Commit Graph

4606 Commits

Author SHA1 Message Date
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
Brandon Yates 64b027f71c feature: Add gfxCoreHelper for StateSip required
Related-to: NEO-12967

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-03-05 20:24:17 +01:00
Kamil Kopryk 4c795027e3 refactor: add check if event L3 flush is needed
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-03-05 18:25:29 +01:00
Zbigniew Zdanowicz ae1eb076b7 feature: add optional epilogue to flush task method
Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-05 15:15:59 +01:00
Tomasz Biernacik 92512fdc64 fix: preserve allocation type for memory object
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-03-05 14:48:57 +01:00
Lukasz Jobczyk 5a04d1e10a refactor: Print unknown gmm usage type value
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-03-05 10:34:40 +01:00
Compute-Runtime-Validation 98d1d629a8 Revert "feature: Enable defer backing by default"
This reverts commit fffe8f8027.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-05 03:35:03 +01:00
Compute-Runtime-Validation 3414abe74a Revert "fix: make global fence always resident on linux"
This reverts commit efb814d979.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-03-05 02:07:38 +01:00
Zbigniew Zdanowicz 27d7d72033 feature: add pipeline state management for append command list operation
- command list append state is managed from internal queue and can be skipped
- initial state configuration should be processed by both kernel and non-kernel
- only kernel operation can process required state, as non-kernel cannot change

Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-04 20:43:22 +01:00
Szymon Morek ff4da67979 fix: signal notify field before KMD wait
Related-To: NEO-13870

Currently all monitor fences are triggering
interrupt due to Notify Enable field.
With this change, such field is programmed
right before KMD wait.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-04 15:19:16 +01:00
Bellekallu Rajkiran fffe8f8027 feature: Enable defer backing by default
Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2025-03-04 14:29:53 +01:00
Szymon Morek efb814d979 fix: make global fence always resident on linux
Related-To: NEO-13843

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-03-04 12:32:53 +01:00
Chuansheng Liu 1876a43024 performance: add low latency hint for i915
i915 has provided the low latency hint interface, it helps
improve the performance for light workload a lot.

Related-To: NEO-14250

Signed-off-by: Chuansheng Liu <chuansheng.liu@intel.com>
2025-03-04 11:14:04 +01:00
Bellekallu Rajkiran 7d851dda87 test: Add command encoder tests
Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2025-03-04 05:58:50 +01:00
Zbigniew Zdanowicz db99c25c79 feature: add support to dispatch epilogue commands into dedicated stream
Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-03-03 14:39:34 +01:00
Jaroslaw Warchulski 8814b6ac4f fix: do not prefer image compression on xe_lpg for linux and WSL
Related-To: HSD-18034872015
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-02-28 14:20:57 +01:00
Zbigniew Zdanowicz 08b13750a1 fix: set stall cmd flag for bcs flush task count flag
Related-To: NEO-10356

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-02-28 12:24:51 +01:00
Andrzej Koska 021723e154 fix: Removal of unnecessary offsets during blitter copying
When copying with the blitter and setting ArrarIndex to zero, additional
offsets from the origin are no longer necessary

Related-To: NEO-14171

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-02-28 09:32:19 +01:00
Kamil Kopryk 4503972faf refactor: add adjustSamplerStateBorderColor function
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-02-27 14:05:09 +01:00
Jaroslaw Warchulski 837d6f5ad1 fix: do not enable compression on xe_lpg for linux and WSL
Resolves: HSD-18034872015
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-02-27 11:12:23 +01:00
Compute-Runtime-Validation c02dc8208c Revert "fix: do not enable compression on xe_lpg"
This reverts commit a6abda83a4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-27 03:15:32 +01:00
Lukasz Jobczyk 20d29207cd refactor: Allow debug key to force USM cleaner with ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-26 17:52:18 +01:00
Vysochyn, Illia 1eafbc30f8 feature: Enable eu thread scheduling mode override via IDD
Enables eu thread scheduling mode override via the
INTERFACE_DESCRIPTOR_DATA and COMPUTE_WALKER.

Defines encodeEuSchedulingPolicy operating on INTERFACE_DESCRIPTOR_DATA
or Xe3 platform.

Adds tests verifying that thread scheduling mode can be overridden via
COMPUTE_WALKER.

Related-To: NEO-13771, HSD-18041256338, HSD-14013056398

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-02-26 17:04:43 +01:00
Wojciech Konior 7f81d0e3e8 fix: vmbind of i915 canonization check
Related-To: NEO-7313

Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
2025-02-25 19:00:31 +01:00
Jaroslaw Warchulski a6abda83a4 fix: do not enable compression on xe_lpg
Resolves: HSD-18034872015
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-02-25 18:05:56 +01:00
Mateusz Jablonski 374863ba08 refactor: remove cl pipe related logic
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-25 17:56:53 +01:00
Jitendra Sharma d480cc093c feature: Add method to determine if Sip should be get from external library
Related-To: NEO-13735
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2025-02-25 15:14:54 +01:00
Mateusz Hoppe 291745cdf7 feature: add support for ImplicitArgs versioning
- define ImplicitArgs version 1

Related-To: NEO-14115

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-02-25 10:27:11 +01:00
Slawomir Milczarek 0a7ed9f9f4 feature: Add ioctl helpers for primary contexts
Related-To: NEO-12952

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
2025-02-24 17:37:05 +01:00
Compute-Runtime-Validation f907c7dcb2 Revert "performance: set 1ms timeout for ulls controller since xe2"
This reverts commit 28c008e438.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-24 15:04:54 +01:00
Lukasz Jobczyk be946ae56c performance: Optimize make resident for ULLS light
Do not check if ULLS light is active during every Csr::makeResident
call. Store that information once during ULLS init.

Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-24 12:59:56 +01:00
Mateusz Jablonski 50e22ef5e7 refactor: remove device enqueue specific code
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-24 12:37:51 +01:00
Compute-Runtime-Validation f64fd7fc42 Revert "performance: disable cpu caching for buffers on PTL"
This reverts commit 681ef3693a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-24 10:07:15 +01:00
Lukasz Jobczyk 1f7c67ea8d performance: Enable ULLS light for ARLH
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-21 18:00:46 +01:00
Compute-Runtime-Validation 66c4288494 Revert "fix: using canonized addr in xe kmd"
This reverts commit 683d7c7acf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-21 17:49:05 +01:00
Lukasz Jobczyk 91c07e24f6 performance: Enable ULLS light for MTLH
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-21 16:52:02 +01:00
Lukasz Jobczyk cad776412b performance: Enable ULLS light for ARLS, ARLU, MTLU
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-21 16:10:18 +01:00
Wojciech Konior 683d7c7acf fix: using canonized addr in xe kmd
Related-To: NEO-7313

Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
2025-02-21 16:06:06 +01:00
Lukasz Jobczyk 5961850bbc fix: blink ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-21 13:31:35 +01:00
Szymon Morek 681ef3693a performance: disable cpu caching for buffers on PTL
Related-To: NEO-14168

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-21 13:07:04 +01:00
Compute-Runtime-Validation a929551cb2 Revert "performance: Enable ULLS light for ARLS, ARLU, MTLU"
This reverts commit 0b6b51fa19.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-21 09:35:00 +01:00
Szymon Morek 01a66a9347 fix: download staging buffer before reading from it
Related-To: NEO-14154

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-21 09:30:23 +01:00
Compute-Runtime-Validation dda4beb719 Revert "performance: enable Direct Submission on LNL Linux"
This reverts commit b7d21b135c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-21 04:13:28 +01:00
Mateusz Jablonski 70f3342c2d refactor: remove vme specific code
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-20 17:08:52 +01:00
Filip Hazubski 794b21a3fa refactor: Add extra parameters to computeSlmValues function
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2025-02-20 15:35:52 +01:00
Radoslaw Jablonski b7d21b135c performance: enable Direct Submission on LNL Linux
Related-To: NEO-9004

Signed-off-by: Radoslaw Jablonski <radoslaw.jablonski@intel.com>
2025-02-20 15:22:44 +01:00
Mateusz Jablonski 7865509aa0 feature: enable WMTP on BMG
Related-To: NEO-12814
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-20 12:52:40 +01:00
Compute-Runtime-Validation 0996247dfd Revert "performance: Enable ULLS light for MTLH"
This reverts commit 7a62f27d8b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-20 11:11:51 +01:00
Bartosz Dunajski a0a735804f feature: disable counter caching for external storage Events
Related-To: NEO-13971

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-02-20 11:11:29 +01:00
Fabian Zwoliński bf20ae7ae8 fix: configure ISA Pool params based on productHelper
When is2MBLocalMemAlignmentEnabled returns true,
increase pool size for builtins from 64k to 2MB.

Additionally, set appropriate alignment for kernel ISA heap allocations.
Additionally, configure isaAllocationPageSize based on productHelper

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-02-20 08:42:35 +01:00
Compute-Runtime-Validation 29b3cb3c85 Revert "performance: Enable ULLS light for ARLH"
This reverts commit 20d00f53eb.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-20 03:54:49 +01:00
Maciej Plewka 8ba43065c5 fix: handle literal raw strings correctly in printf formater
Related-To: NEO-14138
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-02-19 17:14:54 +01:00
Lukasz Jobczyk 7a62f27d8b performance: Enable ULLS light for MTLH
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-19 16:25:08 +01:00
Lukasz Jobczyk 20d00f53eb performance: Enable ULLS light for ARLH
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-19 15:55:07 +01:00
Lukasz Jobczyk 0b6b51fa19 performance: Enable ULLS light for ARLS, ARLU, MTLU
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-19 15:47:50 +01:00
Lukasz Jobczyk 42261526e4 refactor: Handle dlopen error
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-19 15:28:48 +01:00
Szymon Morek 28c008e438 performance: set 1ms timeout for ulls controller since xe2
Related-To: NEO-13843

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-19 13:48:26 +01:00
Lukasz Jobczyk b0e3d8656e refactor: Add OV detection mechanism for ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-19 13:28:29 +01:00
Jitendra Sharma 2daca51bd9 build: update eudebug headers
Related-To: NEO-14069
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2025-02-19 09:22:15 +01:00
Bellekallu Rajkiran ff9d0d7ea0 fix: fix setting up ccs mode
Related-To: NEO-14122

