Commit Graph

4606 Commits

Author SHA1 Message Date
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
Chandio, Bibrak Qamar bed2ad1ac0 feature: memAdise for System Allocator
Related-To: NEO-13715

Implements basic functionality for zeCommandListAppendMemoryAdvise for
system allocator

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-04-16 07:11:14 +02:00
Maciej Plewka b8be602bfb fix: Return max wg count equal one on platforms without dispatch all support
Related-To: NEO-14125, GSD-10725
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-04-15 15:41:23 +02:00
Maciej Bielski bf68fed199 test: mark a function as override
Clang-tidy rule: `[modernize-use-override]`

Related-To: NEO-14506
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-04-15 14:32:27 +02:00
Lukasz Jobczyk f7939735da refactor: Adjust USM cleaner to ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-15 14:05:02 +02:00
Lukasz Jobczyk 455209aadc refactor: Simplify fence selection in ULLS
Related-To: NEO-14642

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-15 14:04:47 +02:00
Marcel Skierkowski 31f0fd4672 refactor: rename variable slmSize
Max programmable slm size is stored in RuntimeCapabilityTable as slmSize.
That is misleading name
Rename the variable slmSize to better reflect the actual meaning of the member.

Related-To: NEO-12949
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
2025-04-14 20:00:29 +02:00
Chodor, Jaroslaw 7bded13638 feature: Enabling support for redirecting FCL to IGC for OCL
This allows for invoking IGC as OCL C translator in OpenCL paths

Accepted debug env :
UseIgcAsFcl=1 ; forces IGC
UseIgcAsFcl=2 ; forces FCL
UseIgcAsFcl=0 ; uses defaults

Related-To: NEO-14473
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-04-14 18:41:48 +02:00
Jaroslaw Warchulski 3e1aa33924 refactor: cleanup headers
Related-To: NEO-5548
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-04-14 14:59:40 +02:00
Maciej Bielski 6ecf5b373e feature: exit with warning if small bar detected on Linux
Return early and provide justification, otherwise SIGBUS error is
returned.

Related-To: NEO-14506
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-04-14 14:43:25 +02:00
Marcel Skierkowski e82be94368 refactor: Modernize writeDataToFile function
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
2025-04-14 14:28:58 +02:00
Kamil Kopryk dd3d294f87 performance: cache MOCS values
This change caches the most used MOCS values:

* getMOCS(GMM_RESOURCE_USAGE_OCL_BUFFER_CONST);
* getMOCS(GMM_RESOURCE_USAGE_OCL_BUFFER);
* getMOCS(GMM_RESOURCE_USAGE_OCL_BUFFER_CACHELINE_MISALIGNED);
inside gmmHelper class during initialization to avoid repeated
calls of virtual functions, branches and/or gmm lib access.

and adds more readably corresponding getters:
* getL1EnabledMOCS
* getL3EnabledMOCS
* getUncachedMOCS

If force all resources uncached is called,
these 3 cached mocs values are reinitialized

It also changes the order of gmmHelper members, to avoid
not needed padding after addressWidth
and simplifies logic in getMocsIndex function
for xehp and later products.

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-04-14 14:12:48 +02:00
Tomasz Biernacik 194c3058b8 performance: change usage for ringBuffer on integrated devices
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-04-14 12:25:38 +02:00
Tomasz Biernacik 18435df04c fix: unify deferring MOCS to PAT
Related-To: NEO-14643

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-04-11 20:10:25 +02:00
Chodor, Jaroslaw 9e14eaaed1 feature: Adding support for scoped debug variables
This allows for limitting debug variables to specific
components.

Related-To: NEO-14473
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-04-11 17:52:17 +02:00
Szymon Morek 5b20450162 performance: enable compression on PTL
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-11 17:26:29 +02:00
Igor Venevtsev ef52479ce4 feature: add FillImage1dBuffer built-in kernel
Resolves: NEO-13984, HSD-18041422852

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
2025-04-10 14:04:13 +02:00
Damian Tomczak f9516b8723 test: remove DEFAULT_TEST_FAMILY_NAME from fixture
Related-to: NEO-14395

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-04-09 23:29:25 +02:00
Marcel Skierkowski 5d01677454 refactor: Mock file system in ULTs
Functions: fileExists and loadDataToFile
use IO functions from namespace IoFunctions

Now tests that use these functions
are mocked by default,
but some still require access to real files
and have been restored the ability to read files.
They will be mocked in next PRs.

