Commit Graph

4547 Commits

Author SHA1 Message Date
Mateusz Hoppe
e345d55fe5 fix: correctly patch implicit arg buffer in indirect data
- use correct size alignment of implicit arg buffer, crosshtread data
should start after the buffer without extra padding

Related-To: NEO-14449

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-05-05 16:03:57 +02:00
Pratik Bari
22ddaea09f fix(sysman): Correct gtId is fetched from the EngineInfo
Related-To: NEO-14626

Signed-off-by: Pratik Bari <pratik.bari@intel.com>
2025-05-05 15:50:50 +02:00
Tomasz Biernacik
f03decfc25 performance: disable coherency for buffers on PTL
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-05-05 13:47:23 +02:00
Brandon Yates
ee75c59da5 fix: check BANNED in reset_stats before aborting when debugger is enabled
Related-to: GSD-10788

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-05-05 11:51:27 +02:00
Aleksandra Nizio
62739986bf fix: print error in sim mode without available aubstream
Resolves: NEO-14693

Signed-off-by: Aleksandra Nizio <aleksandra.nizio@intel.com>
2025-05-05 11:48:35 +02:00
Compute-Runtime-Validation
9595526a52 Revert "performance: Remove global fence from command stream on BMG"
This reverts commit 304fba1eba.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-05-05 11:06:16 +02:00
Compute-Runtime-Validation
edd230b6cb Revert "performance: Remove global fence allocation from BMG"
This reverts commit c9a21c158e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-05-02 13:32:47 +02:00
Young Jin Yoon
529b89c16a feature: support copy function post-sync [4/n]
Added EncodePostSync to BlitPostSyncProperties, and
applyAdditionalBlitProperties to BlitCommandsHelper.

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-05-02 00:02:43 +02:00
Young Jin Yoon
55e7b6a209 feature: support copy function post-sync [3/n]
Refactored EncodePostSync to use more generic terms by renaming
variables.
Added some helper functions in EncodePostSync.

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-05-01 19:20:01 +02:00
Raiyan Latif
ee4be92cc1 feature: Add TimelineWin32 External Semaphore support
Related-To: NEO-14397

Signed-off-by: Raiyan Latif <raiyan.latif@intel.com>
2025-05-01 18:51:58 +02:00
Young Jin Yoon
9d47247ef0 refactor: add product helper for blit properties
Created a new function in ProductHelper to determine whether the
additional blit properties can be used.

Related-To: NEO-13003

Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-05-01 18:05:48 +02:00
Compute-Runtime-Validation
0c3b765942 Revert "refactor: add BlitSyncPropertiesExt to BlitSyncProperties"
This reverts commit b5a259aded.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-05-01 03:23:53 +02:00
Young Jin Yoon
b5a259aded refactor: add BlitSyncPropertiesExt to BlitSyncProperties
Added BlitSyncPropertiesExt to provide additional information for
different platform and/or blitter commands.

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-30 19:11:34 +02:00
Lukasz Jobczyk
c9a21c158e performance: Remove global fence allocation from BMG
Resolves: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-30 17:08:44 +02:00
Lukasz Jobczyk
304fba1eba performance: Remove global fence from command stream on BMG
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-30 15:58:37 +02:00
Lukasz Jobczyk
6c2ddf1120 fix: program system fence address when global fence passed to ULLS
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-30 12:57:04 +02:00
John Falkowski
70eb6716ae refactor: Page align and size for prefetch
Resolves: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
2025-04-30 06:46:35 +02:00
Mateusz Jablonski
523e53c862 fix: passing hw generation of local ids for implicit args patching
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-04-29 16:28:23 +02:00
Slawomir Milczarek
cb4443a545 refactor: Add a new getter to product helper
Related-To: NEO-12952

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
2025-04-29 13:02:16 +02:00
Compute-Runtime-Validation
a6b4e61d34 Revert "performance: Remove global fence from command stream on BMG"
This reverts commit f5301ac379.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-04-29 05:17:21 +02:00
Dominik Dabek
75e313ce28 feature: prepare for l0 usm device pooling
Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-04-28 14:55:03 +02:00
Lukasz Jobczyk
6f4a56d440 refactor: pass product helper to isFenceAllocationRequired
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-28 14:09:02 +02:00
Lukasz Jobczyk
f5301ac379 performance: Remove global fence from command stream on BMG
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-28 14:08:47 +02:00
Lukasz Jobczyk
97358acabe fix: use mfence instead of sfence on discrete devices
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-25 13:32:25 +02:00
Mateusz Hoppe
41efee1e7c feature: add mode to expose single root device
- simplify API to expose and use only single root device. Disallow
returning subdevices. This is experimental mode.

