Commit Graph

422 Commits

Author SHA1 Message Date
Mateusz Jablonski
869cc35933 fix: create printf buffer only for kernel with printf calls
Related-To: NEO-15211
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-10-31 15:06:28 +01:00
Michal Mrozek
6cdb73ccca performance: apply stateful programming only if needed
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2025-10-20 17:21:44 +02:00
Compute-Runtime-Validation
8706160236 Revert "fix: return error code when set arg for local argument has size zero"
This reverts commit a503776008.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-10-20 15:18:05 +02:00
Lukasz Jobczyk
7c96076d5e performance: Migrate only svm gpu kernel args
Resolves: NEO-16496

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-10-20 13:01:06 +02:00
Maciej Plewka
a503776008 fix: return error code when set arg for local argument has size zero
Related-To: NEO-16450
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2025-10-17 15:57:25 +02:00
Radoslaw Jablonski
54de14a9dc refactor: apply clang-format's InsertBraces rule
Formats code before InsertBraces rule is enabled.

Signed-off-by: Radoslaw Jablonski <radoslaw.jablonski@intel.com>
2025-10-06 15:32:46 +02:00
Mateusz Jablonski
6c0c229c82 refactor: remove not needed flags to force OCL version support
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-10-03 16:57:08 +02:00
Fabian Zwoliński
a2f60af5c6 fix: change global Var/Const Buffer type to SharedPoolAllocation
This is prep work for the future implementation of pooling these allocations.

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2025-08-19 17:29:34 +02:00
Maciej Bielski
0f57c8ab4c fix: do not forward args in a loop
Related-To: NEO-15630

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2025-08-18 13:13:12 +02:00
Mateusz Hoppe
757f4774b6 fix: fix unit tests relying on kernels
Related-To: NEO-15743

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-08-05 11:15:08 +02:00
Mateusz Hoppe
b7a73653a2 fix: set sync buffer ptr in implicit args
Related-To: NEO-15737

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-08-04 14:22:46 +02:00
Mateusz Jablonski
dd568b35b9 refactor: remove not needed code related to vme
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-07-29 10:00:23 +02:00
Mateusz Hoppe
be483491bf feature: extract indirect access buffer major version from ELF's notes
- use version from ELF to create correct layout of implcit args
Related-To: NEO-15574

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-07-25 14:50:49 +02:00
Mateusz Jablonski
066447e5eb refactor: remove not needed code
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-07-24 16:33:29 +02:00
Szymon Morek
bbcca97682 fix: flush cache after accessing img from buffer
Related-To: NEO-15391

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-07-23 19:17:47 +02:00
Compute-Runtime-Validation
cf89342bf8 Revert "fix: flush cache after accessing img from buffer"
This reverts commit b90b77e4e3.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-07-23 05:25:55 +02:00
Naklicki, Mateusz
dade66307e refactor: cleanup header includes 4/n
cleanup of opencl/source directory

Related-To: NEO-15383
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2025-07-22 19:36:34 +02:00
Szymon Morek
b90b77e4e3 fix: flush cache after accessing img from buffer
Related-To: NEO-15391

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2025-07-22 16:55:04 +02:00
Mateusz Hoppe
b17ed79618 fix: update implicitArgs versions
- fix layout of implicit args
- add enqueued local size and sync buffer ptr

Related-To: NEO-15160

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-07-22 15:12:55 +02:00
Mateusz Jablonski
5e43ee905d refactor: remove not needed logic related to vme
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-07-11 17:02:48 +02:00
Mateusz Jablonski
8b6aaceab4 refactor: remove not needed code related to cl accelerator
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-07-10 18:08:32 +02:00
Mateusz Jablonski
0c066b4266 refactor: remove C-style casts 1/n
Related-To: NEO-15174
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-06-17 17:50:56 +02:00
Mateusz Jablonski
0a325e09be fix: correct initialization of Kernel::isBuiltIn
value is used in Kernel::initialize but was set after initialize call