Related-To: NEO-7006
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
2025-04-09 19:51:46 +02:00
Young Jin Yoon 077fe1ab48 test: simplify postsync mocs tests for gen12lp
Fixed a clang-format error on unassigned value comparison with
one of command_encoder tests for gen12lp

Related-To: NEO-13003
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-09 19:51:31 +02:00
Maciej Plewka 286acf30a3 fix: Dispatch residency fence when stopping ulls on windows
Related-To: NEO-14396, HSD-18041496023, HSD-13012953666, NEO-14611
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-04-09 19:51:16 +02:00
Szymon Morek f4815a9b69 performance: enable ULLS on LNL Linux
Related-To: NEO-9004

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-09 14:45:46 +02:00
Lukasz Jobczyk 1b5519a880 fix: Adjust standard heaps when on 57 bit address space
Resolves: GSD-10871

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-09 12:51:03 +02:00
Fabian Zwoliński 363aa8cdbd performance: align local memory Tag allocations to 2MB
Align local memory allocations of tag types to 2MB when
2MB alignment is enabled via the product helper
(is2MBLocalMemAlignmentEnabled flag).

Refactored the allocateGraphicsMemoryInDevicePool function to improve
readability and maintainability. Simplified the logic for
determining base size and final alignment by reducing redundant code.

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-04-09 09:59:44 +02:00
Aravind Gopalakrishnan c7fe7dde90 fix: Correct Xe sysfs paths for ccs mode setting
Fix the sysfs paths for Xe KMD

Related-To: NEO-10378

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-04-09 06:51:18 +02:00
Marcel Skierkowski 4b75d9b218 test: mock filesystem in setting manager
Related-To: NEO-14084
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
2025-04-08 18:41:15 +02:00
Bartosz Dunajski ab7364ae19 test: improve HWTEST2_F macro
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-04-08 17:18:14 +02:00
Maciej Plewka bb36614567 fix: add separate counter for tracking ring buffer completion
Related-To: NEO-14396, NEO-9548
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-04-08 16:30:44 +02:00
Jaroslaw Warchulski fb5da0c3e5 fix: do not forbid compression for xe_lpg Windows and DG2
Related-To: NEO-14583, NEO-14593
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-04-08 16:08:59 +02:00
Mateusz Jablonski 1c377dc930 fix: ensure payload arguments are patched before walker command is fetched
In case of indirect kernel launch some payload arguments are patched
just before walker command, this change disables prefetch, performs
batch buffer start to next bytes and then re-enable prefetch. All these
operations are performed between MI_STORE_REGISTER_MEM and COMPUTE_WALKER

Related-To: NEO-14584
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-04-08 11:57:45 +02:00
Lukasz Jobczyk ca45573dd3 fix: Handle new ring buffer residency when switch ULLS light ring
Related-To: NEO-14406, NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-08 10:12:57 +02:00
Young Jin Yoon 0de024dbf9 refactor: separate post-sync into EncodePostSync
Created EncodePostSync template struct to organize various post-sync
variables/functions from EncodeDispatchKernel

Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-04-07 20:06:14 +02:00
Vysochyn, Illia 950e4a22d8 test: Remove trailing whitespaces
Related-To: NEO-13972

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-04-07 16:34:38 +02:00
Vysochyn, Illia 146a7f7b9b feature: Add support for BUFFER_SIZE explicit argument
Related-To: NEO-13972

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-04-07 14:15:26 +02:00
Lukasz Jobczyk 8978ea5e5a performance: Do not create global fence allocation on integrated
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-07 11:22:04 +02:00
Jaroslaw Warchulski df07897144 fix: forbid compression for pre-xe2 platforms
Related-To: NEO-9465
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-04-05 00:15:16 +02:00
Compute-Runtime-Validation f332571d96 Revert "performance: Do not create global fence allocation on integrated"
This reverts commit ecf8a07d26.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-04-04 16:26:19 +02:00
Dominik Dabek bd516b3552 fix: usm reuse, clean from largest
When trimming old allocations in usm reuse start from largest
allocations.
This will reduce memory usage more quickly once max hold time is hit.