Related-To: NEO-14559

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-04-25 13:20:56 +02:00
Lukasz Jobczyk
dfcdbb20cc fix: Move ULLS semaphore to smem on xe2
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-25 12:54:27 +02:00
Lukasz Jobczyk
a75f1434b0 performance: Store vm bind available in drmCsr
Resolves: GSD-10986

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-24 15:45:05 +02:00
Szymon Morek
8ec5688ca1 Revert "performance: extend usage of staging buffers"
This reverts commit 6a4ddf5dfb.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-24 11:02:27 +02:00
Lukasz Jobczyk
f36e3c7d23 refactor: Disable gem close worker in ULTs
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-23 17:58:18 +02:00
Michał Pryba
edfc512d3b test: adjust test machers after pre-gen12 removal
Related-To: NEO-12681
Signed-off-by: Michał Pryba <michal.pryba@intel.com>
2025-04-23 14:30:21 +02:00
Maciej Plewka
6d085ed0d4 fix: Return max wg count equal one on platforms without dispatch all support
Second push of a change that was reverted due to errors in tests
Related-To: NEO-14125, GSD-10725

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-04-23 13:48:11 +02:00
Lukasz Jobczyk
53f0832614 fix: Register shared handle size on windows
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-23 13:00:27 +02:00
Lukasz Jobczyk
5d2b673ef6 fix: Adjust waitpkg threshold to 20 us
Resolves: HSD-13012958900

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-23 10:46:22 +02:00
Szymon Morek
6a4ddf5dfb performance: extend usage of staging buffers
Related-To: NEO-14026

Move enabling from xe2 to xe2_and_later

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-22 16:46:52 +02:00
Lukasz Jobczyk
d510f742da fix: Pass Deallocate2 callback to gmm
Resolves: HSD-18041541320

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-22 12:08:56 +02:00
Fabian Zwoliński
204577a91f fix: disable TimestampPoolAllocator
Related-To: NEO-12287, HSD-13012945876
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-04-18 11:30:35 +02:00
Compute-Runtime-Validation
fe1db94454 Revert "performance: Remove global fence from command stream on BMG"
This reverts commit 0c778ef6f4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-04-18 09:23:16 +02:00
Young Jin Yoon
05c6612386 refactor: add EncodePostSyncArgs to EncodeDispatchKernelArgs
Refactored various member variables in EncodeDispatchKernel to directly
include EncodePostSync
Changed command encoder and command list to use the modified
EncodeDispatchKernel.

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-17 20:55:40 +02:00
Szymon Morek
3596522637 refactor: remove unused logic in ULLS controller
Related-To: NEO-13843

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-17 18:35:20 +02:00
Oskar Hubert Weber
1816c8eac4 fix: avoid joining thread in deferred deleter
Join thread in DllMain (which we are not aware of)
can result in hang occurring in DeferredDeleter, if the library is
freed before FreeLibraryAndExitThread call from within the worker thread,
the thread gets stuck, thus the main thread is stuck on worker->join().

Related-To: NEO-14121

Signed-off-by: Oskar Hubert Weber <oskar.hubert.weber@intel.com>
2025-04-17 16:17:42 +02:00
Fabian Zwoliński
ee769f5983 fix: Add texture cache flush after kernels writing to images on imm cmdlists
- add `hasImageWriteArg` flag to KernelDescriptor,
based on image access qualifier
- add `isPostImageWriteFlushRequired` method to productHelper,
to require cache flush only on selected platforms
- if possible, add the `textureCacheInvalidationEnable` arg to the
existing PC, otherwise add a new PC

Related-To: NEO-13427, HSD-18041321008
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-04-17 16:04:31 +02:00
Young Jin Yoon
5a2a792c34 Revert "refactor: add EncodePostSyncArgs to EncodeDispatchKernelArgs"
This reverts commit 40aef1555e.

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-17 15:37:05 +02:00
Compute-Runtime-Validation
b96cf55985 Revert "fix: Return max wg count equal one on platforms without dispatch all ...
This reverts commit b8be602bfb.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-04-17 12:10:11 +02:00
Lukasz Jobczyk
d9a40734ae performance: Remove global fence from CW post sync on BMG
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-17 10:23:40 +02:00
Young Jin Yoon
40aef1555e refactor: add EncodePostSyncArgs to EncodeDispatchKernelArgs
Refactored various member variables in EncodeDispatchKernel to directly
include EncodePostSync
Changed command encoder and command list to use the modified
EncodeDispatchKernel.

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-16 17:46:07 +02:00
Lukasz Jobczyk
f335295432 test: correct uint32_t
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-16 17:22:44 +02:00
Lukasz Jobczyk
0c778ef6f4 performance: Remove global fence from command stream on BMG
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-16 16:01:05 +02:00
Szymon Morek
4d60465a9e fix: don't flush texture cache if not required
Related-To: NEO-14645

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-16 10:38:24 +02:00
Mateusz Jablonski
f6b92aa5d5 build: update default PTL revision to B0
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-04-16 09:44:58 +02:00
Tomasz Biernacik
eff2d1cde8 performance: change usage for semaphoreBuffer on integrated devices
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-04-16 09:07:05 +02:00