intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-08 05:56:36 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,087 Commits 43 Branches 655 Tags
fccd22e3c78d34de86093e45def070e528b376d4
Commit Graph

117 Commits

Author SHA1 Message Date
Rafal Maziejuk
c6ee7065db Move isPageTableManagerSupported function from HwHelper to HwInfoConfig 
Signed-off-by: Rafal Maziejuk <rafal.maziejuk@intel.com>
Related-To: NEO-4541
 2021-08-19 17:35:08 +02:00
Kamil Kopryk
582a3620a2 Remove not needed hwHelper 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2021-08-11 17:04:31 +02:00
Kamil Kopryk
0845a3b34b Revert "Remove not needed hwHelper" 
This reverts commit 0d11b51c6b.

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2021-08-09 12:43:20 +02:00
Kamil Kopryk
0d11b51c6b Remove not needed hwHelper 
Related-To: NEO-6106

Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2021-08-06 14:28:04 +02:00
Filip Hazubski
2dd0e67e65 Disable overdispatch by default 
When disable overdispatch is available:
- change default value of CFE_STATE::ComputeOverdispatchDisable to true.
- change default value of
INTERFACE_DESCRIPTOR_DATA::ThreadGroupDispatchSize to 3u.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-08-03 15:28:53 +02:00
Milczarek, Slawomir
eb14d8458b Add helper function to enable stateless compression 
Related-To: NEO-5107

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2021-08-02 14:34:33 +02:00
Lukasz Jobczyk
3c842575c1 Enable direct submission by default on XE HP 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-08-02 12:10:03 +02:00
Zbigniew Zdanowicz
a869921c2a Remove RMW from gfx allocations 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-07-15 11:28:03 +02:00
Bartosz Dunajski
a49b45a679 Initialize HwInfo in tests 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-06-30 17:59:46 +02:00
Zbigniew Zdanowicz
0e5ca243e2 Add notify enable parameter to post sync commands 
Related-To: NEO-5845

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-06-17 19:22:51 +02:00
Szymon Morek
3ed0f074af Add method to set compression flag 
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2021-06-10 12:27:24 +02:00
Zbigniew Zdanowicz
6088b71256 Improve implementation of getMaxThreadsForWorkgroup method 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-05-27 13:25:38 +02:00
Mateusz Jablonski
b50a6bec82 Correct isBlitCopyRequiredForLocalMemory 
detect not lockable allocation based on gmm flag
Related-To: NEO-5733

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-20 13:17:49 +02:00
Szymon Morek
d55afceb8b Additional method to disable compression 
Resolves: NEO-5828

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2021-05-19 16:53:07 +02:00
Bartosz Dunajski
afa461efb0 L0::Event to support dynamic size - part 2 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-05-19 14:00:58 +02:00
Compute-Runtime-Validation
b415cbae23 Revert "Additional method to disable compression" 
This reverts commit 058679b5c2.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-05-17 17:19:56 +02:00
Szymon Morek
058679b5c2 Additional method to disable compression 
Resolves: NEO-5828

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2021-05-17 12:15:06 +02:00
Bartosz Dunajski
a6c6290c09 Move TSP creation to HwHelper 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-05-14 15:08:53 +02:00
Kamil Kopryk
86f63bb2ed Check supportsMediaBlock capability in ocloc 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2021-05-13 18:57:05 +02:00
Mateusz Jablonski
fcbf1dcf32 Mark SVM_GPU allocation as not lockable 
require blitter usage if allocation is not lockable and in local memory

Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 17:47:15 +02:00
Mateusz Jablonski
a552d1fd65 Revert "Mark SVM_GPU allocation as not lockable" 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 12:24:02 +02:00
Mateusz Jablonski
a79f7b678b Mark SVM_GPU allocation as not lockable 
require blitter usage if allocation is not lockable and in local memory

Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 09:49:35 +02:00
Zbigniew Zdanowicz
544890c066 Change default placement of preemption allocation 
Related-To: NEO-5800