Related-To: NEO-6893, NEO-14429

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-04-04 14:57:15 +02:00
Lukasz Jobczyk ecf8a07d26 performance: Do not create global fence allocation on integrated
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-04 11:45:22 +02:00
Dominik Dabek 3703ff550c fix: use real size when putting into usm reuse
Real allocation size should be used to properly apply limits and allow
more usm reuse hits.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-04-04 09:44:32 +02:00
Chandio, Bibrak Qamar f344eb9bca test: ULT for makeResidentResources
Related-To: NEO-14056

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-04-04 05:55:08 +02:00
Mateusz Jablonski bb518adf34 fix: patching payload arguments in inline data in case of indirect kernel
Related-To: NEO-14532
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-04-03 17:21:28 +02:00
Szymon Morek 95e0244f70 fix: properly pass info about 3D image
Related-To: NEO-14538

It's valid for 3D image to copy 2D region.
Current checks for mip map do not consider that.
This change correctly checks for mip mapped 3D image.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-03 16:33:57 +02:00
Dominik Dabek be27367020 performance: usm reuse, avoid looking up svmData
Save svmData on putting into reuse, instead of searching each time.
Change UNRECOVERABLE_IF to DEBUG_BREAK_IF.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-04-03 15:50:49 +02:00
Jaroslaw Warchulski c010d17842 fix: respect compression flag in capability table
Related-To: NEO-9465
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-04-03 15:36:55 +02:00
Szymon Morek 6ea83f322d fix: do not override user data beyond slice region
Related-To: NEO-14538

If user passes slice pitch which is larger than region
to copy, do not override memory beyond region but within
that slice pitch.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-03 12:37:35 +02:00
Jaroslaw Warchulski 62baf28316 fix: remove unnecesarry WA for DG2 compression
Related-To: NEO-9465
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-04-03 08:04:19 +02:00
Brandon Yates 4651e72b0b fix: Fail device init if kernel debugging is misconfigured
Also print error to stderr

Related-to: GSD-10780

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-04-02 21:06:30 +02:00
Filip Hazubski 504440fc4d feature: Add ftrHeaplessMode flag
Pass hwInfo to isHeaplessModeEnabled and isForceBindlessRequired functions.

Related-To: NEO-14526

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2025-04-02 21:06:05 +02:00
Lukasz Jobczyk deca36fd32 fix: Stop ULLS light when evict resource
Related-To: NEO-14406

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-04-02 16:37:43 +02:00
Fabian Zwoliński 7ef3880793 feature: implement pool allocator for gpuTimestampDeviceBuffer
The patch applies to Level Zero.
Only allocations < 2MB will be fetched from the pool.
Allocations are shared and reused within a given device.

Additionally, I added a new debug flag to control the allocator:
EnableTimestampPoolAllocator

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-04-02 14:28:56 +02:00
Szymon Morek 8836f6df0b fix: forward mip map level for 3D images
Related-To: NEO-14539

1D and 2D images have already mip map level set correctly.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-02 11:46:41 +02:00
Aravind Gopalakrishnan 3a7d7e022c fix: Add platform support for reservation on svm heap
Related-To: GSD-10816

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-04-02 02:46:30 +02:00
Szymon Morek 3010af596e performance: add infrastructure for staging with 3D images
Related-To: NEO-14026

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-04-01 15:30:30 +02:00
Andrzej Koska e3e01e94a0 Revert "performance: enable Direct Submission on LNL Linux"
This reverts commit cb3b4d326d.

