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
10,792 Commits 42 Branches 655 Tags
b04a337b3fe2bc1401effe0f729f63c73c58cfcd
Commit Graph

1563 Commits

Author SHA1 Message Date
Zbigniew Zdanowicz
3f8c19eec9 Limit system memory flag in builtin kernels to destination argument 
Related-To: NEO-6959

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2022-07-19 10:58:51 +02:00
Bartosz Dunajski
52b00a11b0 Remove LSH from CommandQueue 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-07-19 08:47:02 +02:00
Baj, Tomasz
b450d3c20b Add cl_khr_device_uuid to extension list 
Related-To: NEO-5681

Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
 2022-07-18 12:28:04 +02:00
Compute-Runtime-Validation
f9888db0fb Revert "Check indirect access from igc" 
This reverts commit e14c91fa6c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2022-07-16 07:36:49 +02:00
Dominik Dabek
e14c91fa6c Check indirect access from igc 
Related-To: NEO-7182

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2022-07-15 15:01:48 +02:00
Warchulski, Jaroslaw
4147f40970 DisableKernelRecompilation flag and binary kernel recompilation warning 
Resolves: NEO-6513
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2022-07-14 18:22:49 +02:00
Milczarek, Slawomir
3e22f30ed5 clEnqueueMigrateMemINTEL with memory prefetch for KMD migrated shared allocation 
Related-To: NEO-6740

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2022-07-14 17:35:22 +02:00
Kamil Kopryk
7c538b956a Correct typo 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-07-14 10:13:12 +02:00
Lukasz Jobczyk
5dd25d9e8c Destroy multi graphics allocations synchronously 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-07-13 17:18:33 +02:00
Zbigniew Zdanowicz
82a6f9e7b2 Use compute walker system fence for system memory or events in use 
Related-To: NEO-6959

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2022-07-13 11:55:32 +02:00
Zbigniew Zdanowicz
e07f9f0698 Add kernel algorithm to check any argument is using system memory 
Related-To: NEO-6959

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2022-07-12 13:08:49 +02:00
Mateusz Hoppe
5a3a39a281 Experimental support for OCL debugging with L0 
- initial changes

Related-To: NEO-7075

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2022-07-12 12:57:15 +02:00
Artur Harasimiuk
6cb44ae0d9 includes refactor 
use gen specific hw_cmds instead of all-in-one

Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-07-08 17:02:19 +02:00
Mateusz Hoppe
9a667308b9 Refactor: move DebuggerL0 initialization to RootDeviceEnvironment 
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2022-07-07 16:36:53 +02:00
Katarzyna Cencelewska
25ce4d0c04 Clean unused code 
remove parts with device queue

Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2022-07-07 14:52:26 +02:00
Artur Harasimiuk
e245523730 per gen/per sku TEST_F/TEST_P refactor 
In gen/sku specific tests include only required files to reduce
dependency on not related HW scpecific headers and improve build
performance.
This is achieved by reduce in usage of hw_test.h and related collateral,
like shared/source/helpers/definitions/hw_cmds.h which can be replaced
by sku specific hw_cmds_<sku>.h

Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-07-06 23:13:46 +02:00
Zbigniew Zdanowicz
461a2eb8c7 Refactor interface to hardware interface 
Related-To: NEO-6959

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2022-07-05 11:54:33 +02:00
Bartosz Dunajski
4fb4a1d77b Add LogicalStateHelper getter for CommandQueue. 
Refactor Kernel handling

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-07-04 13:21:15 +02:00
Kamil Kopryk
1ef5161a54 Correct check if binding table prefetch is supported 
Remove redundant resetBindingTablePrefetch function,
disable binding table prefetch on xe platforms in OCL.


Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-07-01 11:43:39 +02:00
Artur Harasimiuk
2b9827ad7d hw_cmds.h for XE refactor 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-06-30 11:52:27 +02:00
Artur Harasimiuk
a8e2bd3f98 hw_cmds.h usage cleanup 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-06-29 11:15:45 +02:00
Kamil Kopryk
efa19a0b18 Simplify code - reverse helper function logic to avoid not needed negation 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-06-29 09:19:33 +02:00
Kamil Kopryk
68d26470d7 Simplify code - buffer create 1/n 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-06-28 16:56:41 +02:00
Wawiorko, Grzegorz
e500581da3 Update CL_DEVICE_LATEST_CONFORMANCE_VERSION_PASSED value 
Signed-off-by: Wawiorko, Grzegorz <grzegorz.wawiorko@intel.com>
 2022-06-28 12:00:18 +02:00
Kamil Kopryk
47fa30b419 Simplify code - image create function 
Reduce number of lines, reduce nested if statements
and others
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-06-27 17:46:03 +02:00
Artur Harasimiuk
4dff4e165c includes simplification 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-06-27 15:08:46 +02:00
Kamil Kopryk
858059a3c0 Reduce unnecessary move constructors calls 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-06-27 12:49:53 +02:00
Lukasz Jobczyk
7a1cac0674 Fix EnableCmdQRoundRobindEngineAssign flag 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-06-27 11:38:52 +02:00
Artur Harasimiuk
4673a98074 includes simplification 
use HW specific header instead generic one

Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-06-24 22:07:18 +02:00
Kamil Kopryk
83cab52dc4 Reduce unnecessary copies of memory properties 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-06-24 16:49:26 +02:00
Naklicki, Mateusz
fd867c1621 Update OCL headers 
Update headers to the OpenCL-Headers-2022.05.18 release:
https://github.com/KhronosGroup/OpenCL-Headers/releases/tag/v2022.05.18

Related-to: NEO-7102
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
 2022-06-23 17:07:16 +02:00
Filip Hazubski
b1a9fb886f Remove useChannelRedForUnusedShaderChannels helper function 
For CL_LUMINANCE images always force channel red.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2022-06-22 12:18:58 +02:00
Szymon Morek
9a26e505a8 Pass LSC policy to IGC in build options 
Related-To: NEO-7003


Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2022-06-21 11:51:56 +02:00
Dominik Dabek
39dfaf64bc Fix: Flush on svmMap on multi device 2/n 
Previous fix was causing the runtime to get buffer size
without gfx allocation, causing a seg fault.

This commit moves the fix logic to enqueue handler,
only changing the enqueueProperties.

Related-To: NEO-6948

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2022-06-21 11:38:28 +02:00
Maciej Plewka
6ab6e1abff Fix mutex order for event task and move args to gpu 
This commit fixes problem with untransfered shared usm memory to gpu
when there is submit to gpu trigerred by user event. Also there is a fix
for dead lock problem caused by mixed orders of locking mutexes in csr
and in direct submission controller.

Related-To: NEO-6762

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-06-21 11:28:25 +02:00
Kamil Kopryk
d308df254c Add ail for FAHBench on DG2 
Add missing synchronization in the FAHBench kernel
which caused hang on DG2.

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
Related-To: NEO-6946
 2022-06-21 10:21:51 +02:00
Lukasz Jobczyk
f98c6b1a8b Disable round robin engine assign on PVC 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-06-20 15:24:18 +02:00
Dominik Dabek
ae61f0368a Fix: Flush on svmMap on multi device 
On multi device contexts we allocate svm in system memory.

This caused svmMap calls to assume no copy is needed and
no cache flush was sent to gpu and data modified by earlier
gpu commands was not being visible on host.

This change will add pipecontrol with dcFlush on svmMap
calls when task count from wait is enabled.

Related-To: NEO-6948

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2022-06-20 12:24:43 +02:00
Kamil Diedrich
97ea332a9f Add support for ntHandles in OCL 
Signed-off-by: Kamil Diedrich <kamil.diedrich@intel.com>
 2022-06-17 22:55:53 +02:00
Filip Hazubski
9c18c0247e Correct surface format used for CL_LUMINANCE images 
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2022-06-15 19:00:11 +02:00
Neumann, Marta
0583413499 Remove error for unused parameter 
Remove error for unused parameter
from clGetKernelMaxConcurrentWorkGroupCountINTEL

Resolves: NEO-7044

Signed-off-by: Neumann, Marta <marta.neumann@intel.com>
 2022-06-15 18:48:22 +02:00
Bartosz Dunajski
939d109362 Add LogicalStateHelper class 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-06-14 16:57:16 +02:00
Maciej Plewka
213dc2fe24 Make CPU copy for read buffer when host ptr is write combined on DG2 
With this commit on DG2 32bit driver will check if passed host ptr for
clEnqueueReadBuffer is write combined memory. If check will be true copy
will be make on CPU.

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-06-13 21:23:21 +02:00
Artur Harasimiuk
6d43e96dee style: configure readability-identifier-naming.ClassCase 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2022-06-13 18:02:39 +02:00
Katarzyna Cencelewska
c59c4b2957 Add hwInfo as argument to method getSupportedDeviceFeatureCapabilities 
set proper value in method isMatrixMultiplyAccumulateSupported to be
consistent with support of extension *matrix_multiply_accumulate*

Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2022-06-13 15:03:43 +02:00
Bartosz Dunajski
5510dc7daa Add adjustHwInfoForIgc support 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-06-13 14:31:53 +02:00
Bartosz Dunajski
39c1c4d530 Remove virtual padding support 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-06-08 12:42:44 +02:00
Maciej Plewka
5bee8ebd35 Revert "Allow cpu buffers copy on DG2 in 32bit" 
This reverts commit 2055daf696.

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-06-08 11:26:00 +02:00
Daniel Chabrowski
c303c218be Add missing pragma once in header files 
Signed-off-by: Daniel Chabrowski <daniel.chabrowski@intel.com>
 2022-06-07 16:19:11 +02:00
Maciej Plewka
2055daf696 Allow cpu buffers copy on DG2 in 32bit 
Resolves: NEO-6906, NEO-6000

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-06-06 16:32:35 +02:00