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2025-02-18 17:10:51 +01:00
Bartosz Dunajski c1f2ff1ad6 fix: disable batched dispatch mode in aub csr
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-02-18 13:45:15 +01:00
Jack Myers c26d24e555 fix: tbx page fault manager hang issue
- Updated `isAllocTbxFaultable` to exclude `gpuTimestampDeviceBuffer` from being
faultable.
- Replaced `SpinLock` with `RecursiveSpinLock` in `CpuPageFaultManager` and
`TbxPageFaultManager` to allow recursive locking.
- Added unit tests to verify the correct handling of `gpuTimestampDeviceBuffer`
in `TbxCommandStreamTests`.

Related-To: NEO-13748
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-02-18 05:05:38 +01:00
Mateusz Hoppe 9c962cdbc8 test: fix error message in opencl ULTs
- opencl ults do not require changing directory
- fix base execution directory for all aub test modes

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-02-18 02:44:02 +01:00
Lukasz Jobczyk 051f7928f1 performance: tiny improvements for ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-17 23:52:33 +01:00
Fabian Zwoliński ad968550e8 fix: separate isUsmPoolAllocatorSupported for host and device
Related-To: NEO-12287, HSD-18041505773

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-02-17 11:47:34 +01:00
Maciej Bielski 6924a48ca6 refactor: prepare CLOS logic for extension
Prepare cache setup and reservation logic to be extended w.r.t other
cache-levels.

Conceptually this change is like adding a switch-statement, in several
places, in which existing code makes a single (and only) case. This is
caused by splitting larger development to ease the review. Further cases
will be added in following steps. Such approach sometimes creates code
which may seem redundant but it is meant to simplify plugging following
extensions in an easy way.

Related-To: NEO-12837
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-02-17 10:43:08 +01:00
Mateusz Jablonski 24a61d096d fix: correct logic of groupDevices function
discrete devices should be exposed before integrated devices

Related-To: NEO-14062
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-16 14:27:44 +01:00
Lukasz Jobczyk 14b89591e6 performance: Disable gem close worker for ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-14 19:03:28 +01:00
Brandon Yates 4da8a3694c feature: Enable page faults for xe driver with debugger on
Related-to: NEO-10134

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-02-14 19:01:55 +01:00
Kamil Kopryk c2387954e9 fix: disable 3d and media sharing support on PVC
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-02-14 17:37:05 +01:00
Lukasz Jobczyk 7cb7229c1c performance: Disable force pin for ULLS light
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-14 15:31:50 +01:00
Lukasz Jobczyk 356d89d608 performance: Disable USM cleaner for ULLS light
Realted-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-14 12:38:16 +01:00
Mateusz Jablonski 6ec92ac082 refactor: move groupDevices logic to shared code
update platforms used in unit test

Related-To: NEO-14062
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-13 21:42:43 +01:00
Lukasz Jobczyk c7c7ae9d49 refactor: Remove redundancy around gemCloseWorker in csr
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-13 21:42:28 +01:00
Kamil Kopryk 2b6442b7a3 refactor: correct matchers and typenames for non-heapless ults
This change includes:
- added corresponding matchers for non-heapless unit tests
- added matcher for binding table state
- corrected type names for the interface descriptor and compute walker


Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-02-13 19:47:57 +01:00
Bartosz Dunajski 68a0aa0525 fix: return correct allocation from InOrderExecInfo getter
Related-To: NEO-13971

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-02-13 17:35:54 +01:00
Lukasz Jobczyk a78e3f98d5 performance: Stop ULLS in bo::wait only when light mode active
Resolves: HSD-18041491739

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-13 17:01:58 +01:00
Compute-Runtime-Validation 1533f07912 Revert "feature: Enable page faults for xe driver with debugger on"
This reverts commit 62b30fa72c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-13 16:37:51 +01:00
Compute-Runtime-Validation b3807e7a36 Revert "feature: Append recorded commandlist into immediate (8/N)"
This reverts commit 9db77efd03.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-13 16:35:40 +01:00
Lukasz Jobczyk f06fb6b6e8 test: close gem close worker thread in ULT
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-13 13:06:28 +01:00
Fabian Zwoliński 1d8c8ac843 refactor: use designated initializers for SmallBuffersParams initialization
Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-02-13 12:32:52 +01:00
Lukasz Jobczyk bc2b49b958 feature: Introduce ULLS light
Add core implementation of ULLS without VM_BIND interface aka ULLS
light.

Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-02-12 17:52:02 +01:00
Szymon Morek 8152241693 fix: don't override user data during staging read
Related-To: NEO-13574

User can read image with row pitch larger than region width.
In such cases, don't override memory which is out of region
but within row pitch.

