intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-27 15:53:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
13,813 Commits 42 Branches 655 Tags
f5d683063b0da32f34567658d5d8eeed73eec3e5
Commit Graph

5063 Commits

Author SHA1 Message Date
Mateusz Jablonski
f5d683063b test: pass empty execution environment when preparing device environments 
Related-To: NEO-8187

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-02 13:05:34 +02:00
Lukasz Jobczyk
51a00fb4c8 fix: Enable timestamp wait for events on MTL 
Related-To: NEO-8067

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-08-02 11:51:01 +02:00
Mateusz Jablonski
6d020ceb97 test: improve tests for getProductMaxPreferredSlmSize for releases 12.70 / 12.71 
Related-To: NEO-7786
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-02 11:27:40 +02:00
Mateusz Jablonski
659f7b645f refactor: move methods from CompilerProductHelper to ReleaseHelper 
Related-To: NEO-7786
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-02 10:40:48 +02:00
Dominik Dabek
12ab74fe96 performance: flag to program barrier in task cs 
Add debug flag ProgramBarrierInCommandStreamTask to program barrier
pipe control in task command stream instead of csr command stream.
This will reduce the number of batch buffer starts.

Related-To: NEO-8147

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-08-02 10:26:34 +02:00
Mateusz Jablonski
02aa4b6acc refactor: unify isMatrixMultiplyAccumulateSupported definition 
Related-To: NEO-7786
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-01 14:39:53 +02:00
Mateusz Jablonski
59c7cef9db test: add dedicated tests for release helpers 
Related-To: NEO-7786
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-01 14:27:05 +02:00
Igor Venevtsev
e2ad2e8db0 fix: initialize GPU VA for additional synchronization WA 
Related-To: NEO-8072

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
 2023-08-01 11:43:52 +02:00
Zbigniew Zdanowicz
22ab72ed3d performance: do not flush caches when writing global timestamp 
Related-To: HSD-18032167035

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-08-01 10:46:18 +02:00
Lukasz Jobczyk
1d2ed7e534 fix: invalidate tlb when dispatch monitor fence 
Related-To: NEO-8067

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-31 21:26:39 +02:00
Lukasz Jobczyk
b6535541ab performance: Enable ULLS on MTL Windows 
Resolves: NEO-8067

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-31 21:03:15 +02:00
Mateusz Jablonski
1e95ed33f9 refactor: remove redundant parameter from HardwareInfo ctor 
hw ip version is queried from KMD or set based on device id and rev id

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-31 16:12:57 +02:00
Mateusz Jablonski
43654bfc02 fix: add support for handling same hw ip release for different products 
Related-To: NEO-8187
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-31 15:58:19 +02:00
Compute-Runtime-Validation
f4d05a8e6b Revert "fix: Add missing fp64 extensions in caps initialization" 
This reverts commit 22a719d62f.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-07-31 13:43:23 +02:00
Mateusz Jablonski
98fd9f5687 performance: change preferred allocation method on MTL devices 
prefer allocating resources by KMD

Related-To: NEO-7194
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-31 10:45:43 +02:00
Lukasz Jobczyk
820771212c Revert "performance: Enable ULLS on MTL Windows" 
This reverts commit 47d099a565.

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-31 09:22:40 +02:00
Filip Hazubski
12af65a970 fix: Change default value of EnableCpuCacheForResources debug toggle 
This change disables CPU caching for resources
not accessed by CPU for MTL devices.

Related-To: NEO-7194

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-07-31 09:15:43 +02:00
Filip Hazubski
7ea22d0369 feature: Add pat index programming to gem create ext call 
When upstream ioctl helper is created it will try to create small
allocation, adding I915_GEM_CREATE_EXT_SET_PAT extension. If it
succeeds, for all resources with valid pat index value it will then
explicitly program pat index value with gem create ext call.

PrintBOCreateDestroyResult value can be used to:
- print whether the set pat extension is supported by the kernel, when
  ioctl helper is created
- print whether set pat extension was added for a given gem create ext
  call and what pat index value was programmed

Note: introduced changes are disabled by defualt.
Toggle DisableGemCreateExtSetPat can be used to enable new functionality.

Related-To: NEO-7896

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-07-31 09:00:04 +02:00
Filip Hazubski
3e811fc9d4 test: Move shared code tests from gmm_helper_tests.cpp to shared directory 
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-07-31 08:44:26 +02:00
Compute-Runtime-Validation
4b517832a9 Revert "performance: Remove tlb flush on DG2" 
This reverts commit 5a16411e71.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-07-29 14:40:24 +02:00
Katarzyna Cencelewska
db35790d5d fix: add missing types that require stateless access 
Related-To: HSD-16020995919
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2023-07-28 21:32:21 +02:00
Fabian Zwolinski
22a719d62f fix: Add missing fp64 extensions in caps initialization 
In a scenario where fp64 emulation is both supported and enabled,
we want to include 2 additional extensions:
- cl_khr_fp64 to deviceExtensions
- __opencl_c_fp64 to openclCFeatures (OpenCL ver. 3.0)

Related-To: NEO-7611
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2023-07-28 21:29:30 +02:00
Filip Hazubski
8dd23f4b4d feature: Add logic around cpu side allocations 
Group allocation types related to cpu side allocations in function to
query gmm usage type. These types will have caching enabled even if
CPU caching is not preferred by GPU.

