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
18,177 Commits 42 Branches 655 Tags
bf4d4e71c3560718df42df250baa9b230604fd1b
Commit Graph

4953 Commits

Author SHA1 Message Date
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
Zbigniew Zdanowicz
a27c9200d3 test: add new test matcher 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2025-01-10 18:23:05 +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
Mateusz Jablonski
112abeeeef fix: don't adjust programmed per thread scratch size 
when adjusting scratch space size then adjust only allocation size

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-10 11:35:50 +01:00
Maciej Bielski
ec5477e3ee fix: set memoryBanks correctly for single memory bank 
Resolves: HSD-18040585222

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-01-10 10:01:33 +01:00
Mateusz Jablonski
a3b6c1fa6d fix: correct thread/eu ratio for scratch to Xe2 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-09 22:42:36 +01:00
Szymon Morek
f3c9362fc5 fix: check for gpu hang during wait for ring completion 
Related-To: NEO-13490

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-01-09 18:44:25 +01:00
Compute-Runtime-Validation
9e5a52f689 Revert "fix: correct thread/eu ratio for scratch to Xe2" 
This reverts commit b192893738.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-09 11:06:26 +01:00
Jack Myers
7f9fadc314 fix: regression caused by tbx fault mngr 
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.

Recursive locking of mutex caused deadlock.

To fix, separate tbx fault data from base
cpu fault data, allowing separate mutexes
for each, eliminating recursive locks on
the same mutex.

By separating, we also help ensure that tbx-related
changes don't affect the original cpu fault manager code
paths.

As an added safe guard preventing critical regressions
and avoiding another auto-revert, the tbx fault manager
is hidden behind a new debug flag which is disabled by default.

Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
 2025-01-09 07:48:53 +01:00
Compute-Runtime-Validation
22cebedcd1 Revert "refactor: Update thread scheduling mode naming" 
This reverts commit d50beb5df4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-09 05:03:36 +01:00
Vysochyn, Illia
d50beb5df4 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>
 2025-01-08 16:52:45 +01:00
Vysochyn, Illia
a2aa645404 refactor: Update MI_MEM_FENCE 
Refactors the MI_MEM_FENCE to align with the latest specification.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
 2025-01-08 16:46:58 +01:00
Mateusz Jablonski
b192893738 fix: correct thread/eu ratio for scratch to Xe2 
Xe2 platforms don't need overallocation there

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-08 15:34:50 +01:00
Szymon Morek
2815d4167d fix: don't use staging for map allocations 
Related-To: NEO-13572

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-01-07 13:30:11 +01:00
Dominik Dabek
8d4721d613 performance: update igc indirect detection version 
Update required indirect detection versions to 9 for pvc vector compiler
and non-pvc non-vector compiler.

Related-To: NEO-12491

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2025-01-07 13:25:12 +01:00
Brandon Yates
4111821c86 feature: place device bitfield in debugger metadata 
Device bitfield is used to track tile instanced isa segments
by dmgUMD

Related-To: NEO-11104

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
 2025-01-07 11:56:25 +01:00
Mateusz Jablonski
bb1a125f0c feature: add support for Panther Lake platform 
Related-To: NEO-12803

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-07 11:39:56 +01:00
Filip Hazubski
3997d2a6b3 Revert "feature: Append recorded commandlist into immediate (8/N)" 
This reverts commit acfeffe274.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2025-01-03 15:50:52 +01:00
Mateusz Jablonski
0232ae60f2 test: remove redundant test for WMTP on LNL 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-03 12:59:59 +01:00
Mateusz Jablonski
c867a5ed5d refactor: remove redundant flag levelZeroSupported 
all platforms are supported by L0

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-03 11:28:11 +01:00
Marcel Skierkowski
91a2b9e66b test: use virtualFileSystem in Cpuinfo tests 
Related-To: NEO-7006
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
 2025-01-03 10:31:04 +01:00
Mateusz Jablonski
5eece6d578 feature: add enableVariableRegisterSizeAllocation to StateComputeModeProperties 
Related-To: NEO-12803

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-02 17:15:18 +01:00
Mateusz Jablonski
165c294590 refactor: extract methods to setup SCM state per context 
per context properties are now set explicitly

Related-To: NEO-12803, NEO-13632
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2025-01-02 15:19:39 +01:00
Compute-Runtime-Validation
ed24c07227 Revert "feature: add enableVariableRegisterSizeAllocation to StateComputeMode... 
This reverts commit 9ccecb5a35.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-01 02:35:32 +01:00
Kulkarni, Ashwin Kumar
badbecb126 feature: adds support for 3 channel (2/N) 
Allows user to create L0 images with 3 channel

