intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-30 01:35:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
17,532 Commits 42 Branches 655 Tags
ec66d9e82d84f9abd70e697b627a46ae398bde7f
Commit Graph

7081 Commits

Author SHA1 Message Date
Slawomir Milczarek
ec66d9e82d feature: Add getter to query drm about device node 
Related-To: NEO-11817

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-10-14 17:58:24 +02:00
Bartosz Dunajski
f430279d62 fix: change doorbell type 
Related-To: NEO-12870

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-10-14 14:58:11 +02:00
Szymon Morek
7f2b806413 fix: Override timestamp width from KMD 
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2024-10-14 13:38:33 +02:00
Oskar Hubert Weber
8527779778 fix: running Blender with SYSMAN enabled on Linux 
Related-To: NEO-11618

Signed-off-by: Oskar Hubert Weber <oskar.hubert.weber@intel.com>
 2024-10-14 12:36:08 +02:00
Bartosz Dunajski
5adfaa0380 test: improve drm mocking 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-10-14 11:49:04 +02:00
Wojciech Konior
8a6626da23 refactor: two engineInstanced-methods removed 
Related-To: NEO-12594

Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
 2024-10-11 18:34:06 +02:00
Compute-Runtime-Validation
5899e926fa Revert "fix: reduce preemption surface size in aub tests" 
This reverts commit 8daae7e8ae.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-11 18:17:29 +02:00
Damian Tomczak
0c8af82d1b fix: stateless suffix for stateless kernels 
Resolves: NEO-12847

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
 2024-10-11 17:40:10 +02:00
Weronika Kapusta
8cb630b29a test: neo ULT should build with optimizations disabled 
Related-To: NEO-8116
Signed-off-by: Weronika Kapusta <weronika.kapusta@intel.com>
 2024-10-11 17:26:06 +02:00
Compute-Runtime-Validation
a55a846284 Revert "fix: update slm size based on gt system info in wddm path" 
This reverts commit d433fd585a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-11 03:43:37 +02:00
Compute-Runtime-Validation
94d662a9a9 Revert "fix: update slm size based on gt system info in drm path" 
This reverts commit 6a8a5bca3b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-11 03:20:29 +02:00
Zbigniew Zdanowicz
227ce579fe fix: align total slm size for preferred size 
Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-10-10 20:44:19 +02:00
Zbigniew Zdanowicz
f4746a5b07 fix: remove not needed limitations for preferred slm 
Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-10-10 19:40:54 +02:00
Kamil Kopryk
50221dd572 feature: add heapless builtins with images compilation 
Related-To: NEO-12743
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2024-10-10 19:21:37 +02:00
Mateusz Jablonski
8daae7e8ae fix: reduce preemption surface size in aub tests 
Related-To: NEO-12648

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-10 15:36:49 +02:00
Artur Harasimiuk
1260023efa fix: add missing NOLINT to forward declarations 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2024-10-10 13:46:14 +02:00
Artur Harasimiuk
00aedcaed4 refactor: add NOLINT for pending problems 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2024-10-10 11:46:35 +02:00
Mateusz Jablonski
d433fd585a fix: update slm size based on gt system info in wddm path 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-10 11:29:19 +02:00
Mateusz Jablonski
6a8a5bca3b fix: update slm size based on gt system info in drm path 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-10 11:25:24 +02:00
Mateusz Jablonski
3c06b316e6 refactor: remove legacy code 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-10 09:54:22 +02:00
Kamil Kopryk
a333b048fe refactor: remove legacy code vme 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2024-10-10 09:32:00 +02:00
Szymon Morek
8c5be5c55a performance: Enable direct submission on DG2 Windows 
Related-To: NEO-12892

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2024-10-09 17:57:32 +02:00
Mateusz Jablonski
0168067c9c refactor: define dg2 g10 device ids in separate file 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-09 17:45:05 +02:00
Zbigniew Zdanowicz
ac6472b105 fix: limit slm size based on hw informations 
- add override default values method

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-10-09 17:34:56 +02:00
Mateusz Jablonski
19e2dd0846 refactor: remove legacy code 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-09 17:25:08 +02:00
Mateusz Hoppe
31265edfee fix: program RenderTargetCacheFlush in PC prior to PIPELINE_SELECT 
- fix code by removing csStallOnly that skipped seeting RTCF flag

