intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-31 12:11:31 +08:00
Code Issues Packages Projects Releases Wiki Activity
21,523 Commits 42 Branches 655 Tags
ed6565cbbb5b56164c37c0eb4d065d89e1e16c75
Commit Graph

953 Commits

Author SHA1 Message Date
Jaroslaw Warchulski
33e25b260e refactor: do not include gmm_lib.h in gmm.h 
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
 2025-12-08 12:52:02 +01:00
Mateusz Jablonski
4f5d1f1175 feature: add stream properties for xe3p specific fields 
Related-To: NEO-16649

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-12-08 09:23:23 +01:00
Maciej Bielski
d59df10683 feature: enable redirecting of PRINT_STRING() outputs 
Related-To: NEO-14742
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-12-04 16:55:55 +01:00
Compute-Runtime-Validation
936de45c71 Revert "feature: enable defer backing by default" 
This reverts commit 94a857b975.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-12-03 01:52:36 +01:00
Bellekallu Rajkiran
94a857b975 feature: enable defer backing by default 
Related-To: NEO-13403

Signed-off-by: Narendra Bagria <narendra.bagria@intel.com>
Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
 2025-12-02 04:46:23 +01:00
Aleksandra Nizio
1e2b0228a0 refactor: Moving MakeAllBuffersResident flag from release var to debug var 
Resolves: NEO-16215
Signed-off-by: Aleksandra Nizio <aleksandra.nizio@intel.com>
 2025-12-01 11:22:06 +01:00
Maciej Bielski
147bd894ec refactor: use PRINT_STRING macro for most diagnostics 
Related-To: NEO-14742
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-11-28 13:28:29 +01:00
Michal Mrozek
4fd0452e26 refactor: remove not needed code 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2025-11-27 17:13:44 +01:00
Filip Hazubski
2fbb12b545 feature: Add debug toggle OverrideSamplerArbitrationControl 
Resolves: NEO-16608

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2025-11-27 09:53:06 +01:00
Michal Mrozek
af43bd6236 performance: add debug flag to override node ordinal for ccs 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2025-11-26 13:04:57 +01:00
Szymon Morek
861ea7200d performance: increase heap size to 4MB on OCL 
Related-To: NEO-16348

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-11-25 09:58:16 +01:00
Kamil Kopryk
56b30d1803 feature: redesign host function workers 
Each host function gets its unique ID within a CSR,
uses 1 mi store to write ID - to signal that host function is ready,
and 1 mi semaphore wait will wait for the ID to be cleared,
Use 0th bit from ID as pending/completed flag,
host function ID is incremented by 2, and starts with 1.
So each ID will always have 0bit set.
This is a must have since semaphore wait can wait for 4 bytes only.

Adjust command buffer programming and patching logic to IDs.

Add hostFunction callable class - using invoke method,
which stores required information about callback.

Add host function streamer - stores all host function data
for a given CSR.
All user provided host functions are stored in unordered map,
where key is host function ID.

Add host function scheduler, and a thread pool - under debug flag
Single threaded scheduler loops over all registered host function streamers,
dispatch ready to execute host functions to thread pool.

Allow for out of order host functions execution for OOQ - under debug flag,
each host function has bool isInOrder flag which indicates if it can be
executed Out Of Order - in this mode, ID tag will be cleared immediately,
so semaphore wait will unblock before the host function execution.

Remove Host Function worker CV and atomics based implementation.

Rename classes

Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2025-11-25 08:05:41 +01:00
Fabian Zwoliński
1b9b78ac16 feature: implement ISA allocation pooling in OpenCL 
Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2025-11-18 18:02:51 +01:00
Mateusz Jablonski
29dcc17ed9 feature: add support for release helpers 35.11 (CRI) 
Related-To: NEO-16649

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-11-18 10:05:27 +01:00
Mateusz Hoppe
91fe2ec380 refactor: remove not needed debug flag AppendAubStreamContextFlags 
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2025-11-12 16:06:09 +01:00
Falkowski, John
cfa007e551 feature: Set shared system USM madvise preferred location as prefetch region 
Resolves: NEO-16482

Signed-off-by: Falkowski, John <john.falkowski@intel.com>
 2025-11-11 04:04:57 +01:00
Michal Mrozek
9366f4339a refactor: remove not needed code 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2025-11-07 12:13:24 +01:00
Compute-Runtime-Validation
7b1c8e10ba Revert "feature: Set shared system USM madvise preferred location as prefetch... 
This reverts commit 6b63304673.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-11-07 11:26:40 +01:00
Jaroslaw Warchulski
dd7eb96082 fix: enable state cache invalidation WA by default on xe3 
Related-To: NEO-16281, NEO-16405

Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
 2025-11-06 10:03:50 +01:00
John Falkowski
6b63304673 feature: Set shared system USM madvise preferred location as prefetch region 
Resolves: NEO-16482

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2025-11-05 15:37:08 +01:00
Dominik Dabek
0f5381456d feature: l0, flag to lazy init usm pools 
If enabled, usm pools will allocated on first usm allocation.

