intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-22 18:25:05 +08:00
Code Issues Packages Projects Releases Wiki Activity
14,124 Commits 42 Branches 655 Tags
f901b26222f3cefc163f30f2aca00ae97f4aa2ad
Commit Graph

4496 Commits

Author SHA1 Message Date
Fabian Zwolinski
0538f0524a refactor: make os_handle.h non os specific 
Use the same file `os_handle.h` on both
Linux and Windows.
Change implementation of `HandleType` -> `UnifiedHandle` to
`std::variant<int, void *>`
use `int` on Linux
use `void *` on Windows

Related-To: NEO-8092
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-09-15 15:53:41 +02:00
Dominik Dabek
ee767822b8 performance(ocl): add bcsEngineCount to cmdq 
Related-To: NEO-8155

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-09-15 15:49:56 +02:00
Maciej Plewka
44b3f18567 refactor: Use release helper for adjusting depth 
Related-To: NEO-8295, HSD-14019991753

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-09-15 13:24:37 +02:00
Lukasz Jobczyk
7cb92dad25 fix: add AIL for svchost on MTL 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-09-15 13:05:15 +02:00
Compute-Runtime-Validation
73731d3be5 Revert "fix: correct suggested number of work groups for concurrent kernels o... 
This reverts commit 6fc673b0fe.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-15 04:21:58 +02:00
Cencelewska, Katarzyna
d5441cc2d9 fix: change process name in AIL for Adobe Premiere Pro 
Related-To: HSD-22018809561
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-09-14 20:53:46 +02:00
Mateusz Jablonski
6fc673b0fe fix: correct suggested number of work groups for concurrent kernels on PVC 
value depends on CCS count:
- single CCS mode (default) - no limitations
- two CCS mode - 25% available
- four CCS mode - 12.5% available

Related-To: NEO-8377
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-14 16:13:54 +02:00
Baj, Tomasz
e10f39017d fix: Add ImageInfo to createGraphicsAllocation on Linux 
Related-To: NEO-6757

Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
 2023-09-14 12:58:59 +02:00
Mateusz Jablonski
fca50ba710 refactor: remove not needed logic for syncobj in xe 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-14 10:27:28 +02:00
Kamil Kopryk
1ab0467301 fix: Add bind info for allocation from ipc handle in xe 
Related-To: NEO-7996
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2023-09-13 12:34:10 +02:00
Mateusz Jablonski
3eb98163a8 fix: define isCachingOnCpuAvailable per hw release 
Related-To: NEO-8187
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-13 11:13:42 +02:00
Mateusz Jablonski
2f7c33c1fd refactor: move xe hpg specific appendBlitCommandsBlockCopy to xe hpg file 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-13 10:49:28 +02:00
Dunajski, Bartosz
7562842a58 refactor: remove LogicalStateHelper 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-09-13 10:29:53 +02:00
Mateusz Jablonski
f94ed7cd28 refactor: pass root device environment to CacheSettingsHelper::preferNoCpuAccess 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-13 09:32:36 +02:00
Compute-Runtime-Validation
413365a7bf Revert "fix: Correct logic for SIMD1" 
This reverts commit fc099ead2e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-13 08:23:59 +02:00
Kacper Nowak
fc099ead2e fix: Correct logic for SIMD1 
- For calculating number of threads per workgroup, treat simd 1 as it
  was simd 32
- Correct logic of calculating space for per thread data for simd 1
- Minor: unit tests refactor
- Corrected naming
Related-To: NEO-8261
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
 2023-09-13 07:03:12 +02:00
Cencelewska, Katarzyna
a6ea67bd09 fix: add empty functions to set and get gemTiling in xeIoctlHelper 
it is needed until there is no support in xe kmd for image tiling

Related-To: NEO-8325
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-09-12 16:11:37 +02:00
Cencelewska, Katarzyna
df961b3dc0 fix: update properly bindInfo in GemCreate on xe kmd 
Related-To: NEO-8325
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-09-12 16:04:28 +02:00
Fabian Zwolinski
0dd40b8616 refactor: Split compiler interface between OSs 
Create new file:
`os_handle.h` which contains OS specific Handle type.
Add `shared/source/os_interface/<windows/linux>`
include directory to level_zero.

Related-To: NEO-8092
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-09-12 15:56:53 +02:00
Filip Hazubski
afba02afa9 fix: Add AIL for Adobe Premiere Pro 
Use legacy platform name: "Intel(R) OpenCL".

Resolves: HSD-22018809561

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-09-12 15:39:47 +02:00
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
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
2a6be2fccd feature: update conditional bb start to use qword data 
Related-To: NEO-8242

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-09-12 11:24:28 +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
Filip Hazubski
d7db6ac467 feature: Add preferredPlatformName field to RuntimeCapabilityTable 
For all of the devices, preferredPlatformName is initialized with
nullptr by default and platform name will be initialized to driver's default
platform name, at the moment this is "Intel(R) OpenCL Graphics".

