intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-21 01:04:57 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,640 Commits 42 Branches 655 Tags
4a369ad88d2dcd3351f07a9b03673137b55d2708
Commit Graph

12640 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Compute-Runtime-Validation
4a369ad88d Revert "feature: check indirect access for kernel" 
This reverts commit 075c96267d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-24 03:48:22 +01:00
Compute-Runtime-Validation
a7075f9ffb Revert "Add support for cl_ext_float_atomics" 
This reverts commit da22e0aac9.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-23 22:27:49 +01:00
ocldev
9eccd5d3d1 dependencies update 
Signed-off-by: ocldev <ocldev@intel.com>
 2023-02-23 21:23:00 +01:00
Lukasz Jobczyk
eb73d86784 Enable copy command buffer into ring buffer 
Resolves: NEO-7422

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-02-23 13:24:39 +01:00
Zbigniew Zdanowicz
3cb064fe95 Refactor state base address programing 3/n 
This is small optimization to replace virtual call and retrieved struct with
cached value.

Related-To: NEO-5055

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-23 13:08:32 +01:00
Dominik Dabek
075c96267d feature: check indirect access for kernel 
Do not make indirect allocations resident if kernel does not use
indirect access.
Enable for both level zero and opencl.

Related-To: NEO-7712

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-02-23 12:38:53 +01:00
Lukasz Jobczyk
59557d31dc Enhance L0 split barrier ULT 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-02-23 12:35:42 +01:00
Lukasz Jobczyk
26edbbcb37 Init ULLS before cmd container init 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-02-23 12:24:19 +01:00
Zbigniew Zdanowicz
43a49c4486 Refactor state base address programing 2/n 
This change allows to read sba data directly from sba properties

Related-To: NEO-5055

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-23 12:20:25 +01:00
Mateusz Hoppe
6947220298 perf(debugger): Optimize registers access during debugging 
Register read/write implementation was unnecessarily checking magic values
which were taking significant time. By removing those checks, register
access is speed-up by a factor of 3.

Resolves: NEO-7754

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-02-23 12:14:03 +01:00
Mateusz Hoppe
e8b4841577 perf(debugger): Optimize single-stepping of eu threads 
Single-stepping threads is based on resume() and THREAD_STOPPED events
To speed up single-stepping, stopped threads must be discovered
immediately after resume() is called.
This change is adding ATT scan and event generation in resume()

Related-To: NEO-7750

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-02-23 11:06:13 +01:00
Daria Hinz
acececc214 feat: Add device IP version extension 
This change introduces an extension to query the device IP version for L0,
which corresponds to the PRODUCT_CONFIG value.
For OCL, the old mechanism is maintained with a debug flag,
and the default behavior has been unified with L0.

Signed-off-by: Daria Hinz <daria.hinz@intel.com>
Related-To: NEO-7735
 2023-02-23 10:20:42 +01:00
Maciej Plewka
829c93ca68 Limit space in tile for concurrent kernels on pvc 
Related-To: NEO-7658, HSD-16016919338

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-02-23 09:50:47 +01:00
Raiyan Latif
aa661c1878 fix: Add peer USM Allocation to Residency Container 
Added the USM Graphics Allocation originally allocated on the
remote peer device to the residency container, to ensure it is
migrated properly to device before a P2P operation occurs. The
page fault manager handles moving this allocation to the
appropriate device.

Related-To: LOCI-3597

Signed-off-by: Raiyan Latif <raiyan.latif@intel.com>
 2023-02-23 09:27:15 +01:00
Compute-Runtime-Validation
796dd642bd Revert "igc revision update" 
This reverts commit 6e39b98094.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-23 03:39:12 +01:00
Kacper Kasper
da22e0aac9 Add support for cl_ext_float_atomics 
Resolves: NEO-6596

Signed-off-by: Kacper Kasper <kacper.k.kasper@intel.com>
 2023-02-22 18:08:58 +01:00
Mateusz Hoppe
6c2f5df6c3 test: fix memoryZeroed() in ULTs 
first byte in the buffer was not checked what resulted in incorrect check
if memory was zeroed,

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-02-22 17:29:27 +01:00
Lukasz Jobczyk
2f5be7a48d Copy command buffer into ring buffer 
Resolves: NEO-7422

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-02-22 16:37:34 +01:00
ocldev
6e39b98094 igc revision update 
Signed-off-by: ocldev <ocldev@intel.com>
 2023-02-22 16:24:00 +01:00
Zbigniew Zdanowicz
c7ca1b8cc7 Refactor state base address programing 1/n 
This refactor simplifies internal interfaces and implementations for
different platforms. The change is introduction into adapting
state base address helper class for all functional needs of the driver.

Related-To: NEO-5055

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-22 15:17:29 +01:00
Mayank Raghuwanshi
29ed6ea077 Add support l3_bank and subslice Ras errors 
Related-To: LOCI-3662

