Commit Graph

7513 Commits

Author SHA1 Message Date
Mateusz Jablonski
15d0feeda8 fix: improve propagating external functions info to kernel
When relocation points to symbol that is not defined within module mark
it as optional. When symbol is available at dynamic linking time then
info from the function is retrieved but when the symbol is not available
then ignore the dependency.

Any unresolved symbol needed for module linking is already handled
in a separate place.

Related-To: NEO-16243, NEO-16263, NEO-16262, NEO-16268
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-29 15:34:41 +02:00
Maciej Bielski
a440a3e8ea refactor: use Clonable type for pImplicitArgs
Clonable is a helper type which eases proper management of
dynamically-allocated resources. It allows to reduce the amount of
manual handling.

Related-To: NEO-16017
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-09-29 15:34:24 +02:00
Mateusz Hoppe
4b5f206058 feature: add ForceCompatibilityMode debug flag
- allows using device binary without validating device against target
device

Related-To: HSD-13013893426

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-09-29 15:22:06 +02:00
Filip Hazubski
07abb404e0 refactor: Refactor release_helper_common_xe_lpg.inl
Apply common file to release 12.74.

Move isMatrixMultiplyAccumulateSupported
specialization outside of the common file.

Move common specializations from releases: 12.70, 12.71, 12.74
to release_helper_common_xe_lpg.inl file.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2025-09-29 14:44:08 +02:00
Slawomir Milczarek
40ce5eb55e fix: Fix DirectSubmissionController deadlock with try_lock pattern
Related-To: NEO-13325

Replace blocking obtainUniqueOwnership() with tryObtainUniqueOwnership()
in critical paths to prevent deadlock between controller thread holding
directSubmissionsMutex and submission threads holding CSR locks.

Changes:
- Add CommandStreamReceiver::tryObtainUniqueOwnership() method
- Use try_lock in checkNewSubmissions() and context group idle detection
- Skip contended CSRs instead of blocking (conservative approach)
- Add comprehensive unit tests for try_lock functionality

Fixes deadlock scenario where registerDirectSubmission() waits for
directSubmissionsMutex while checkNewSubmissions() holds it and waits
for CSR ownership locks.

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
2025-09-29 11:38:26 +02:00
Mateusz Jablonski
39f10f9c5e refactor: stop using DEFAULT_TEST_FAMILY_NAME
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-29 10:15:13 +02:00
Compute-Runtime-Validation
aaa9342141 Revert "fix: improve parsing relocations in external usage"
This reverts commit 65d883bc9d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-29 10:05:58 +02:00
Mateusz Hoppe
98fcaf4ceb feature: support for context group on Windows
Related-To: NEO-14289


Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-09-28 13:38:53 +02:00
Mateusz Jablonski
65d883bc9d fix: improve parsing relocations in external usage
ignore relocations for symbols with undefined section

Related-To: NEO-16243
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-26 16:33:11 +02:00
Compute-Runtime-Validation
ce65d34a8f Revert "fix: set proper gmm usage type for misaligned user ptr"
This reverts commit a665f27676.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-26 16:24:45 +02:00
Bartosz Dunajski
4df478c513 fix: change default lnl rev id
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-09-25 16:44:04 +02:00
Szymon Morek
d429f0d8a0 fix: respect uncacheable flag for USM host allocations
Related-To: NEO-14360

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-25 16:31:19 +02:00
Bartosz Dunajski
72a5bcbfa1 feature: extend copy offload hint support
Related-To: NEO-14557

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2025-09-25 12:56:40 +02:00
Szymon Morek
a665f27676 fix: set proper gmm usage type for misaligned user ptr
Related-To: NEO-15295

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-25 12:06:43 +02:00
Mateusz Hoppe
cfb3dade30 refactor: replace isContextGroup with contextGroupCount in osContext
Related-To: NEO-14289

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-09-25 11:33:38 +02:00
Kamil Kopryk
8c7fb0dde8 fix: data race in host function data initialization
Make sure hostFunctionInitialized bool is set after actual operations
are done

Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-25 11:29:01 +02:00
Tomasz Biernacik
bc104a7b0d fix: move headers to definitions folder
Related-To: NEO-15440

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2025-09-25 07:35:55 +02:00
Compute-Runtime-Validation
79cdf69efe Revert "fix: disable support for deprecated patchtokens format"
This reverts commit 506d5837df.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-25 03:09:03 +02:00
Maciej Plewka
cf35f8b40e fix: wa for multi ccs execution on bmg
Related-To: NEO-15771
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-09-24 18:15:07 +02:00
Kamil Kopryk
4133827e6f fix: set host function allocation as uncached
The usage of host function allocation is similar to tagBuffer.
Ensure it's uncached and it follows tag buffer's cache policy.
Host function allocation will be readable and writable
by both: cpu and gpu.

Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-24 18:00:50 +02:00
Szymon Morek
804b8f5db6 fix: do not cache tag buffer allocation on GPU
Related-To: NEO-14360

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-24 16:28:35 +02:00
Dominik Dabek
f54e3fda41 feature: adapt usm pool manager
Change behavior to continue allocating usm pools as needed.
Intended to replace singular usm pools.

