intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-21 09:14:47 +08:00
Code Issues Packages Projects Releases Wiki Activity
15,873 Commits 42 Branches 655 Tags
4aa7c6c99ea844fd366b35c54f508dd02bb2076c
Commit Graph

1860 Commits

Author SHA1 Message Date
Bartosz Dunajski
53f436095e refactor: pass hwInfo to getSupportedLocalDispatchSizes 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-04-25 15:20:03 +02:00
Lukasz Jobczyk
36ddfaaf4d fix: Fix front end programming for cooperative dispatch 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-04-25 12:55:46 +02:00
Mateusz Jablonski
25bed07989 fix: correct calculating system shared memory size 
do not exceed system memory region size when region is available

Related-To: HSD-18038050680
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-24 18:55:23 +02:00
Lukasz Jobczyk
4be3230051 fix: Use current fence values when create fence for ULLS 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-04-24 18:19:58 +02:00
Mateusz Jablonski
22bedda081 fix: handle GPU error in xe path 
get DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN property and signal gpuHang based on this

Related-To: HSD-18038050680
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-24 10:29:39 +02:00
Maciej Bielski
8bef74133f feature: add setupIpVersion for Xe 
Related-To: NEO-10773

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2024-04-23 16:07:23 +02:00
Brandon Yates
11e13ee04d fix: Wait indefinitely for vmbind fence when debugging 
Related-to: NEO-9672

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
 2024-04-22 09:23:43 +02:00
Mateusz Jablonski
5d5f3b8d3d refactor: remove not needed adjustment of timeout in xe path 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-19 15:40:03 +02:00
Maciej Plewka
71286be6ad fix: Pass umd type info to kmd 
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2024-04-19 12:40:28 +02:00
Igor Venevtsev
6425afc548 fix: properly set ReadOnly flag for D3DKMTCreateAllocation2 
This is an OS behavior to have failed an allocation with a
const buffer backing storage (PAGE_READONLY attribute set)
ReadOnly flag allows to create allocation with read-only
backing storage

Related-To: NEO-9664, HSD-16021966023

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
 2024-04-19 11:32:46 +02:00
Maciej Bielski
07ac0809db fix: put VRAM regions in the reporting order on xe 
Related-To: NEO-11165
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2024-04-18 22:06:01 +02:00
Mateusz Jablonski
704ea18ce3 refactor: remove not needed code 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-18 15:38:22 +02:00
Compute-Runtime-Validation
da9df9f0e7 Revert "performance: Reuse GPU timestamp instead of KMD escape" 
This reverts commit 9ca2091725.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-04-18 10:25:15 +02:00
Mateusz Hoppe
34544c35dc refactor: add const and virtual to context methods 
Related-To: NEO-10920

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-04-17 19:20:03 +02:00
Mateusz Jablonski
aa26694bad refactor: remove not needed function 
Related-To: NEO-11160

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-17 10:52:14 +02:00
Morek, Szymon
9ca2091725 performance: Reuse GPU timestamp instead of KMD escape 
Resolves: NEO-10615

Signed-off-by: Morek, Szymon <szymon.morek@intel.com>
 2024-04-17 09:39:29 +02:00
Mateusz Jablonski
15d7a31148 refactor: add separate function to create IoctlHelperXe 
unify ioctl helper xe logic

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-17 08:52:30 +02:00
Jaroslaw Warchulski
ca70bb99b2 refactor: reduce the number of DrmAllocation constructors 
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
 2024-04-16 15:37:09 +02:00
Maciej Bielski
c2b4699cb6 feature: Add mask of tiles to each memory region in Xe 
* Derive that information from GT list
* Use it to compute local memory size given the mask of tiles to account
for
* Leverage IoctlHelper to dispatch execution (i915 vs Xe)

Related-To: NEO-9754
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2024-04-16 14:22:40 +02:00
Lukasz Jobczyk
a230c762e0 feature: Adjust PATs for dc flush mitigation 
Related-To: NEO-10556

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-04-16 13:31:02 +02:00
Mateusz Jablonski
5b6acb4f3f fix: ignore unrecognized topology type in xe path 
Related-To: NEO-11125
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-15 12:16:38 +02:00
Mateusz Jablonski
ff4a919004 fix: correct gt id in context param engines in xe path 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-15 12:07:48 +02:00
Mateusz Jablonski
62390d3def feature: add number of l3 banks to TopologyData 
Related-To: NEO-11125
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-15 11:20:43 +02:00
Mateusz Jablonski
635d495767 fix: correct gtId when getting path to frequency files in xe path 
Related-To: NEO-11111
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-15 10:44:06 +02:00
Mateusz Jablonski
27398c2b6f fix: get timestamp frequency from default engine in xe path 
Related-To: NEO-11111
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-15 10:36:08 +02:00
Lukasz Jobczyk
8a0c425495 feature: Mark selected resources as UC when mitigating dc flush 
Related-To: NEO-10556

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2024-04-12 12:52:13 +02:00
Mateusz Jablonski
b5435f7dfe fix: store queried gt list data in ioctl helper xe 
with this commit we query the info only once

