intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-21 09:14:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Change level zero command queue internal interface for front end programing

Browse Source 
Front end estimation use internal loop for command list browsing and
estimation of each command list.
This refactor moves internal loop into external execution, so command list
browsing in loop can be shared by all state commands.
This refactor - sharing loop - will correct performance of each added state
estimator.

Related-To: NEO-5019

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
This commit is contained in:
Zbigniew Zdanowicz
2022-09-20 16:46:15 +00:00
committed by Compute-Runtime-Automation
parent 43676ed02a
commit 7832195cd8
4 changed files with 84 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
level_zero/core/source/cmdqueue/cmdqueue.cpp
View File

@@ -28,6 +28,10 @@ namespace L0 {
CommandQueueAllocatorFn commandQueueFactory[IGFX_MAX_PRODUCT] = {};
bool CommandQueue::frontEndTrackingEnabled() const {
return NEO::DebugManager.flags.AllowPatchingVfeStateInCommandLists.get() || this->multiReturnPointCommandList;
}
CommandQueueImp::CommandQueueImp(Device *device, NEO::CommandStreamReceiver *csr, const ze_command_queue_desc_t *desc)
: desc(*desc), device(device), csr(csr) {
int overrideCmdQueueSyncMode = NEO::DebugManager.flags.OverrideCmdQueueSynchronousMode.get();