Related-To: NEO-12887

Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
 2024-12-31 20:02:13 +01:00
Vysochyn, Illia
f198507875 refactor: Remove 3DSTATE_BTD_BODY structure 
Removes 3DSTATE_BTD_BODY as redundant structure.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
 2024-12-31 16:27:29 +01:00
Mateusz Jablonski
9ccecb5a35 feature: add enableVariableRegisterSizeAllocation to StateComputeModeProperties 
Related-To: NEO-12803

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-12-31 12:28:19 +01:00
Mateusz Jablonski
aa7f06ca58 test: remove isUsingNonDefaultIoctls trait, use gen matcher instead 
Related-To: NEO-12803
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-12-31 11:45:48 +01:00
Mateusz Hoppe
c08c9b7f86 refactor: change test to HWTEST 
- move Heapful matcher to test macros
- check alignment in patchWithRequiredSize


Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-12-31 10:37:37 +01:00
Compute-Runtime-Validation
b83db7ee32 Revert "feature: disable page fault handler on migration" 
This reverts commit a258c9b010.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-12-31 03:57:02 +01:00
Mateusz Hoppe
44264b2b5c fix: assume stateless access to buffers 
- if buffers are not bindful or bindless, set stateless addressing mode
for buffers

Related-To: NEO-12800

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-12-30 12:22:23 +01:00
Young Jin Yoon
a258c9b010 feature: disable page fault handler on migration 
Disabled RegisterPageFaultHandlerOnMigration by default

Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
 2024-12-30 09:42:52 +01:00
Lukasz Jobczyk
83ebbb01d3 performance: Add flag to mitigate host visible signal in CB events 
Related-To: NEO-13441

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-12-24 12:35:55 +01:00
Vysochyn, Illia
c05ac6ff70 refactor: Rename enumerators to common naming 
Renames SHARED_LOCAL_MEMORY_SIZE_ENCODES and PREFERRED_SLM_ALLOCATION_SIZE
enumerators' members to follow the specification.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
 2024-12-24 12:10:26 +01:00
Chodor, Jaroslaw
54a2006759 test: refactor - remove NDEBUG from regex WA 
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
 2024-12-24 11:12:31 +01:00
Compute-Runtime-Validation
95b3d16d76 Revert "fix: add scratch page support with xekmd" 
This reverts commit dec695f405.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-12-23 19:05:29 +01:00
Lukasz Jobczyk
ed813def70 performance: Always allocate by KMD on Xe2 
Related-To: NEO-13441

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-12-23 17:56:35 +01:00
Vysochyn, Illia
83b7143485 refactor: Standardize DESTINATION_SURFACE_TYPE 
Standardizes DESTINATION_SURFACE_TYPE to align with the latest
specification.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
 2024-12-23 16:39:25 +01:00
Mateusz Hoppe
a0cefc5577 test: refactor EncodeDispatchKernelTest 
- modify test matcher

Related-To: NEO-12800


Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-12-23 14:59:20 +01:00
Vysochyn, Illia
2951f8a411 refactor: Update CFE_STATE 
Refactors the CFE_STATE to align with the latest specification.

Related-To: NEO-13147

Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
 2024-12-23 14:31:20 +01:00
Szymon Morek
1135c1033e fix: set staging buffer writeable for aub and tbx 
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2024-12-23 13:35:01 +01:00
Maciej Plewka
54e62da553 fix: use release helper to get ftrXe2Compression value 
Related-To: NEO-13381, NEO-13526
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2024-12-23 13:28:06 +01:00
Oskar Hubert Weber
1c1b2db9a9 fix: allowing neo ULT build with optimization enabled 5/n 
- fix mismatched-new-delete warnings
- fix initialization warnings
- fix attempt to free a non-heap object warnings

Related-To: NEO-8116

Signed-off-by: Oskar Hubert Weber <oskar.hubert.weber@intel.com>
 2024-12-23 13:07:55 +01:00
Naklicki, Mateusz
dec695f405 fix: add scratch page support with xekmd 
Also explicitly disable it by default.


Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
 2024-12-23 11:00:12 +01:00
Aravind Gopalakrishnan
acfeffe274 feature: Append recorded commandlist into immediate (8/N) 
Add primary dispatch capability for immediate command list

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
 2024-12-20 18:52:33 +01:00
Dominik Dabek
5b429dd415 fix: usm reuse, check for in use before returning 
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-12-20 18:24:18 +01:00
Chodor, Jaroslaw
dd3d5c6460 feature: Add logic for reading loaded library's version 
getLoadedLibVersion is intended for reading version of a library that was
already loaded into the process prior to this call (i.e. new instance of
the library willnot be loaded).
Note: Currently, only windows version of this functionality is implemented.
Related-To: GSD-10248

Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
 2024-12-20 17:29:19 +01:00
Maciej Plewka
98aedc5b35 fix: disable xe2 compression through release helper 
Related-To: NEO-13381, NEO-13526
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2024-12-20 14:09:59 +01:00