Related-To: NEO-9194

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-10-09 16:59:43 +02:00
Kamil Kopryk
e690217227 refactor: remove not needed slm alignment 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2024-10-09 16:45:19 +02:00
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
Bartosz Dunajski
834f00d48b fix: dont query timestamp if debug flag is disabled 
Related-To: NEO-12907

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-10-09 16:08:04 +02:00
Mateusz Jablonski
8fbe873e1b build: correct setting for i915/xe prelim setting in package scripts 
rename i915 flag to uppercase, for consistency
disable i915 / xe prelim by default in package scripts

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-09 15:55:59 +02:00
Jitendra Sharma
b816f6e127 test: check space also in timestamp logs of debugger print 
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
 2024-10-09 15:03:01 +02:00
Andrzej Koska
dad53a13c3 fix: set stackSizePerRay appropriately for release 
Related-to: NEO-12816

Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
 2024-10-09 11:33:42 +02:00
Mateusz Hoppe
5ae2552b4b fix: track shifted contextIds in bitset in bindlessHeapsHelper 
- bitset is 64 bit in size, context ids may go beyond that limit
when multiple devices are available
- this change subtracts contextId of first context for a given root
device - tracked state dirty contexts ids are now zero-based

Resolves: GSD-10025

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-10-09 10:32:29 +02:00
Zbigniew Zdanowicz
46a63d3e0e refactor: unify programming of preferred slm size 5/n 
- remove xe2 hpg encode preferred slm size
- add xe2 release helper preferred slm array
- add dedicated method to calculate thread count per sub slice

Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-10-09 09:39:35 +02:00
Compute-Runtime-Validation
946e421f77 Revert "performance: Enable direct submission on DG2 Windows" 
This reverts commit b520c64775.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-09 08:18:06 +02:00
Jitendra Sharma
a111c18fb1 refactor: Add timestamp to all debugger log 
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
 2024-10-08 18:12:20 +02:00
Kamil Kopryk
91f1f58a47 refactor: remove legacy code 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2024-10-08 15:24:26 +02:00
Mateusz Jablonski
6f909113f9 fix: abort when programming mid thread preemption for pre-Xe2 platforms 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-08 15:10:20 +02:00
Mateusz Jablonski
1f801f412f fix: don't program mid thread preemption for pre-Xe2 platforms 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-08 14:16:14 +02:00
Mateusz Jablonski
552930a75f fix: don't setup preemption surface when debugger is active 
Related-To: NEO-12878
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-10-08 13:58:11 +02:00
Lukasz Jobczyk
5b2f2f3d83 performance: Ensure hostptrs removed before creating new one 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-10-08 13:04:56 +02:00
Dominik Dabek
9159e2acd4 fix: limit max size for allocation reuse 
Limit max size for allocation reuse mechanism to 256MB.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-10-08 11:52:47 +02:00
Compute-Runtime-Validation
60afb83b3b Revert "performance: Ensure hostptrs removed before creating new one" 
This reverts commit a890ed5648.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-08 07:45:55 +02:00
Compute-Runtime-Validation
4449842c7b Revert "refactor: unify programming of preferred slm size 5/n" 
This reverts commit 9fc4663383.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-07 22:26:37 +02:00
Zbigniew Zdanowicz
9fc4663383 refactor: unify programming of preferred slm size 5/n 
- remove xe2 hpg encode preferred slm size
- add xe2 release helper preferred slm array

Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-10-07 18:03:08 +02:00
Matias Cabral
6ddb550e05 feature: improve metrics debug messages 
Resolves: NEO-12640

Signed-off-by: Matias Cabral <matias.a.cabral@intel.com>
 2024-10-07 17:58:41 +02:00
Szymon Morek
068ceee8bd performance: improve iterating over residency allocations 
Related-To: NEO-12698,NEO-12746,NEO-12729

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2024-10-07 16:12:22 +02:00
Katarzyna Cencelewska
42ca656edb fix: change logic to calculate available thread count 
don't use magic number, value depend on grf size

Related-To: HSD-18039369782
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2024-10-07 15:46:33 +02:00
Szymon Morek
b520c64775 performance: Enable direct submission on DG2 Windows 
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2024-10-07 15:38:20 +02:00
Dominik Dabek
6d6c4267b3 performance: enable indirect detection 
Platforms other than PVC require detection version >= 4
Vector compiler kernels require >= 6

Related-To: NEO-12491

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-10-07 14:38:22 +02:00