Related-To: NEO-14517, NEO-9004

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-03-31 15:22:29 +02:00
Maciej Plewka a5e19330e9 fix: lock csr before locking residency controller in trim to budget path
Lock on csr is needed before lock on residency controller to prevent
incorrect lock order. Csr may be locked in waitOnCpu called from trimToBudget,
which may lead to deadlocks

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-03-28 16:18:20 +01:00
Szymon Morek 3fff3dd77b fix: set misaligned source memory 1-way coherent
Related-To: NEO-14443

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-28 14:16:45 +01:00
Compute-Runtime-Validation 88a48f1c5b Revert "performance: Improve ULLS light residency management"
This reverts commit 35eae3f977.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-28 11:21:27 +01:00
Mateusz Hoppe c105c77930 fix: calculation of os context count
Related-To: NEO-12952

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-03-28 09:55:17 +01:00
Andrzej Koska cb3b4d326d performance: enable Direct Submission on LNL Linux
Related-To: NEO-9004

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-03-27 17:09:54 +01:00
Lukasz Jobczyk b43b23b6ed fix: Init wait utils after hwInfo init for both OS
Resolves: HSD-18041922513

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-27 16:45:22 +01:00
Szymon Morek ead0842763 feature: add L0 API to query kernel argument info
Related-To: NEO-14358

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-27 16:43:33 +01:00
Bartosz Dunajski 85f2734ca4 fix: correct gt_id to tile_id engine mapping
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-03-27 15:57:57 +01:00
Dominik Dabek c76edaba4e fix: enable usm reuse limit based on memory usage
Related-To: NEO-14160, NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-03-27 15:14:08 +01:00
Dominik Dabek 915d657420 fix: flag to limit usm reuse based on memory usage
Host usm and device usm for igfx checks system memory usage.
Device usm for dgfx checks local memory usage.

If used memory is above limit threshold:
- no new allocations will be saved for reuse
- cleaner will use shorter hold time of 2 seconds
- cleaner will free all eligible allocations, regardless of async
deleter thread having work

Motivation: in case of gfx memory being full, making resident new
allocations will require evictions which leads to massive slowdown on
enqueue calls.
This change aims to minimize cases where extra memory usage from usm
reuse mechanism leads to above situation.

Related-To: NEO-6893, NEO-14160

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-03-27 10:25:19 +01:00
Jack Myers 0aa2c4f0cb feature: allow removal of heapful code paths
Related-To: NEO-13007

Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-03-27 01:34:35 +01:00
Damian Tomczak 0243004907 feature: additional checkers to enable feature
Resolves: NEO-13973

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-26 18:06:20 +01:00
Mateusz Jablonski 4bc13fa0dc fix: correct MetricsLibraryGenId for Xe3
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-03-26 16:35:10 +01:00
Lukasz Jobczyk 60b551758c performance: Adjust waitpkg threshold for discrete devices
Related-To: NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-26 14:59:19 +01:00
Compute-Runtime-Validation a89113fa1a Revert "fix: Fail device init if kernel debugging is misconfigured"
This reverts commit c122bc51f9.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-26 13:27:12 +01:00
Compute-Runtime-Validation 214277125d Revert "performance: enable ULLS on LNL Linux"
This reverts commit a15de0c4f6.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-26 13:26:57 +01:00
Brandon Yates c122bc51f9 fix: Fail device init if kernel debugging is misconfigured
Also print error to stderr

Related-to: GSD-10780

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-03-25 20:40:25 +01:00
Jaroslaw Warchulski 75119f1887 test: add compression_tests_xe2_and_later
Related-To: NEO-9465

Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-03-25 18:15:20 +01:00
Lukasz Jobczyk 35eae3f977 performance: Improve ULLS light residency management
-skip bo::wait if completion fence not needed
-do not restart exec on evict

Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-24 17:48:55 +01:00
Pratik Bari f67663d863 fix(sysman): Create Engine Handles for multiple gt w.r.t Xe driver
For the Xe driver, a single tile can have multiple gts. Now the Engine
handles are created for multiple gts available on the single tile as in
the case for the Xe driver.

Related-To: NEO-14401

Signed-off-by: Pratik Bari <pratik.bari@intel.com>
2025-03-24 17:14:02 +01:00
Szymon Morek ad49418575 test: change incorrect name of constant
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-24 17:13:45 +01:00
Kamil Kopryk 73795ced64 refactor: add setupTimestampPacketFlushL3 function
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-24 13:10:03 +01:00
Lukasz Jobczyk 8fbde30432 fix: Adjust waitpkg threshold to 12 us
Resolves: NEO-14434, NEO-14435
Related-To: NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-24 11:43:54 +01:00
Szymon Morek a15de0c4f6 performance: enable ULLS on LNL Linux
Related-To: NEO-9004

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-24 10:44:23 +01:00
Tomasz Biernacik f4f13dfeec Revert "performance: disable cpu caching for buffers on PTL"
This reverts commit c3f0c4e4ac.