Add logic to query whether the cpu access is allowed for an allocation
(in cases when it is not preffered by GPU).

Related-To: NEO-7194

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-07-28 21:04:24 +02:00
Zbigniew Zdanowicz
b4d6822991 fix: add time units to time interval logs 
Related-To: NEO-8211

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-28 20:53:51 +02:00
Mateusz Hoppe
997b599168 fix(debugger): pass correct sipAllocation to makeResident 
- sipAllocation for context must be resident in Offline mode

Related-To: NEO-7630

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-07-28 20:51:12 +02:00
Mateusz Hoppe
8516f7f6ef fix(debugger): enable debug flows in Offline mode 
- create Debugger object when Offline mode selected
Related-To: NEO-7630

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-07-28 20:37:30 +02:00
Mateusz Jablonski
11afeb29c0 test: rename test files to make them unique within neo_shared_tests 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-28 20:06:49 +02:00
Mateusz Jablonski
c22482f6f7 test: unify main function for test targets 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-28 20:00:45 +02:00
Mateusz Jablonski
c68c41c8c4 refactor: prework for setting preferred allocation method per platform 
Related-To: NEO-7194
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-28 19:54:35 +02:00
Lukasz Jobczyk
5a16411e71 performance: Remove tlb flush on DG2 
Resolves: NEO-7116

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-28 19:39:05 +02:00
Mateusz Jablonski
27e459dfd0 fix: add missing cache flushes on MTL and later integrated GPUs 
hdc pipeline / untyped dataport cache flushes were applied only on discrete GPUs

Related-To: GSD-5085
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-28 19:30:13 +02:00
Dunajski, Bartosz
e1e9907973 feature: debug flag to signal user interrupts. 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-28 18:56:28 +02:00
Mateusz Jablonski
02337bbbf8 refactor: remove not needed includes from ocloc sources 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-28 18:56:16 +02:00
Zbigniew Zdanowicz
0d8523c386 performance: add time measurement between make resident and wait on gpu 
Related-To: NEO-8211

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-27 10:13:23 +02:00
Katarzyna Cencelewska
b529adf941 fix: for 32 bit addressing adjust correctly gpuAddress if CONSTANT_SURFACE 
Related-To: HSD-16020995919
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2023-07-27 07:50:17 +02:00
Milczarek, Slawomir
1195578d96 fix: KW issue with dereference in function call that may return null 
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2023-07-27 07:39:15 +02:00
Dunajski, Bartosz
cd9ad1f04c fix: decanonize GPU VA during TBX memory read. 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-26 19:44:19 +02:00
Dunajski, Bartosz
a241099dff feature: use WaitUserFence on zeEventHostSynchronize 
Disabled by default. Debug flag is required.

Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-26 19:41:09 +02:00
Mateusz Jablonski
f84f22d23c refactor: remove unused isSharedContext variable 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-26 12:14:23 +02:00
Mayank Raghuwanshi
ea7d9fe106 feature: Xe Porting for sysman engine module 
Related-To: LOCI-4243

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
 2023-07-26 10:24:05 +02:00
Filip Hazubski
6217d97bbe Revert "fix: Increase size of reported global memory available to 98%" 
Temporarily reverting back to previously reported value to avoid corner-case
regression. Intent is reintroduce as soon as regressions are rootcaused.

This only affects Linux.

Related-To: GSD-5474, GSD-5412

This reverts commit e8ac22c265.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2023-07-26 07:52:40 +02:00
Zbigniew Zdanowicz
5ca376e655 performance: add residency diagnostic for trim callback 
Related-To: NEO-8211

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-26 07:46:55 +02:00
Compute-Runtime-Validation
b7a56521f8 Revert "refactor: Enable CSR heap sharing on Older Gen platforms" 
This reverts commit 160daeb874.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-07-26 05:40:59 +02:00
Jitendra Sharma
160daeb874 refactor: Enable CSR heap sharing on Older Gen platforms 
Related-To: LOCI-4312
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
 2023-07-25 19:37:33 +02:00
Milczarek, Slawomir
027c51d396 feature: Add CPU side USM allocation to trim candidate list on page fault 
Enable eviction of CPU side USM allocation for UMD migrations on Windows.
Reverts incorrect auto-revert commit 218de586a4f28b1de3e983b9006e7a99d3a4d10e.

Related-To: NEO-8015

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2023-07-25 15:21:12 +02:00
Igor Venevtsev
2e48f9eeff Revert "performance: Enable ULLS direct submission on DG2 Windows" 
This reverts commit 9ee6e5bf19.

Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com>
 2023-07-25 12:20:24 +02:00
Dunajski, Bartosz
2c50fd9486 fix: waiting for completion in TBX mode 
- use testTaskCountReady method to check TaskCount value
- download all allocations when TaskCount is ready

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-25 11:54:09 +02:00
Joshua Santosh Ranjan
b6e76b9118 fix: Move event reference time tracking into event class 
This would avoid recalculating reference timestamps
when event is used with different command lists.

Related-To: LOCI-4563

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
 2023-07-25 08:44:47 +02:00
Mayank Raghuwanshi
175ceb9bd1 feature: Add support for media freq domain on linux 
Related-To: LOCI-4552

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
 2023-07-25 08:12:33 +02:00
Compute-Runtime-Validation
e3a408f536 Revert "performance: Change preferred allocation method to AllocateByKmd" 
This reverts commit 957aa99f9e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-07-25 07:23:46 +02:00