Media
/
compute-runtime
mirror of https://github.com/intel/compute-runtime.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
14,099 Commits 36 Branches 614 Tags 179 MiB
Commit Graph

607 Commits

Author SHA1 Message Date
Mrozek, Michal d9f938f3db refactor: remove not needed code 
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
 2023-09-12 14:25:04 +02:00
Mrozek, Michal 15a0bf9d7b refactor: remove not needed code. 
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
 2023-09-12 13:52:47 +02:00
Dunajski, Bartosz 6648065703 feature: add indirect semaphore mode 
Related-To: NEO-8242

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-09-12 13:15:51 +02:00
Dunajski, Bartosz def3f2e9ad refactor: improve semaphore programming 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-09-12 11:24:11 +02:00
Mrozek, Michal cac547946a refactor: remove not needed code 
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
 2023-09-12 08:51:58 +02:00
Compute-Runtime-Validation b5e9c10f64 Revert "performance(ocl): program barrier pc in taskStream" 
This reverts commit 839c2d6737.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-12 01:32:28 +02:00
Dominik Dabek 839c2d6737 performance(ocl): program barrier pc in taskStream 
Program barrier immediately to task stream.
This will reduce the number of batch buffer starts.

Related-To: NEO-8147

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-09-11 13:23:26 +02:00
Lukasz Jobczyk a38ac3557b performance: Disable blit enqueue on xe_lpg 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-09-11 13:10:23 +02:00
Compute-Runtime-Validation 7b5ef1b2f4 Revert "performance: Disable blit enqueue on xe_lpg" 
This reverts commit ac97b1c493.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-11 10:10:21 +02:00
Michal Mrozek 65188fc90b refactor: remove not needed code 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2023-09-08 17:22:18 +02:00
Lukasz Jobczyk ac97b1c493 performance: Disable blit enqueue on xe_lpg 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-09-08 14:04:24 +02:00
Dunajski, Bartosz 269adbe43b refactor: add L0 dispatch params debug logs 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-09-08 05:35:32 +02:00
Dunajski, Bartosz f1fc273cfc fix: check for new submission before releasing TSP nodes in wait call. 
Related-To: NEO-8318

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-08-31 13:19:19 +02:00
Maciej Plewka 2e249d819e fix: submit marker for cpu transfer with event on IOQ queue 
Related-To: NEO-8081

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-08-21 15:07:37 +02:00
Dunajski, Bartosz 3cf1f5c462 fix: unregister CSR client on OCL sync points 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-08-16 13:35:07 +02:00
Dunajski, Bartosz a42e88d55b fix: stall RelaxedOrdering scheduler when programming OCL dependencies 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-08-14 10:47:35 +02:00
Fabian Zwolinski 6fca8ee195 refactor: Remove SourceLevelDebugger 
Removed:
- SourceLevelDebugger (with tests)
- DebuggerLibrary
- DebuggerLibraryRestore
- debuggerSupported field from hwInfo.capabilityTable
- HasSourceLevelDebuggerSupport matcher
- ExperimentalEnableSourceLevelDebugger debug var
- EnableMockSourceLevelDebugger debug var
- DebuggerOptDisable debug var
- lib_names.h.in file
- third_party/source_level_debugger/igfx_debug_interchange_types.h

Related-To: NEO-7213
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-08-10 11:14:02 +02:00
Mateusz Hoppe 997b599168 fix(debugger): pass correct sipAllocation to makeResident 
- sipAllocation for context must be resident in Offline mode

Related-To: NEO-7630

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-07-28 20:51:12 +02:00
Dunajski, Bartosz 6656e23b86 refactor: unify completion check methods 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-25 14:17:52 +02:00
Dunajski, Bartosz 2c50fd9486 fix: waiting for completion in TBX mode 
- use testTaskCountReady method to check TaskCount value
- download all allocations when TaskCount is ready

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-25 11:54:09 +02:00
Cencelewska, Katarzyna 6f45574ff9 fix: add proper bcs synchronization when marker 
Related-To: NEO-8105
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-07-24 10:57:41 +02:00
Dominik Dabek 0a4d0917d4 performance(ocl): skip dcFlush on no event 
Skip dcFlush on waitForBarrier without event by default.

Related-To: NEO-8147

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-07-20 14:57:37 +02:00
Dominik Dabek 622a3ed89c performance(ocl): flag to not dcFlush on no event 
If waitForBarrier is not passed outEvent then do
dcFlush on the next synchronize call.