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-12 16:22:48 +01:00
Aravind Gopalakrishnan 9db77efd03 feature: Append recorded commandlist into immediate (8/N)
- Add primary dispatch capability for immediate command list
- turn off usage of parent linear stream for copy engine

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2025-02-12 12:39:38 +01:00
Compute-Runtime-Validation 116f7270be Revert "fix: tbx page fault manager hang issue"
This reverts commit 7d4e70a25b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-12 10:38:05 +01:00
Jack Myers 7d4e70a25b fix: tbx page fault manager hang issue
- Updated `isAllocTbxFaultable` to exclude `gpuTimestampDeviceBuffer` from being
faultable.
- Replaced `SpinLock` with `RecursiveSpinLock` in `CpuPageFaultManager` and
`TbxPageFaultManager` to allow recursive locking.
- Added unit tests to verify the correct handling of `gpuTimestampDeviceBuffer`
in `TbxCommandStreamTests`.

Related-To: NEO-13748
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-02-12 02:19:37 +01:00
Pawel Cieslak 184378e4df fix: silence new issues with clang-tidy 18 on windows
Signed-off-by: Pawel Cieslak <pawel.cieslak@intel.com>
2025-02-11 13:55:29 +01:00
Chandio, Bibrak Qamar 9d08148846 test: clang tidy errors in drm_buffer_object_tests
Related-To: NEO-11977, GSD-10293

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-02-11 11:08:58 +01:00
Jaroslaw Warchulski 9732653019 performance: reuse usm allocations with similar requested size
Resolves: NEO-14009
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-02-11 10:50:27 +01:00
Mateusz Jablonski d25237c104 fix: pass ReadOnly flag only for page-misaligned input ptr
Related-To: NEO-12986
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-11 10:42:42 +01:00
Brandon Yates 62b30fa72c feature: Enable page faults for xe driver with debugger on
Related-to: NEO-10134

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-02-10 22:25:19 +01:00
Kamil Kopryk 03b56dc919 fix: untrusted input
Do not read an unlimited size of environment variables.

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-02-10 14:54:03 +01:00
Chandio, Bibrak Qamar 7149743162 fix: Set vmbind user fence when makeMemoryResident
Related-To: NEO-11977, GSD-10293

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-02-10 14:20:09 +01:00
Bartosz Dunajski 18d7a22861 refactor: pass increment address and value to dispatch params
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-02-10 14:04:34 +01:00
Dominik Dabek b987877712 fix: remove patchtoken fallback
Related-To: NEO-14028

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-02-10 12:29:45 +01:00
Dominik Dabek e2d317aaee performance: tweak usm reuse cleaner
Cleaner thread will run every 15ms instead of 2s.
Allocations will be held for at least 10s.
If deferred deleter has elements to release, will skip cleaning cache.
Will clean only 1 allocation per cache, per cleaning run.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-02-10 12:18:13 +01:00
Szymon Morek 844a934c15 fix: Add debug flag to enable dummy pages
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-07 20:25:49 +01:00
Filip Hazubski cf8b6435b2 test: fix typo
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2025-02-07 18:11:45 +01:00
Fabian Zwoliński 1eb8e0efd9 fix: configure small buffers params based on productHelper
Refactor buffer pool allocator to support configurable
SmallBuffersParams based on product helper capabilities.

This patch enables setting custom pool
parameters instead of using fixed static values.

For devices with 2MB local memory alignment enabled
(is2MBLocalMemAlignmentEnabled),
use larger pool configuration:
- Pool size: 16MB (up from 2MB)
- Threshold: 2MB (up from 1MB)
- Alignment: 64KB (unchanged)
- Starting offset: 64KB (unchanged)

This improves memory utilization for devices supporting larger memory
alignments
while maintaining original parameters for other devices.

Key changes:
- Moved params from static template to instance member
- Added SmallBuffersParams struct with default/large configs
- Added constructor and setter methods for params configuration

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-02-07 12:01:23 +01:00
Mateusz Hoppe 1877e66bc8 feature: add mechanism to extend cmdlist launch params
Related-To: NEO-13954

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-02-06 22:05:15 +01:00
Mateusz Hoppe 05977f6158 feature: add getMaxLocalSubRegionSize() to product helper
Related-To: NEO-13954

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-02-06 15:20:34 +01:00
Andrzej Koska d0871e0e37 fix: Fix copying with blitter
Related-To: NEO-12134, NEO-13874, NEO-14002

Thanks to this change we avoid programming y1 offset for 2D surface
above the maximum allowable value, i.e. 16 kb for blitter for BMG

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-02-06 14:11:23 +01:00
Compute-Runtime-Validation 5d3a914849 Revert "fix: Fix copying with blitter"
This reverts commit efcbd3875b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-06 02:14:19 +01:00
Jaroslaw Warchulski f07fa90483 fix: set correct allocation size in freeSVMAlloc
Resolves: GSD-10621
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-02-05 20:10:43 +01:00
Brandon Yates f7e63ba0d0 feature: Add support for optional PF enable flag for exec queue create
Related-to: NEO-8306

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-02-05 19:24:01 +01:00
Mateusz Jablonski 81227cedd1 feature: enable WMTP on PTL
Related-To: NEO-13706
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-05 16:59:23 +01:00
Kamil Kopryk b8504913e3 fix: allow for image array type if array size is 1 for Xe2 and later
This commit enabled the use of the array image type with array size 1
from Xe2.
Additinally, it removes two incorrect unit tests, as array size of 0 is not
correct with the OpenCL specification.