Related-To: NEO-16084

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-09-24 15:16:10 +02:00
Mateusz Jablonski
506d5837df fix: disable support for deprecated patchtokens format
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-24 12:44:12 +02:00
Mateusz Hoppe
12263b2e7c fix: implicit arg buffer
- refactor validating target device and dcoding Intel GT Notes
- decoded versions are stored in singleDeviceBinary when decoding zebin
- adds parsing Intel GT notes from elf when unpacking binary
- sets indirectAccessBufferMajorVersion with correct value
- fix ImplicitArgsV1 - add simdWidth
- use correct simd size in patchImplicitArgs()

Related-To: NEO-16167, NEO-15211, IGC-12358

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-09-24 09:23:23 +02:00
Fabian Zwoliński
a1c5fa1a13 feature: add pooling of USM global/constant surface
Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-09-23 18:24:18 +02:00
shubham kumar
0b6b0e3954 Revert "feature: Use zesInit on windows always"
This reverts commit 9dadadfa73.

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
2025-09-23 17:18:12 +02:00
Compute-Runtime-Validation
6736378c4d Revert "fix: use condition variables instead of busy waits in worker threads"
This reverts commit 452475a0b9.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-23 17:06:18 +02:00
Chandio, Bibrak Qamar
cf21cbc910 feature: Complete madvise for System Allocator
Related-To: NEO-13715

Provides implmentation of getAtomicAccessAttribute using system
allocator.
Completes the implementation of the madvise feature using the
new IOCTLs in xe_drm header.

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-09-23 16:00:35 +02:00
Mateusz Jablonski
95130b7256 fix: setup hasPrintfCalls in case of printfBuffer arg
in case of AOT kernels compiled with older encoder version
printf calls are present when printf buffer arg is present

Related-To: NEO-15211
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-23 15:23:24 +02:00
Szymon Morek
797807bea8 fix: reduce USM pool size for platforms prior Xe2
Related-To: NEO-16192

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-23 15:06:54 +02:00
Igor Venevtsev
452475a0b9 fix: use condition variables instead of busy waits in worker threads
Resolves: NEO-16085, GSD-11678, HSD-14025819208

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
2025-09-23 14:44:39 +02:00
Mateusz Jablonski
49293fcac6 refactor: store special relocation names as string_view
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-09-23 14:33:40 +02:00
Maciej Bielski
819702ceb8 fix: add various debug-mode asserts
Related-To: NEO-15630

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-09-23 11:33:01 +02:00
Kamil Kopryk
f3ba701a9b refactor: host function data programming
Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-23 11:27:35 +02:00
Kamil Kopryk
5f59b4ca08 feature: add host function allocation
Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-23 11:10:45 +02:00
Compute-Runtime-Validation
c2f3007140 Revert "performance: set proper bcs count for xe2"
This reverts commit 1d2ba692de.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-23 10:21:37 +02:00
Compute-Runtime-Validation
a559c440e2 Revert "fix: Make zesInit path disabled by default on windows"
This reverts commit 27922536ff.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-23 04:34:46 +02:00
Compute-Runtime-Validation
16a6c3ca8a Revert "feature: add host function allocation"
This reverts commit 75b4de70cd.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-23 02:33:15 +02:00
Compute-Runtime-Validation
39a3ea0e0e Revert "fix: remove spir support from xe2 and later"
This reverts commit bcfcd02a03.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-23 02:13:22 +02:00
Kamil Kopryk
75b4de70cd feature: add host function allocation
Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-22 17:55:36 +02:00
shubham kumar
27922536ff fix: Make zesInit path disabled by default on windows
Related-To: NEO-15060

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
2025-09-22 17:02:14 +02:00
Kamil Kopryk
0c2662dc1b performance: dont call getMaxBlitWidth multiple times
getMaxBlitWidth reads global memory - debug manager flags-
and calls virtual functions multiple times,
so it might not be optimized and called multiple times

Related-To: NEO-16132
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-22 15:30:52 +02:00
Grochowski, Stanislaw
bcfcd02a03 fix: remove spir support from xe2 and later
Related-To: NEO-15215

Signed-off-by: Grochowski, Stanislaw <stanislaw.grochowski@intel.com>
2025-09-22 15:08:31 +02:00
Szymon Morek
4d64ec8aaa refactor: add debug flag to not set 2way coherency
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-22 14:48:30 +02:00
Kamil Kopryk
bf0e71f81b refactor: use designated initialization for capabilityTable
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-09-22 13:43:09 +02:00
Brandon Yates
cd862022a8 feature: add debug key for WMTP size
Related-To: HSD-16028003349

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2025-09-22 13:04:48 +02:00
Szymon Morek
5714c3858f fix: increase staging threshold for misaligned ptrs
Related-To: NEO-16118

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-09-22 12:46:58 +02:00
Jaroslaw Warchulski
195bf66a49 refactor: fix typos
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2025-09-22 12:46:41 +02:00
Compute-Runtime-Validation
c08aa1d400 Revert "performance: remove TLB invalidations on BMG/Windows"
This reverts commit 1239858eda.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-20 09:30:33 +02:00
Compute-Runtime-Validation
c7bd6b7b13 Revert "performance: remove TLB invalidations on PTL/Windows"
This reverts commit 9dfa9f1cbb.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-09-20 07:37:00 +02:00