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-24 10:23:07 +01:00
Dominik Dabek 6e998fc3c1 fix: move host usm reuse max size to mem manager
Intialize value on memory manager creation.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-03-24 08:53:30 +01:00
Lukasz Jobczyk 54cb0e24f8 performance: Switch waitpkg use to tpause for ULLS light
Related-To: NEO-13922, NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-21 18:09:37 +01:00
Szymon Morek bb10290828 fix: make misaligned user memory 2-Way coherent
Related-To: NEO-9004

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-21 17:56:37 +01:00
Lukasz Jobczyk 7c75807987 performance: Enable waitpkg with tpause
Resolves: NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-21 17:30:55 +01:00
Maciej Plewka 1b7bf690d2 fix: update fence values when residency list passed to switch ring buffer
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-03-21 12:26:08 +01:00
Lukasz Jobczyk 8a85a96ed2 feature: Add 3-level wait scheme with tpause intrinsic
Related-To: NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-21 12:12:57 +01:00
Aravind Gopalakrishnan 4e9afb32e6 refactor: Fix coverage issue with parse ccs mode
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-03-21 11:12:24 +01:00
Chodor, Jaroslaw 0bff9def3b feature: New allocators for opaque arrays
Adds fast allocators for opaque objects of uniform size.

Related-To: NEO-13406

Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-03-20 21:59:44 +01:00
Damian Tomczak 1995a7fbcf feature: additional fixes to enable feature and adjusting builtins types
Resolves: NEO-13973

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-20 14:23:08 +01:00
Lukasz Jobczyk 75461d190d performance: Adjust umwait counter value
Related-To: NEO-13922, NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-20 13:57:25 +01:00
Damian Tomczak e6ff523a8e fix: heapless has the highest priority as builtin
Related-to: NEO-13973

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-20 08:10:44 +01:00
Aravind Gopalakrishnan 724ba20e41 fix: Parse CCS mode setting for non PVC platforms
Related-To: GSD-8785

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-03-19 12:47:46 +01:00
Lukasz Jobczyk 6cb52f71b4 fix: Avoid mutex deadlock when switch ulls light ring buffer
Related-To: NEO-14406

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-19 11:47:40 +01:00
Jitendra Sharma dda7876d3a feature: Introduce SipClassType::externalLib
Related-To: NEO-13737
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2025-03-19 11:06:03 +01:00
Jack Myers 0e25970853 fix: re-add switch case for once writable query
A change related to the tbx fault manager
incorrectly removed a switch case from
`AubHelper::isOneTimeAubWritableAllocationType`.

This fixes that and refactors some APIs to prevent
similar mistakes from happening again by cleaning
up logic.

Addresses show stopper for pre-si pytorch workflows.

Resolves: NEO-14399
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-03-19 09:54:54 +01:00
Kamil Kopryk 2e729bcb4c refactor: move isTimestampWaitSupportedForQueues to productHelper
Related-to: NEO-13163
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-19 09:31:33 +01:00
Compute-Runtime-Validation 5f7f0dd785 Revert "performance: Enable waitpkg"
This reverts commit 8ec5434460.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-18 13:28:29 +01:00
Maciej Plewka 36fa6d66ae fix: lock csr in stopDirectSubmission if needed
Related-To: NEO-13875, NEO-14143, HSD-16026538384, HSD-16026780358
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-03-18 09:30:38 +01:00
Compute-Runtime-Validation ce2fbb87ba Revert "feature: additional checkers to enable feature"
This reverts commit dbd7d00b27.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-18 03:12:47 +01:00
Damian Tomczak dbd7d00b27 feature: additional checkers to enable feature
Resolves: NEO-13973

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-17 23:32:21 +01:00
Maciej Bielski a7c46b8213 feature: support L2 cache reservation
Related-To: NEO-12837
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-03-17 19:41:55 +01:00
Michał Pryba 117f4c8d32 test: fix ults that are not freeing Sip kernel correctly
Related-To: NEO-13839
Signed-off-by: Michał Pryba <michal.pryba@intel.com>
2025-03-17 18:53:12 +01:00
Mateusz Hoppe 9d052cd8ee fix: pass rootDevice when creating secondary contexts
- fix initialization of gfxCoreHelper in drm and wddm