Related-To: NEO-13976
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-02-05 13:50:05 +01:00
Szymon Morek b11322332c performance: enable staging write for cl buffers
Related-To: NEO-13529

Also, add size threshold on iGPU on Linux,
and disable staging if imported host ptr could
be reused

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-02-05 09:41:17 +01:00
Andrzej Koska efcbd3875b fix: Fix copying with blitter
Related-To: NEO-12134, NEO-13874

Thanks to this change we avoid programming y1 offset for 2D surface
above the maximum allowable value, i.e. 16 kb for blitter for BMG

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-02-04 19:07:50 +01:00
Mateusz Jablonski d7b0495c90 test: remove usage of IGFX_BROADWELL in tests
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-04 19:07:34 +01:00
Maciej Bielski 971b7c27a2 fix: enable usm compression on linux
Related-To: NEO-12056
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-02-04 13:09:04 +01:00
Naklicki, Mateusz 9aad7750be fix: adjust IGC hwinfo for related tests
Also update builtin kernels


Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2025-02-04 10:05:08 +01:00
Mateusz Hoppe 6e35d055f2 feature: make contextGroupSize dependent on number of processes
Related-To: NEO-12952

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-02-03 18:13:33 +01:00
Bartosz Dunajski dd1e85a3d4 fix: bcs mem fill pattern alignment
Related-To: NEO-13928

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-02-03 14:43:04 +01:00
Bellekallu Rajkiran 3bef9f886a fix: Crash on over memory allocation
- Add defer backing flag to gem create ioctl
- Make memory resident before lock

Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2025-02-03 14:29:42 +01:00
Fabian Zwoliński aab1113632 test: Resolve clang-tidy dead store warning
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-02-03 12:12:36 +01:00
Mateusz Jablonski a924761ed1 fix: correct flags for creating allocation with existing system memory
on Windows setup ReadOnly flag, it makes there is no ProbeForWrite call within
CreateAllocation2 function call

it doesn't force read-only access from GPU perspective, that access it
defined in MapGpuVa function

Related-To: NEO-12986, HSD-15016952776
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-03 11:24:55 +01:00
Maciej Plewka aace15d6bc fix: remove msaa w/a for xe3
Related-To: NEO-13290, NEO-12587
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-02-03 10:38:01 +01:00
shubham kumar f2b48b97d2 refactor: Prework to get sampling unit through ioctl query on xe
Related-To: NEO-13777

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
2025-02-03 10:37:46 +01:00
Compute-Runtime-Validation 99d4e6d054 Revert "performance: don't wait immediately after VmBind"
This reverts commit 09118d2011.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-02 18:00:28 +01:00
Fabian Zwoliński 7e9c358a73 fix: apply 2MB alignment to large local memory image allocations
In this patch, we align up the allocation size to 2MB for all
image allocations >= 2MB located in local memory.
2MB alignment support is defined by function:
`is2MBLocalMemAlignmentEnabled`

Related-To: NEO-12287

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-01-31 14:58:24 +01:00
Compute-Runtime-Validation 3556d9ded6 Revert "fix: set ReadOnly flag when creating allocation with existing system ...
This reverts commit bddb24124d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-31 12:15:12 +01:00
Compute-Runtime-Validation d23249b061 Revert "fix: Set vmbind user fence when makeMemoryResident"
This reverts commit 80dc4fb43a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-31 11:36:29 +01:00
Brandon Yates 635f69e54a fix: Configure scratch pages for debugger
DG2 requires scratch pages on for debugger. Other platforms do not.

Related-to: NEO-13883

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-01-31 06:49:49 +01:00
Brandon Yates 106e8be9a9 fix: Don't abort application due to gpu fault when debugging is enabled
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-01-30 23:37:50 +01:00
Fabian Zwoliński 7918b44a94 fix: apply 2MB alignment to large local memory allocations
In this patch, we align up the allocation size to 2MB for all
allocations >= 2MB located in local memory.
2MB alignment support is defined by function:
`is2MBLocalMemAlignmentEnabled`

Related-To: NEO-12287

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-01-30 22:09:39 +01:00
Bartosz Dunajski 4846fbe410 refactor: unify blit memory fill methods and pass BlitProperties 2
Related-To: NEO-13003

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-01-30 20:16:10 +01:00
Mateusz Jablonski bddb24124d fix: set ReadOnly flag when creating allocation with existing system memory
setting ReadOnly flag makes there is no ProbeForWrite call within
CreateAllocation2 function call

it doesn't make read-only access from GPU perspective, that access it
defined in MapGpuVa function

Related-To: NEO-12986, HSD-15016952776
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-01-30 19:43:44 +01:00
Kamil Kopryk ef896cc799 refactor: introduce ImageSurfaceState helper class
Moved global functions to the ImageSurfaceStateHelper class,
with declarations in the header file and definitions in the base .inl
file.
This change reduces compilation time by:
- removing unnecessary includes from the header file
- adding explicit template instantiations, which are faster than
implicit template instantiations.