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-05-11 15:26:24 +02:00
Compute-Runtime-Validation
c453e7fe8b Revert "Mark SVM_GPU allocation as not lockable" 
This reverts commit 5341d0663c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-04-29 18:06:38 +02:00
Mateusz Jablonski
5341d0663c Mark SVM_GPU allocation as not lockable 
use blitter if available and allocation is not lockable

Related-To: NEO-5733

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-29 15:55:13 +02:00
Dominik Dabek
bb9d902899 Add padding for ISA allocations 
Related-To: NEO-5771
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2021-04-27 11:03:58 +02:00
Kamil Kopryk
7a5e0e13a5 Add isBlitterForImagesSupported helper 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2021-04-22 16:10:20 +02:00
Milczarek, Slawomir
e5eba8be53 Add setters and getters for coherency type in render surface state 
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2021-04-13 16:12:46 +02:00
Lukasz Jobczyk
1921bfb3dc Add infrastructure to enable direct submission 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-04-07 14:23:58 +02:00
Bartosz Dunajski
47c2a3011a Remove not used MemorySynchronizationCommands argument 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-03-31 17:58:43 +02:00
Bartosz Dunajski
b6e3817f31 Dont program dcFlush when not allowed 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-03-31 16:13:19 +02:00
Sebastian Luzynski
6163120809 Remove unnecessary check for gen12lp during symbol relocations 
Related-To: NEO-5433

Signed-off-by: Sebastian Luzynski <sebastian.jozef.luzynski@intel.com>
 2021-03-30 11:48:06 +02:00
Artur Harasimiuk
330ee3d227 AubMemDump refactor 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2021-03-24 18:26:00 +01:00
Michal Mrozek
b5ba5028d7 Add tlb invalidation. 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2021-03-23 13:20:44 +01:00
Filip Hazubski
8d55bfe21d Implement zeCommandListAppendLaunchCooperativeKernel 
Resolves: NEO-4725


Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-03-22 19:26:41 +01:00
Lukasz Jobczyk
27ca04f77f Check new residency model support 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-03-18 10:06:31 +01:00
Katarzyna Cencelewska
d9172c9b7f 1Mb alignment support in OsAgnostic path 
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2021-03-10 10:56:25 +01:00
Bartosz Dunajski
8b89fb8541 Capability to exclude Engine on SubDevice 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-03-08 11:32:13 +01:00
Bartosz Dunajski
9c164a01a6 AuxTranslationMode fallback path 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-03-02 12:09:04 +01:00
Filip Hazubski
a0d3e8b352 Simplify stepping conversion 
Related-To: NEO-5475

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-02-16 11:52:17 +01:00
Filip Hazubski
7d01074ee4 Update aub/tbx stepping handling 
For the stepping value use hardware value.

Resolves: NEO-5475

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-02-15 13:57:39 +01:00
Slawomir Milczarek
ca84fdd64a Add helper function stub to get number of cache regions 
Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2021-02-12 11:01:07 +01:00
Filip Hazubski
ae484993e2 Update builtins generation 
Use revision id when generating cpp files.
Related-To: NEO-5167

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-02-11 14:36:58 +01:00
Sebastian Luzynski
0526910f6f Check if additional flag is required 
Signed-off-by: Sebastian Luzynski <sebastian.jozef.luzynski@intel.com>
 2021-02-10 13:51:05 +01:00
Maciej Plewka
51e073af73 Revert "Extra checks for gen12lp" 
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2021-02-04 18:02:30 +01:00
Lukasz Jobczyk
049e77b235 Check if KMD migration is supported 
Related-To: NEO-3312

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-02-04 11:49:46 +01:00
Sebastian Luzynski
22c25a231e Extra checks for gen12lp 
Signed-off-by: Sebastian Luzynski <sebastian.jozef.luzynski@intel.com>
 2021-02-04 11:23:15 +01:00
Filip Hazubski
5618d4dfa4 Correct image initialization for linear storage allocations 2/2 
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-02-02 17:12:18 +01:00
Bartosz Dunajski
580fdd757c Improve buffer surface state programming 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-02-02 14:42:18 +01:00
Bartosz Dunajski
90f96f083c Add const suffix 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-01-14 14:12:16 +01:00