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-06-11 18:29:06 +02:00
Compute-Runtime-Validation
9be9ec22ac Revert "fix: setup printf surface when implicit args are programmed"
This reverts commit ca3079f263.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-06-11 14:09:56 +02:00
Mateusz Jablonski
ca3079f263 fix: setup printf surface when implicit args are programmed
even if main kernel is not using printf

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-05-30 19:01:12 +02:00
Katarzyna Cencelewska
828d6bafa7 fix: return proper value for zeKernelSuggestGroupSize
Resolves: HSD-18042274687
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2025-05-30 16:35:21 +02:00
Compute-Runtime-Validation
a188c29e8c Revert "fix: setup printf surface when implicit args are programmed"
This reverts commit e3be9eaea7.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-05-30 15:24:29 +02:00
Katarzyna Cencelewska
e357e7e404 fix: correct limitation for num threads per thread group
taking into account the max work group limit
when simd1 don't use the same limitation as for simd32

Resolves: NEO-14922
Related-To: NEO-11881
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2025-05-29 16:34:40 +02:00
Mateusz Jablonski
e3be9eaea7 fix: setup printf surface when implicit args are programmed
even if main kernel is not using printf

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-05-29 11:49:54 +02:00
Compute-Runtime-Validation
593c9e76f2 Revert "fix: correct limitation for num threads per thread group"
This reverts commit 6ad4ad41b1.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-05-23 02:51:17 +02:00
Kamil Kopryk
caf1781e73 fix: add L3 flush after post sync for zero copy mem objects
Related-To: NEO-13163
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-05-22 10:23:26 +02:00
Katarzyna Cencelewska
6ad4ad41b1 fix: correct limitation for num threads per thread group
taking into account the max work group limit

Resolves: NEO-14922
Related-To: NEO-11881
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2025-05-22 00:06:21 +02:00
Lukasz Jobczyk
62619f9525 refactor: remove unused kernel tunning
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2025-05-08 14:18:21 +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
Mateusz Hoppe
a86105814d fix: default initialize allocated memory when memory is overwritten
Related-To: NEO-5093

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2025-03-11 15:32:33 +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
Compute-Runtime-Validation
5e4238ddb1 Revert "fix: respect arg size when setting kernel arg in OCL path"
This reverts commit c10ff0f3c6.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2025-02-27 04:42:22 +01:00
Mateusz Jablonski
c10ff0f3c6 fix: respect arg size when setting kernel arg in OCL path
Fixes: #777

https://github.com/intel/compute-runtime/issues/777
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-02-26 14:04:09 +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
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
Filip Hazubski
6b2b42972a fix: Add asserts to ensure NonCopyable and NonMovable 1/n
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2025-02-18 09:41:20 +01:00
Kamil Kopryk
6926582915 feature: use bindless samplers in heapless ocl
Related-To: NEO-12741
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-22 11:49:48 +01:00
Kamil Kopryk
d263fda1ad feature: patch 64bit addresses for bindless images in heapless OCL
Related-To: NEO-12741
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-01-16 15:24:02 +01:00
Damian Tomczak
b859a3b35b refactor: remove usesBindfulAddressingForBuffers function
Related-to: NEO-12737

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
2025-01-14 10:45:04 +01:00
Zbigniew Zdanowicz
56b15f17f7 refactor: unify further calculation to get max work group count
- move available device calculcation into common helper
- change interface to have code available where no descriptor is available
- expand unit test for implementation of new inteface

Related-To: NEO-13350

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-11-29 17:51:05 +01:00
Wojciech Konior
6b40f9bc5a refactor: engineInstancedType removed
Related-To: NEO-12594

Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
2024-10-09 16:30:48 +02:00
Michal Mrozek
363aca782f refactor: remove not needed code.
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-09-19 18:50:16 +02:00
Mateusz Jablonski
16458ca0ac refactor: remove not used image transforming logic
image transformer logic was used on gen9 and gen11

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-09-17 16:19:48 +02:00
Mateusz Jablonski
5912b43841 refactor: remove dead code
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-09-17 13:41:50 +02:00
Bartosz Dunajski
4f1262645b refactor: pass extra walker params
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-09-10 15:30:03 +02:00