Additionally, the image_skl_and_later.inl file has been removed as it
is no longer needed, and its implementation has been moved to the base .inl

Related-To: NEO-12149

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-30 19:20:31 +01:00
Szymon Morek 09118d2011 performance: don't wait immediately after VmBind
Related-To: NEO-13456

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-01-30 18:52:22 +01:00
Maciej Plewka d37943da29 fix: disable xe2 compression only on needed platforms
Related-To: NEO-13381, NEO-13382
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-01-30 16:06:09 +01:00
Radoslaw Jablonski 5f346b57b0 performance: enable Direct Submission on PTL Linux
Related-To: NEO-12982

Signed-off-by: Radoslaw Jablonski <radoslaw.jablonski@intel.com>
2025-01-30 15:35:19 +01:00
Maciej Bielski 8060f04c76 test: simplify test for `getSingleDeviceSharedMemCapabilities()`
Related-To: NEO-10040
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-01-30 13:43:21 +01:00
Lukasz Jobczyk 09e23804dc refactor: Use timestamp types for events and in order nodes
Switching tagAllocation into UC causes regressions in non event
scenarios. It is no longer used as dependant type for semaphores.
Restoring previous GMM_USAGE settings for tag.
Marking events and in order nodes using only timestamp types as they
have proper GMM_USAGE settings already and can be both in smem and lmem.

Resolves: NEO-13847

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-30 12:20:38 +01:00
Compute-Runtime-Validation 768e15bab2 Revert "performance: reduce ULLS controller timeout to 1ms"
This reverts commit 0db7128503.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-30 03:41:58 +01:00
Radoslaw Jablonski 6ead86f0e1 performance: enable PreferredAllocationMethod by KMD on PTL
Related-To: NEO-10526

Signed-off-by: Radoslaw Jablonski <radoslaw.jablonski@intel.com>
2025-01-29 14:11:21 +01:00
Compute-Runtime-Validation 21021f0340 Revert "refactor: unify blit memory fill methods and pass BlitProperties"
This reverts commit d7ca6568fc.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-29 02:09:59 +01:00
Compute-Runtime-Validation 7cbe19c5a9 Revert "fix: Dont enable scratch pages when debugger is on"
This reverts commit 18d04b239e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-29 01:30:59 +01:00
Maciej Bielski a8779c2387 fix: report ZE_MEMORY_ACCESS_CAP_FLAG_CONCURRENT correctly
At the moment the capability is returned only based on the value
returned by the `productHelper`, which is too liberal. The capability
must also consider the support reported by `memoryManager`. Only then
the support reported is aligned with actual logic of handling
USM-allocations.

Related-To: NEO-10040
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-01-29 00:17:38 +01:00
Andrzej Koska 1abb48c3e0 Revert "feature: Enable Tile64 Optimization Flag"
This reverts commit 105a586615.

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2025-01-28 22:32:58 +01:00
Szymon Morek 0db7128503 performance: reduce ULLS controller timeout to 1ms
Currently scope limited to Windows only

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-01-28 22:27:09 +01:00
Chandio, Bibrak Qamar 80dc4fb43a fix: Set vmbind user fence when makeMemoryResident
Related-To: NEO-11977, GSD-10293

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-01-28 22:04:37 +01:00
Bartosz Dunajski d7ca6568fc refactor: unify blit memory fill methods and pass BlitProperties
Related-To: NEO-13003

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-01-28 17:47:31 +01:00
Lukasz Jobczyk 7eac78d253 refactor: Make semaphore dependant resources UC
Change for tagBuffer type on Windows. Timestamp types are already UC on all DC
flush platforms regardless of OS.

Resolves: NEO-13847

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-28 14:51:28 +01:00
Lukasz Jobczyk 82569f6a0f refactor: Switch host events and in order nodes to tagAllocation type
Motivation is to distinguish between host USM resources and internal
driver resources allocated in host memory.

Related-To: NEO-13847

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-28 09:42:19 +01:00
Brandon Yates 18d04b239e fix: Dont enable scratch pages when debugger is on
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-01-27 22:05:34 +01:00
Damian Tomczak 105703b1ae test: CCS and CCCS availability tests
Related-to: NEO-12737

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-01-27 17:16:58 +01:00
Chodor, Jaroslaw beedf709bc feature: LookupArray findGreaterEqual
Adding helpers for find first greater equal
value in lookup array. Useful when finding
minimum SLM encoding that satisfies requirements.

Related-To: NEO-12747

Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-01-27 13:02:02 +01:00
Compute-Runtime-Validation 676334807f Revert "refactor: Switch host events and in order nodes to tagAllocation type"
This reverts commit 8bbba3fe5c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-27 06:44:12 +01:00
Chodor, Jaroslaw 574fe9fb29 refactor: Pass whole kernel descriptor to barrier programming
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-01-27 01:26:49 +01:00
John Falkowski e11e7b9b94 feature: Add shared System USM Allocation in support of appendLaunchKernel
Related-To: NEO-12988

Signed-off-by: John Falkowski <john.falkowski@intel.com>
2025-01-24 23:41:26 +01:00
Szymon Morek 254e7c5c6a fix: set notify enable flag when flushing monitor fence
Related-To: NEO-13848

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-01-24 22:19:24 +01:00
Compute-Runtime-Validation 83af0b77ff Revert "fix: Crash on over memory allocation"
This reverts commit 212ccb8bd4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-24 21:35:59 +01:00
Lukasz Jobczyk 8bbba3fe5c refactor: Switch host events and in order nodes to tagAllocation type
Motivation is to distinguish between host USM resources and internal
driver resources allocated in host memory.