When Platform is initialized and preferredPlatformName is not nullptr then
Platform name will be set to the value stored in preferredPlatformName.

Add ENABLE_LEGACY_PLATFORM_NAME AIL enum related to added functionality.

Move PlatformInfo to NEO namespace.

Related-To: HSD-22018809561

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-09-12 11:07:14 +02:00
Mrozek, Michal
451c48fc2f refactor: remove not needed code. 
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
 2023-09-12 10:51:35 +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
Mateusz Jablonski
c851896482 refactor: move XeHpg specific setExtraAllocationData definition to Xe Hpg file 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-11 13:32:00 +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
Mateusz Jablonski
aa6b837a67 fix: define preferred allocation method per hw release 
Related-To: HSD-18033144631
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-11 12:54:52 +02:00
Compute-Runtime-Validation
1579c69316 Revert "performance: allocate timestamp packet tag buffer in local mem on DG2" 
This reverts commit 819908ec94.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-11 12:07:26 +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
Yoon, Young Jin
c6aac6f2bc fix: remove unnessessary check chunking prefetch 
Removed checking for EnableBOChunkingPrefetch in prefetchBOWithChunking
in DrmAllocation so that zeCommandListAppendMemoryPrefetch will work
as expected with chunking enabled

Related-To: NEO-8098
Signed-off-by: Yoon, Young Jin <young.jin.yoon@intel.com>
 2023-09-08 18:55:38 +02:00
Fabian Zwolinski
b2ba1fbecf fix: enforce zebin format by default in Ocloc for ICL/TGL/RKL/ADL 
Products for which zebin has been set as default format in OCLOC:
- ICELAKE_LP
- TIGERLAKE_LP
- ROCKETLAKE
- ALDERLAKE_S
- ALDERLAKE_P
- ALDERLAKE_N

The default format does not override `--format` parameter.

Related-To: NEO-8334
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-09-08 16:16:18 +02:00
Cencelewska, Katarzyna
79ea10ec98 fix: when no memoryBanks set properly flags to gemCreate 
Related-To: NEO-8325
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-09-08 15:54:54 +02:00
Mateusz Jablonski
46288b8efd fix: setup correct non-release key name in getStringWithFlags 
unify function for getting env

Related-To: NEO-8347
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-08 15:39:36 +02:00
Lukasz Jobczyk
e9f199bcad performance: Wait in busy loop with timeout before Gdi sync object 
Resolves: NEO-8343

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-09-08 14:40:20 +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
Kamil Kopryk
79e30f9ecd fix: Correct maxEuPerSubSlice calculation in drm 
Related-To: NEO-7996
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2023-09-08 13:33:58 +02:00
Maciej Plewka
09c1d474c9 fix: adjust depth limitations for images 
Related-To: NEO-8239, HSD-14019991752

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-09-08 13:05:49 +02:00
Cencelewska, Katarzyna
98dae70415 fix: add helper to proper call GemCreate on xe kmd 
Related-To: NEO-8325
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-09-08 12:27:11 +02:00
Mateusz Hoppe
93469eaf5d feature: bindless addressing for buffers with offset 
- allocate SurfaceStates on kernel's heap for offsetted buffers

Related-To: NEO-7063

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-09-08 12:03:23 +02:00
Joshua Santosh Ranjan
91784a87cc fix: Return success for system address in setArg 
This patch avoids returning error for system addresses in setArg

Related-To: GSD-3597

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
 2023-09-08 05:27:55 +02:00
Fabian Zwolinski
10675134e1 feature: Add process safety to Windows compiler cache 
Related-To: NEO-8092

Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
Co-authored-by: Diedrich, Kamil <kamil.diedrich@intel.com>
 2023-09-06 15:34:15 +02:00
Mateusz Jablonski
3845eb3b90 fix: accept more than 16 root devices 
Related-To: GSD-5892
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-06 10:13:25 +02:00
Naklicki, Mateusz
ff57bec1f0 fix: ignore subDeviceId token instead of skipping builtins resolve 
Previous implementation skipped resolving the subDeviceId token, which
caused in returning the LinkedPartially status if token was present.
It could result in ZE_RESULT_ERROR_INVALID_MODULE_UNLINKED when kernel
was created and crashing an app.

Related-To: NEO-6875, HSD-14015133115
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
 2023-09-05 16:26:44 +02:00
Mateusz Jablonski
6d1c673a70 fix: correct scope of isCachingOnCpuAvailable within xe lpg 
Related-To: HSD-18033144631, HSD-18033158637
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-05 15:45:25 +02:00
John Falkowski
15a5bd6d8e fix: Chunking check for KMD migration 
Check for KMD migration to enable chunking

Related-To: NEO-8098

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2023-09-05 02:58:25 +02:00
Maciej Plewka
3b3e17e738 performance: Use vector for private allocs to reuse 
Related-To: HSD-18033105655, HSD-18033153203

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2023-09-04 13:34:38 +02:00