Related-To: NEO-11111
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-12 12:20:34 +02:00
Mateusz Jablonski
8eb17a843b fix: correct path to frequency files in xe path 
Related-To: NEO-11111
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-12 11:49:48 +02:00
Mateusz Jablonski
5e8c71ca3d refactor: remove not needed members from ioctl helper xe 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-12 11:35:54 +02:00
Morek, Szymon
016529ac12 performance: Set WB cache mode for sysmem 
Related-To: NEO-10867

Signed-off-by: Morek, Szymon <szymon.morek@intel.com>
 2024-04-12 09:01:56 +02:00
shubham kumar
6a55bbe6cd feature(sysman): Add pmt support in windows 
Related-To: NEO-8804

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
 2024-04-10 12:42:19 +02:00
Compute-Runtime-Validation
5288100d86 Revert "feature(sysman): Add pmt support in windows" 
This reverts commit ebf88c92ca.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-04-09 17:37:41 +02:00
Mateusz Jablonski
cb2b572e94 feature: add support for null aub mode 
In this mode AUB csr will be created, however, no aub file will be created

Related-To: NEO-11097
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-09 16:59:42 +02:00
Morek, Szymon
52411a1739 fix: Remove unrecoverable_if in IoctlHelperXe 
This method is always called to check if
debugger is enabled.

Signed-off-by: Morek, Szymon <szymon.morek@intel.com>
 2024-04-09 09:49:01 +02:00
Compute-Runtime-Validation
9568ee47e7 Revert "fix: remove compiler cache legacy implementation" 
This reverts commit 864f42116c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-04-09 02:06:51 +02:00
Dominik Dabek
f40449b3e8 performance: revert usm pool chunk alignment 
Revert chunk alignment change (back to 512 bytes) - real cause of issues
was OOB access and need to be investigated by workload owner.

Remove unrecoverable in WddmInterface23 submit to pass errors to upper
layers.

Related-To: NEO-11005

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-04-08 18:46:50 +02:00
Weronika Kapusta
864f42116c fix: remove compiler cache legacy implementation 
Related-To: NEO-10679
Signed-off-by: Kapusta, Weronika <weronika.kapusta@intel.com>
 2024-04-08 16:40:57 +02:00
Bartosz Dunajski
1627172e28 feature: add helper to check if device to host copy fence is required 
Related-To: NEO-10417

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-04-08 11:18:44 +02:00
Kacper Nowak
b8d19ccfb5 refactor: Move logic for querying maxMemoryFillPatternSize to product helper 
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
 2024-04-05 09:35:01 +02:00
Mateusz Jablonski
9468915768 fix: correct preemption support in xe path 
preemption is always supported by xe kmd

Related-To: NEO-10496, HSD-18037744953
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-04-04 13:29:02 +02:00
shubham kumar
ebf88c92ca feature(sysman): Add pmt support in windows 
Related-To: NEO-8804

Signed-off-by: shubham kumar <shubham.kumar@intel.com>
 2024-04-04 11:08:58 +02:00
Young Jin Yoon
907129bb33 feature: disable scratch page by default 
Modified default values for disableScratch and gpuPageFault
to true and 10 respectively in drm_neo.cpp, in order to
disable scratch pages by default.
Modified to set gpuPageFault to 0 as a default value when
scratch page is not disabled.

Related-To: GSD-5673
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
 2024-04-04 09:50:02 +02:00
Mateusz Jablonski
420e1391b2 fix: handle not aligned gtt size reported by i915 
when i915 reports gtt size between 47 and 48 bits we consider
it as 48 bit VA space

Related-To: GSD-8215
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-03-29 07:51:06 +01:00
Young Jin Yoon
d6a14d4ed5 feature: support explicit memory locking 
Added lockMemory in context to explicitly locking memory,
Added a boolean flag in graphics_allocation to indicate the allocation
is locked, and modified memory_operations_handler to add lock().

Related-To: NEO-8277
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
 2024-03-29 07:31:22 +01:00
Krzysztof Gibala
2374ffa915 refactor: print errno from mmap and munmap calls 
Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
 2024-03-28 19:05:54 +01:00
Jemale Lockett
6d945ad28b fix: Update topology mapping 
Updates topology mapping to handle
case when no dual subslices

Resolves: NEO-10670

Signed-off-by: Jemale Lockett <jemale.lockett@intel.com>
 2024-03-28 19:03:05 +01:00
Kacper Nowak
35ca2bbea9 refactor: refactor logic for querying atomic FP capabilities 
- Move logic from product helper to compiler product helper
- Add method for adjusting fp16 and extra capabilities using release
helper (if present).


Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
 2024-03-28 15:27:45 +01:00
Mateusz Jablonski
bcaa62bed3 build: refactor linux kernel headers 
Add cmake flags to provide path to headers to drm / i915 /i915 prelim / xe

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-03-28 14:48:09 +01:00
Compute-Runtime-Validation
e3f50e8aa9 Revert "fix: handle not aligned gtt size reported by i915" 
This reverts commit dae901c13f.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-03-28 12:03:23 +01:00
Mateusz Jablonski
3b1e6b61e4 fix: remove setting scratch page flag in xe path 
Related-To: HSD-18037680815
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-03-28 09:16:48 +01:00