Related-To: NEO-13847

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-24 20:38:56 +01:00
Bellekallu Rajkiran 212ccb8bd4 fix: Crash on over memory allocation
- Add defer backing flag to gem create ioctl
- Make memory resident before lock

Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2025-01-24 14:01:37 +01:00
Compute-Runtime-Validation ce9202ab9d Revert "feature: enable recoverable pagefault"
This reverts commit 713df81dbf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-23 04:01:31 +01:00
Bartosz Dunajski c2dbdb6797 refactor: move blit post sync data to BlitProperties
Related-To: NEO-13003

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-01-22 18:35:21 +01:00
Mateusz Hoppe 19a0a27862 refactor: adjust unit tests to work with secondary engines
Related-To: NEO-12952, NEO-13789


Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-01-22 13:31:43 +01:00
Kamil Kopryk 47fc1ce34b refactor: use designated initializer for EncodeWalkerArgs
also make EncodeWalkerArgs an aggregate

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-22 11:44:57 +01:00
Zbigniew Zdanowicz 1e89058232 refactor: change data fields for encoder of additional walker fields
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-01-21 16:49:38 +01:00
Bartosz Dunajski 912bd8591a refactor: improve copy commands programming
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-01-21 16:29:59 +01:00
Dominik Dabek 3f646839ca fix: usm reuse cleaning unused allocations
mechanism for freeing allocations saved for reuse that have not been
used in a given time

Related-To: NEO-13425

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-01-21 14:23:19 +01:00
Young Jin Yoon 713df81dbf feature: enable recoverable pagefault
Enabled recoverable pagefault and kmd migration support by
default for bmg and lnl, but disabled kmd migration for XeKMD
in order to disable kmd migration for all platforms using
XeKMD for now.

Related-To: NEO-13116
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-01-21 12:17:04 +01:00
Radoslaw Jablonski be0b2bd06d performance: enable ResolveDependenciesViaPipeControls on PTL Windows
Related-To: NEO-10526

Signed-off-by: Radoslaw Jablonski <radoslaw.jablonski@intel.com>
2025-01-21 11:46:19 +01:00
Fabian Zwoliński 285414e852 fix: cl_cache - add cm header includes to whitelist
This patch adds following includes to the whitelist:
<cm/cm.h>
<cm/cmtl.h>

Related-To: NEO-13641
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-01-21 10:22:03 +01:00
Dominik Dabek 474b91aa36 fix: move device usm reuse max size to device
Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-01-20 18:05:37 +01:00
Chodor, Jaroslaw 5619da6238 feature: Adding hook for applying OpenVino-related AIL
Related-To: NEO-12747

Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2025-01-20 17:38:49 +01:00
Andrzej Koska b1bcfe668c feature: Enable Bindless on PTL L0
Related-To: NEO-13791

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
`
2025-01-20 16:18:48 +01:00
Mateusz Hoppe 850e6c02eb test: allocate sip allocation for all contexts in initSipKernel
- some tests initialize sip kernel but do not free it
- this is causing memory leaks
- as a solution mock sip listener is added that will release allocated
sip kernel

Related-To: NEO-13789

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-01-20 15:46:05 +01:00
Fabian Zwoliński bbaca5d8e2 feature: cl_cache - add support for whitelisted includes
Related-To: NEO-13641
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-01-20 15:07:14 +01:00
Zbigniew Zdanowicz 897c890d03 refactor: add thread group count parameter to implicit scaling functions
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-01-20 13:12:45 +01:00
Jitendra Sharma 8f5a0995e0 fix: Dont directly use gtId as TileId
gtId is not same as tileId. instead use gtIdToTileId
to retrieve tileId based on gtId.

Related-To: NEO-11104
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2025-01-20 10:23:53 +01:00
Mateusz Hoppe 1ce795c265 refactor: fixes in ults
Related-To: NEO-13789

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-01-20 09:57:05 +01:00
Lukasz Jobczyk af0bb7964a performance: Set dispatch all for small TG
Resolves: NEO-11814

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-20 08:49:59 +01:00
Raiyan Latif 12e3204cab fix: Process OpaqueWin32 external semaphore properly
Related-To: NEO-11488

Signed-off-by: Raiyan Latif <raiyan.latif@intel.com>
2025-01-20 00:22:14 +01:00
Compute-Runtime-Validation 71aee41ca3 Revert "feature: enable WMTP on BMG"
This reverts commit d4256475fb.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-19 11:57:40 +01:00
Jack Myers d62122a656 fix: exceptions to TBX faultable types
This commit addresses a bug in the previous implementation where almost all once
writable types, except `gpuTimestampBuffers`, were incorrectly enabled for TBX
faultable checks. The fix ensures that only the subset of once writable
types that are also lockable are considered TBX faultable, using the lockable
check to avoid manual exceptions and re-inventing the wheel.