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
 2023-02-22 09:14:15 +01:00
František Zatloukal
beaff2b735 Include cstdint to fix GCC 13 build 
Signed-off-by: František Zatloukal <fzatlouk@redhat.com>
 2023-02-22 08:02:49 +01:00
ocldev
33fe68ec88 igc revision update 
Signed-off-by: ocldev <ocldev@intel.com>
 2023-02-22 07:54:53 +01:00
Mateusz Jablonski
f23b1114c0 fix Windows: fallback to System32 when can't load library from driver store 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-02-22 07:49:41 +01:00
Compute-Runtime-Validation
4a2261aba5 Revert "Limit space in tile for concurrent kernels on pvc" 
This reverts commit 83eb52591d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-22 06:26:14 +01:00
Lukasz Jobczyk
45139de33a Leave init builtin async only on post silicon 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-02-21 15:45:58 +01:00
Grzegorz Choinski
012cbecb32 ci: lint revision update 
Signed-off-by: Grzegorz Choinski <grzegorz.choinski@intel.com>
 2023-02-21 15:18:18 +01:00
Mateusz Jablonski
8cb4fafd81 test OCL: correct test for device USM 
Related-To: NEO-7737
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-02-21 14:54:02 +01:00
Compute-Runtime-Validation
678e47de2d Revert "Adjust maxWorkGroupSize value" 
This reverts commit f7685a93e4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-21 14:45:36 +01:00
Maciej Plewka
83eb52591d Limit space in tile for concurrent kernels on pvc 
Related-To: NEO-7658, HSD-16016919338

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-02-21 14:32:58 +01:00
Rafal Maziejuk
2d9f1caa8c Add PVC configs 
Signed-off-by: Rafal Maziejuk <rafal.maziejuk@intel.com>
Related-To: NEO-7741
 2023-02-21 12:05:40 +01:00
Konstanty Misiak
d1ea22f115 Fix pathtoken fallback AIL unit test 
Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
 2023-02-21 09:21:21 +01:00
Wrobel, Patryk
d8a65c6958 Try to use provided pointer when dual storage shared memory is not supported 
If user provided not-null hostptr field, then the driver
should try to use it. This change adds omitted functionality,
which handles the described case also in createUnifiedMemoryAllocation().

Related-To: NEO-7600
Signed-off-by: Wrobel, Patryk <patryk.wrobel@intel.com>
 2023-02-21 09:08:11 +01:00
Zbigniew Zdanowicz
b4544f6f78 Fix dependency resolve in level zero black box tests 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-21 08:25:07 +01:00
Bellekallu Rajkiran
ac5d719e25 Fix (sysman): Modify device wedged status retrieval mechanism 
Related-To: LOCI-3551

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
 2023-02-20 23:21:24 +01:00
Mateusz Hoppe
87ea9473e4 fix: zeFenceHostSynchronize() to flush printf output 
- zeFenceHostSynchronize() should flush printf output from GPU kernels

Related-To: NEO-7625

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-02-20 23:16:12 +01:00
Pawel Cieslak
1db08cdfa0 ci: infra update 
Signed-off-by: Pawel Cieslak <pawel.cieslak@intel.com>
 2023-02-20 20:43:49 +01:00
Mateusz Witke
5d7bd41395 ci: kernel revision update 
Signed-off-by: Mateusz Witke <mateusz.witke@intel.com>
 2023-02-20 13:49:04 +01:00
Dominik Dabek
22d7c2ea28 feat(ocl): move dependencies programming 
Move out of csr dependencies programming to queue stream.
Correct method fillCsrDependenciesForTimestampPacketContainer.

Related-To: NEO-7321

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-02-20 13:42:56 +01:00
Zbigniew Zdanowicz
2744501176 Inline base address transition function into flush task method 
Related-To: NEO-5055

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-20 12:06:46 +01:00
Mayank Raghuwanshi
eea0ff8e16 Fix clang tidy issues in fabric ults 
Related-To: LOCI-4054

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
 2023-02-20 11:59:12 +01:00
Ranjan, Joshua Santhosh
8ae2e3dac9 Add per tile metric data support for stall sampling 
Related-To: LOCI-3869

Signed-off-by: Ranjan, Joshua Santhosh <joshua.santosh.ranjan@intel.com>
 2023-02-19 12:16:13 +01:00
Compute-Runtime-Validation
29cbdc2430 Revert "Traverse pNext chain for all memory allocations extensions" 
This reverts commit bd8b85c354.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-19 10:10:24 +01:00
Michal Mrozek
15f08a92c0 [performance] do not perform migrations if not needed. 
Skip migrations if nothing is migrated to the CPU side.

Related-To: NEO-5170
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2023-02-17 18:38:52 +01:00
Raiyan Latif
bd8b85c354 Traverse pNext chain for all memory allocations extensions 
Related-To: LOCI-4036
Signed-off-by: Raiyan Latif <raiyan.latif@intel.com>
 2023-02-17 18:07:39 +01:00
Fabian Zwolinski
5eeea0dee8 Enable CpuMemcpy for USM Host to Device transfer 
This commit enables HostUSM -> DeviceUSM transfer to be performed
through CpuMemcpy with 50KB threshold.
USM copy is done on CPU only when it can be performed immediately -
no dependencies present, no events to wait for.

Related-To: NEO-7564
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-02-17 18:04:13 +01:00
Konstanty Misiak
3cf5850172 fix(AIL) Make DaVinci Resolve AIL apply to all platforms 
Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
 2023-02-17 16:56:51 +01:00
Zbigniew Zdanowicz
bf2072c3ea Add cross regular and intermediate command lists base address state transitions 
- updates coming from regular list are updated in csr last sent variables
- all per context and per kernel transitions kept in single place
- state updates from intermediate to regular are set in csr properties
- global atomics support duplicates removed

Related-To: NEO-5055

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-02-17 16:49:47 +01:00
Artur Harasimiuk
140e59810f add intel-level-zero-gpu-devel 
Related-To: NEO-5997
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2023-02-17 14:55:28 +01:00
Michal Mrozek
8aa1953bd6 [performance] Improve isRelaxedOrderingDispatchAllowed 
- add early return
- change the if sequence

Related-To: NEO-5170

Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2023-02-17 14:52:18 +01:00