Related-To: NEO-8147

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-07-18 15:38:54 +02:00
Dunajski, Bartosz 815b37bf3a performance: allow waiting for OOQ timestamps in clEnqueueWaitForEvents 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-14 11:33:10 +02:00
Dunajski, Bartosz 712e059ace performance: check completion alloc only once when waiting for Event 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-14 08:32:50 +02:00
Dunajski, Bartosz 40c7b2842f fix: check engines completion before releasing deferred TSP nodes 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>

Related-To: NEO-8146
 2023-07-11 16:11:51 +02:00
Cencelewska, Katarzyna aa0beb8191 fix: Unify logic calculating threads per work group part 4 
- also use helper when checking that is simd1 to have same flow

Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-07-07 15:34:59 +02:00
Dunajski, Bartosz 00bae2c827 fix: add missing nullptr check 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-07 11:34:49 +02:00
Dunajski, Bartosz d96cf5846a fix: dont allocate TSP for OOQ without Event 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-06 15:12:22 +02:00
Dunajski, Bartosz 2b5e475db9 refactor: use hex values to print TSP usage 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-23 11:22:10 +02:00
Dunajski, Bartosz b004a27e4e refactor: Debug flag to print TSP usage 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-22 14:47:39 +02:00
Dominik Dabek 60d5e22f3b fix(ocl): reduce busy waiting in clFinish 
Use flushStamp=taskCount when passed flushStamp==0.
This will cause driver to busy wait for a short while before falling
back to use kmd notify.

Related-To: GSD-3612

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-06-14 13:56:40 +02:00
Cencelewska, Katarzyna 7cb3278eb3 fix: add function to calculate number of threads per tg 
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-06-13 14:02:24 +02:00
Dunajski, Bartosz 0372b9410a fix: set correct number of active packets for IOQ barrier 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-05-30 16:02:23 +02:00
Lukasz Jobczyk 0e758e4bb5 performance: Add debug flag to set BCS split minimal size 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-05-17 08:07:43 +02:00
Lukasz Jobczyk 9f755b54ad performance: Bidirectional BCS split implementation for OCL 
Related-To: NEO-7877

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-05-16 13:34:18 +02:00
Fabian Zwolinski cbce863dc2 refactor: Rename member variables to camelCase 3/n 
Additionally enable clang-tidy check for member variables

Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-04-28 16:01:14 +02:00
Maciej Plewka 464c67789f fix: Deffer timestamp packet after failed submission 
Related-To: NEO-7835

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-04-28 12:25:32 +02:00
Maciej Plewka bac02071e7 refactor: Remove template param from enqueueNonBlocked 
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-04-28 09:34:12 +02:00
Fabian Zwolinski e351a90f81 refactor: Rename member variables to camelCase 2/n 
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-04-27 20:39:22 +02:00
Fabian Zwolinski c441e9e971 refactor: Rename member variables to camelCase 
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-04-26 16:05:07 +02:00
Cencelewska, Katarzyna ac8ac62c92 fix: add bcs engine type only if engine exist 
- check bcs availability before insert to bcsEnginesTypes

Resolves: NEO-7886
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-04-20 09:02:38 +02:00
Milczarek, Slawomir 01d03aa5b6 Extended regkey to force prefetch of shared memory in enqueue commands 
Extended the regkey ForceMemoryPrefetchForKmdMigratedSharedAllocations
to force meory prefetch of kmd-migrated shared allocation
in clEnqueueNDRangeKernel(), clEnqueueMemFillINTEL, ...

Related-To: NEO-7841

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2023-04-11 11:23:48 +02:00
Mateusz Jablonski d014a731c5 fix multi device ocl: add missing tag update flush after blit 
when memory is migrated then we need to flush tag update

Related-To: NEO-7552
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-04-04 11:06:57 +02:00
Lukasz Jobczyk 18e5664c88 Set stalling command for split marker 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-03-29 15:34:45 +02:00
Dominik Dabek d7981e153e fix(ocl): tweak resolve deps with pipecontrols 
Keep resolving with semaphores if multiple (>2) queues are submitting to
the same CSR. In such case, semaphores allow concurrent execution while
pipecontrols would serialize it.

Related-To: NEO-7321

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-03-27 17:22:03 +02:00
Dunajski, Bartosz f522744886 OCL: Allow for RelaxedOrdering barriers in IOQ mode 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-03-27 12:25:01 +02:00
Dominik Dabek a634c6a7b1 fix:pass bool to get CS size instead of reevaluate 
Pass resolveDependenciesByPipecontrol bool value to get command stream
methods instead of reevaluating the condition.

Related-To: NEO-7321

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-03-24 15:24:10 +01:00
Dunajski, Bartosz b3c2fa41c5 OCL: Optimize IOQ barriers handling 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-03-24 12:52:47 +01:00
Dunajski, Bartosz 73213c961f Enable RelaxedOrdering for OCL on GPGPU engine 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-03-22 12:39:52 +01:00