Changes:

- Updated `isAllocTbxFaultable` method to check if the allocation type is
lockable in addition to being once writable.
- Refactored unit tests to include separate checks for lockable and non-lockable
allocation types.

Performance optimization:

- Removed unnecessary memory data erasure in `handlePageFault` to avoid constant
erase/insert operations, leveraging the O(1) search time of unordered maps.

Related-To: NEO-12319
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-01-17 00:52:49 +01:00
Naklicki, Mateusz 118c5afc47 test: unify scratch pages product helper tests
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2025-01-16 20:19:47 +01:00
Jaroslaw Warchulski 4dd1c80362 refactor: use enum class instead of enum for DeviceHierarchyMode
Related-To: GSD-9560
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-01-16 15:49:44 +01:00
Kamil Kopryk 7d8e08f00b test: adjust code to compile with c++20 2/n
Related-To: NEO-10767
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-16 15:24:25 +01:00
Mateusz Jablonski d4256475fb feature: enable WMTP on BMG
Related-To: NEO-12814
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-01-16 14:56:12 +01:00
Naklicki, Mateusz 218122c46b test: make sure scratch pages are disabled on pvc+
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2025-01-16 14:23:24 +01:00
Naklicki, Mateusz 3e29ca9057 fix: explicitly disable scratch pages on xekmd platforms
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2025-01-16 12:09:27 +01:00
Kamil Kopryk 0278d2e652 test: adjust code to compile with c++20
Related-To: NEO-10767
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-16 12:04:50 +01:00
Kamil Kopryk c5ba3dd575 test: remove not needed volatile
Related-To: NEO-10767
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-16 11:36:45 +01:00
Compute-Runtime-Validation 945c4a3ccc Revert "feature: Enable page faults for xe driver with debugger"
This reverts commit 4300f0bdbe.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-16 11:16:14 +01:00
Jack Myers 0b2ac4d331 feature: Tbx faults for all once writable types
Patch #34223 introduced the TbxPageFaultManager for handling
uploads/downloads of host buffers to the Tbx server, ensuring
host memory is kept consistent between the host and device,
even after multiple alternating writes from the host and gpu.

This patch enable fault handling for all `isAubOnceWritable`
types.

Minor exception for gpuTimestampBuffers as enabling this type
seems to break things in real-world use cases outside of ULTs.

Related-To: NEO-12319
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-01-16 01:43:19 +01:00
Kamil Kopryk 99a7b5a4fb refactor: remove not needed volatile
Related-To: NEO-10767
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-16 00:43:10 +01:00
Krzysztof Sprzaczkowski a17745532c performance: Move preemption allocation init to the first submission
Related-To: NEO-12323
Signed-off-by: Krzysztof Sprzaczkowski <krzysztof.sprzaczkowski@intel.com>
2025-01-15 20:22:50 +01:00
Lukasz Jobczyk 2dd9940f60 Revert "fix: count active modules for enabling per-dispatch private memory"
This reverts commit a483b361f9.

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-01-15 15:03:37 +01:00
Szymon Morek 0b4fe9a0df performance: add staging transfers for cl buffers
Related-To: NEO-13529

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-01-15 12:24:43 +01:00
Vysochyn, Illia 4270e3c356 feature: Add dynamic stack management on Xe3
Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-01-15 10:12:48 +01:00
Vysochyn, Illia ca72dff1ab feature: Add missing pipelined EU thread arbitration on Xe3
Related-To: NEO-13682

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-01-15 08:24:43 +01:00
Jaroslaw Warchulski 6a7bee67e9 refactor: unify device hierarchy mode
Related-To: GSD-9560
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-01-14 21:08:44 +01:00
Maciej Bielski e95c7aac92 fix: set memoryBanks correctly for single memory bank
Resolves: HSD-18040585222

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-01-14 20:38:10 +01:00
Vysochyn, Illia 7903086db3 refactor: Update thread scheduling mode naming
Renames the EU_THREAD_SCHEDULING_MODE_OVERRIDE member of
STATE_COMPUTE_MODE structure to EU_THREAD_SCHEDULING_MODE.

This modification is introduced in order to align with the latest specification.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-01-14 19:00:46 +01:00
Brandon Yates 4300f0bdbe feature: Enable page faults for xe driver with debugger
Related-to: NEO-10134

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-01-14 09:32:53 +01:00
Zbigniew Zdanowicz 575ae7f6f7 fix: get minimal offset size for region barrier
Related-To: NEO-13350

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2025-01-13 22:56:25 +01:00
Jaroslaw Warchulski a180afa2e6 fix: respect affinity mask with COMBINED hierarchy in OCL
Related-To: GSD-9560
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-01-13 15:38:39 +01:00
Compute-Runtime-Validation dc49d09e64 Revert "fix: set memoryBanks correctly for single memory bank"
This reverts commit ec5477e3ee.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-01-11 01:56:37 +01:00
Wenbin Lu a483b361f9 fix: count active modules for enabling per-dispatch private memory
Related-To: NEO-13086

Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2025-01-10 15:03:34 +01:00