor ZE_ENABLE_PCI_ID_DEVICE_ORDER

Browse Source 
- Make it avaialble also to OpenCL
- Use it before parsing affinity mask, so devices are masked also
following PCI order.


Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
This commit is contained in:
Jaime Arteaga
2021-07-11 00:12:15 +00:00
committed by Compute-Runtime-Automation
parent 42c5f2235b
commit 058c30c9a8
19 changed files with 242 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
shared/source/debug_settings/release_variables.inl
View File

@@ -12,4 +12,5 @@
DECLARE_DEBUG_VARIABLE(bool, MakeAllBuffersResident, false, "Make all buffers resident after creation")
DECLARE_DEBUG_VARIABLE(int32_t, OverrideDefaultFP64Settings, -1, "-1: dont override, 0: disable, 1: enable.")
DECLARE_DEBUG_VARIABLE(int32_t, EnableCrossDeviceAccess, -1, "-1: default behavior, 0: disabled, 1: enabled, Allows one device to access another device's memory")
DECLARE_DEBUG_VARIABLE(std::string, ZE_AFFINITY_MASK, std::string("default"), "Refer to the Level Zero Specification for a desricption")
DECLARE_DEBUG_VARIABLE(std::string, ZE_AFFINITY_MASK, std::string("default"), "Refer to the Level Zero Specification for a description")
DECLARE_DEBUG_VARIABLE(bool, ZE_ENABLE_PCI_ID_DEVICE_ORDER, true, "Refer to the Level Zero Specification for a description")