Related-To: NEO-7824, NEO-8171

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-03-17 16:03:27 +01:00
Compute-Runtime-Validation d54b74e8bd Revert "fix: Parse CCS mode setting for non PVC platforms"
This reverts commit 5ca78dfdd1.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-17 00:30:44 +01:00
Aravind Gopalakrishnan 5ca78dfdd1 fix: Parse CCS mode setting for non PVC platforms
Related-To: GSD-8785

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-03-15 01:39:51 +01:00
Kamil Kopryk 7f607427fa fix: correct dsh generation
Don't use hardcoded sampler state and sampler border color state sizes.

Related-To: NEO-14216

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-14 21:18:38 +01:00
John Falkowski a72b22c2ce test: Implement clang tidy fix for prefecth_manager_tests.cpp
Related-To: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
2025-03-14 19:01:15 +01:00
Kamil Kopryk 2c77d2c698 refactor: add SetMaxBVHLevels debug flag
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-14 16:59:48 +01:00
Kamil Kopryk 01edd58be4 refactor: add additional check in addFlushRequiredCommand
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-14 13:54:20 +01:00
Tomasz Biernacik afcbebef0b Revert "performance: configure Xe2 compression"
This reverts commit ec7821ed84.

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-14 11:25:20 +01:00
Jack Myers 5f78147e16 fix: hotfix for svmcpu tbx uploads
Test program in the linked, related issue
is crashing in tbx mode. Tbx server indicated
upload of invalid memory was made before exit.

Running with debug messages showed that the
problematic upload was an svmcpu buffer when
running neo with separate cpu and gpu
buffers for shared memory management.

Using this info, the problem was narrowed down
to a missing unprotect call in page fault manager
related code, resulting in a protected(invalid)
memory region getting uploaded to tbx.

It is unclear yet why this unprotect call was not made,
since other svmcpu buffers were uploaded without issue.

This hotfix forces the unprotect call in the fault handler,
which allows the test program to run to completion. However,
there is now a failing test case.

Considering the critical nature of the associated
NEO issue and that this patch should unblock
the work depending on the fix, this hotfix should
get merged regardless of the failing test case.

In the meantime, I will continue triaging the
failing test and will implement a proper fix
once the root cause is isolated.

Related-To: NEO-13404
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-03-14 04:47:21 +01:00
Compute-Runtime-Validation 13db35c35f Revert "fix: set correct default value of cacheable flag"
This reverts commit a8d9e7ed35.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-13 20:38:57 +01:00
Tomasz Biernacik c3f0c4e4ac performance: disable cpu caching for buffers on PTL
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-13 18:34:42 +01:00
Tomasz Biernacik a8d9e7ed35 fix: set correct default value of cacheable flag
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-13 18:26:02 +01:00
John Falkowski 4d281cf51d feature: Implement appendMemoryPrefetch for Shared System USM allocations
Related-To: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
2025-03-13 06:26:38 +01:00
Zbigniew Zdanowicz ddc0b0d03b feature: disable flat ring buffer for command list append operation
Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-13 06:06:55 +01:00
shubham kumar e287174211 feature: Add EU stall support for xe2/xe3 core
Related-To: NEO-13777

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
2025-03-12 23:10:24 +01:00
Mateusz Hoppe 04cbbe496d test: use proper test name
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-03-12 13:28:50 +01:00
Compute-Runtime-Validation fa2e3adad3 Revert "feature: Implement appendMemoryPrefetch for Shared System USM Allocat...
This reverts commit 97799b3faf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-12 05:55:32 +01:00
Compute-Runtime-Validation 0d5baa2c30 Revert "performance: Cache timestamps on CPU"
This reverts commit 83637404bf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-12 04:41:46 +01:00
Lukasz Jobczyk 8ec5434460 performance: Enable waitpkg
Resolves: NEO-14336

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-11 14:43:01 +01:00
Lukasz Jobczyk 83637404bf performance: Cache timestamps on CPU
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-11 13:40:18 +01:00
Damian Tomczak c90f3fcb3c test: adjusting sampler border color when heapless is enabled
Related-to: NEO-12737