Use by default in ULTs to avoid not needed allocations of pool storage.

Related-To: NEO-16084

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2025-11-05 14:56:01 +01:00
Jaroslaw Warchulski
0012328c9a feature: add debug flag to control state cache invalidation WA 
Also, temporarily disable this WA.

Related-To: NEO-16281, NEO-16405
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
 2025-11-04 15:58:09 +01:00
Katarzyna Cencelewska
5cf3eeb615 fix: use lowest priority level as default for primary context 
calculate the lowest and highest software priority in one place

Related-To: HSD-18043767497
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2025-11-04 11:42:35 +01:00
Kamil Kopryk
f84a5fbee9 feature: add host functions workers 
* add common host function worker interface
* add worker as a single thread per csr with 3 modes
* add logic for waiting on internal tag, check gpu hang
* if tag is in pending state, read callback data, run callback
and signal completion
* threads will exit the work loop once stop request
is called in finish
* add multi thread unit tests

Related-To: NEO-14577
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2025-11-03 12:11:17 +01:00
Szymon Morek
037756460f refactor: remove unused code 
Related-To: NEO-14360

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-11-03 11:15:12 +01:00
Compute-Runtime-Validation
56ce056ee2 Revert "feature: enable defer backing by default" 
This reverts commit 19bef4f891.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-10-30 03:02:30 +01:00
John Falkowski
9590a42c10 feature: Enable madvise autoreset by default for shared system USM 
Related-To: NEO-16531

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2025-10-29 17:19:27 +01:00
Narendra Bagria
19bef4f891 feature: enable defer backing by default 
Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
Signed-off-by: Narendra Bagria <narendra.bagria@intel.com>
 2025-10-27 16:49:02 +01:00
Dominik Dabek
ff48090c11 feature: usm pool residency tracking 
Initially under debug flag.
Track residency of pool and chunks.
If pool is already resident or already evicted, we can skip memory
operation on chunk from pool.

Return error on using not allocated chunk in pool.

Related-To: NEO-16303

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2025-10-24 13:14:37 +02:00
Lukasz Jobczyk
0bfcd9783c performance: Add flag to aub dump only command stream 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-10-23 11:50:49 +02:00
Zbigniew Zdanowicz
f2c38ee012 feature: add debug flag to control graph patch preamble 
Related-To: NEO-16434

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2025-10-21 13:36:16 +02:00
Michal Mrozek
f63ace10bf refactor: remove not needed code 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2025-10-17 08:05:41 +02:00
Bartosz Dunajski
8c9bff4f4e refactor: new logic to limit per queue split size 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2025-10-13 08:12:51 +02:00
Compute-Runtime-Validation
2eb8928ec5 Revert "performance: increase heap size to 4MB" 
This reverts commit f41bb3517a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-10-10 22:23:23 +02:00
Bartosz Dunajski
0597f064e5 refactor: bcs split class structure 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2025-10-09 14:19:51 +02:00
Szymon Morek
f41bb3517a performance: increase heap size to 4MB 
Related-To: NEO-16348

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-10-09 13:03:53 +02:00
Mateusz Jablonski
298fcb868b fix: Set init zero flag for preemption buffer 
Related-To: HSD-16028003349
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-10-08 15:57:56 +02:00
Kamil Kopryk
0eeb1899d4 refactor: correct debug flag description 
Specify debug flag size unit

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2025-10-07 11:59:13 +02:00
Mateusz Hoppe
f411dc2e65 fix: debug key for using temp memory when writing to aub 
Related-To: NEO-16276

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2025-10-07 09:43:02 +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
Katarzyna Cencelewska
0f866e24e6 fix: enable setting timestamp via submission on tbx mode 
Resolves: NEO-16293
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2025-10-03 08:43:18 +02:00
Kamil Kopryk
2192e0b90e refactor: improve compilation time 
Limit chrono includes,
chrono is very slow to compile

Related-To: NEO-15390
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2025-10-01 13:50:29 +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
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
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
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
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
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
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