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-11 12:17:22 +01:00
John Falkowski 97799b3faf feature: Implement appendMemoryPrefetch for Shared System USM Allocations
Related-To: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
2025-03-11 09:12:48 +01:00
Mateusz Hoppe 34dad4d3de refactor: store implicit args version in kernel
- adjust tests to work with implicitargs v0 and v1

Related-To: NEO-14115

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-03-10 22:58:57 +01:00
Fabian Zwoliński f5e37e725c Revert "fix: configure ISA Pool params based on productHelper"
This reverts commit bf20ae7ae8.

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-03-10 22:41:13 +01:00
Zbigniew Zdanowicz cd904269ed fix: request for task count should enable monitor fence dispatch
Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-10 18:25:35 +01:00
Tomasz Biernacik ec7821ed84 performance: configure Xe2 compression
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-10 15:40:00 +01:00
Compute-Runtime-Validation 6ee39ed94c Revert "fix: Fail device init if kernel debugging is misconfigured"
This reverts commit b0c92ea425.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-10 12:23:07 +01:00
Brandon Yates b0c92ea425 fix: Fail device init if kernel debugging is misconfigured
Also print error to stderr

Related-to: GSD-10780

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-03-08 05:02:42 +01:00
Zbigniew Zdanowicz f8be8414ac feature: add support for wait event preamble in append command list
- add mechanism in queue to trigger start command from queue to regular
- add detection in immediate command list need to dispatch extra start in queue
- fix secondary linear stream in immediate case as it should not use container
- modify tests for primary batch buffer dispatch as default mode
- remove invalid or obsolete tests

Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-07 20:31:09 +01:00
Maciej Plewka c5e1fcf313 fix: Copy tiled 1D array per array element with BLT
Related-To: NEO-14147, HSD-14024424096, HSD-14024424178
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-03-07 17:29:04 +01:00
Tomasz Biernacik e644b09433 performance: override allocation caching on integrated platforms
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-07 15:44:00 +01:00
Dominik Dabek 2170f5ca88 refactor: usm reuse to unique ptr
Change usm allocation cache in usm manager to unique ptr

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-03-07 15:14:58 +01:00
Lukasz Jobczyk 53062056ec performance: Enable wait pkg for ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-07 12:18:38 +01:00
Jaroslaw Warchulski 413194bd2a Revert "fix: do not prefer image compression on xe_lpg for linux and WSL"
This reverts commit 8814b6ac4f.

Resolves: NEO-14286
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-03-07 11:38:46 +01:00
Maciej Bielski 8ad6a7a86b feature: unify local memory size getter for i915 and xe
Previously i915 was using a sysfs node to query the amount of local
memory of a tile. For xe such sysfs node does not exist so the function
was useless.

Instead of a sysfs node, leverage the local memory size present in
MemoryInfo (queried at init-stage) so that the output is now the same
for both i915 and xe.

Related-To: NEO-11127
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-03-07 09:50:19 +01:00
Damian Tomczak 81b0cac65f fix: raytracing heapless missing allocation
Related-to: NEO-12737

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-03-06 17:26:09 +01:00
Lukasz Jobczyk 61fe9ebb8f performance: Allow power efficient waits with ULLS light
Resolves: HSD-18041633458
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-06 14:20:58 +01:00
Maciej Plewka a93cecac36 fix: treat tiled 1D images as 2D with height 1 for BLT copies
Related-To: NEO-14147, HSD-14024424096, HSD-14024424178
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-03-06 11:22:30 +01:00
Dominik Dabek 9eb8e1812c feature: flag to log usm reuse operations
If flag "LogUsmReuse" is set, usm reuse will log operations to csv file.
Each line will contain: timestamp, host/device, operation type,
allocation size, true/false whether operation succeeded.

This data can then be used to produce graphs and help in analyzing
usm reuse in a particular workload.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-03-06 11:06:27 +01:00
Szymon Morek 82fba79d9d performance: set 1ms timeout for ulls controller on LNL and PTL
Related-To: NEO-13843

Limit scope to Windows only.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-06 09:13:58 +01:00