intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-22 10:17:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
17,857 Commits 42 Branches 655 Tags
53da277bc1837016d2bc77242f375c75ff37b9c5
Commit Graph

151 Commits

Author SHA1 Message Date
Lukasz Jobczyk
82e29fd048 Add bcs split control mask 
Introduce debug variable to control which engines
the tranfser will be split into

Related-To: NEO-7173

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-08-19 13:21:10 +02:00
Lukasz Jobczyk
b10b3ed9dd Add initial enqueue bcs split infrastructure 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-08-18 15:02:08 +02:00
Compute-Runtime-Validation
b38c750cc4 Revert "Add finish before command queue is released" 
This reverts commit 50fae92ea2.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2022-08-05 19:25:23 +02:00
Kamil Kopryk
d4d54f5093 Cleanup includes 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-07-25 09:58:38 +02:00
Mateusz Hoppe
50fae92ea2 Add finish before command queue is released 
Related-To: NEO-5279

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2022-07-20 12:16:27 +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
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
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
Lukasz Jobczyk
82d1962aba Assign BCS at first blit enqueue 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-05-04 17:11:34 +02:00
Compute-Runtime-Validation
a3fe50c2e4 Revert "Assign BCS at first blit enqueue" 
This reverts commit 0469034acb.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2022-05-04 13:33:25 +02:00
Lukasz Jobczyk
0469034acb Assign BCS at first blit enqueue 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-05-04 10:19:05 +02:00
Lukasz Jobczyk
73d3d83e60 Assign gpgpu engine at first enqueue 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-04-29 11:33:12 +02:00
Compute-Runtime-Validation
e8e3355a93 Revert "Assign BCS at first blit enqueue" 
This reverts commit 5f5a1a6f81.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2022-04-26 09:40:46 +02:00
Lukasz Jobczyk
5f5a1a6f81 Assign BCS at first blit enqueue 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-04-25 13:48:21 +02:00
Lukasz Jobczyk
6fdcb83020 Add missing tbx calls to timestamp wait logic 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-04-19 14:24:06 +02:00
Lukasz Jobczyk
aa46dd9cdf Assign data only to unused barrier timestamps 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-03-30 16:56:06 +02:00
Lukasz Jobczyk
a74ae8f6af Implement timestamp wait for events 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2022-03-17 17:57:30 +01:00
Michal Mrozek
bfacd14b61 Remove not needed code. 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2022-03-02 13:10:15 +01:00
Patryk Wrobel
0ecc7c5e3b Detect GPU hangs in clFinish 
This change introduces detection of GPU hangs in
clFinish function as well as unit tests to cover
the new code.

Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
 2022-02-28 19:07:36 +01:00
Patryk Wrobel
7f729b7f89 Detect GPU hang in clWaitForEvents 
This change:
- moves NEO::WaitStatus to a separate file
- enables detection of GPU hang in clWaitForEvents
- adjusts most of blocking calls in CommandStreamReceiver to return WaitStatus
- adds ULTs to cover the new code

Related-To: NEO-6681
Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
 2022-02-23 13:33:09 +01:00
Lukasz Jobczyk
418a8854b2 Skip timestamp wait when enqueue non kernel operation 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-30 10:02:07 +01:00
Lukasz Jobczyk
95585a81f7 Optimize timestamp packet dependencies 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-30 09:48:36 +01:00
Lukasz Jobczyk
14e338e669 Revert "Optimize timestamp packet dependencies" 
This reverts commit c365b422963917e7b882f9db985969c036f0fa3f.

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-23 14:29:29 +01:00
Lukasz Jobczyk
1f0c58d0bf Refactor timestamp wait mechanism 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-16 13:22:19 +01:00
Bartosz Dunajski
fe8cb190bc Remove deprecated code 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-12-14 11:36:10 +01:00
Michal Mrozek
ebb16c8b74 Add new debug key to control dependency resolution. 
Currently only supported scenario is one in order queue.
Instead of resolving dependencies via semaphores, do this with pipe controls.

Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2021-12-09 17:26:38 +01:00
Lukasz Jobczyk
0c49fa8203 Add missing cache flush for blocked path 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-07 12:36:34 +01:00
Maciej Dziuban
e3bb526067 Optimize timestamp packet dependencies 
- Clear dependencies even if last engine changed
- Do no program semaphore waiting for blit when blit is submitted with gpgpu
- Track barrier timestamps to correctly synchronize blits in OOQ

Related-To: NEO-6444
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-12-07 11:47:50 +01:00
Lukasz Jobczyk
09d2ffb9ed Add missing cache flush 
Resolves: NEO-6505

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-06 17:28:12 +01:00
Lukasz Jobczyk
63116e4100 Use wait utils while waiting for timestamps 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-02 17:49:05 +01:00
Lukasz Jobczyk
36efe72e3e Add wait on timestamp mechanism 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-01 08:48:00 +01:00
Maciej Dziuban
457ef00abf Reuse graphics allocations in svmMemcpy 
Related-To: NEO-6352
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-11-17 14:03:05 +01:00
Lukasz Jobczyk
e8cc34d7b0 Add infrastructure to assign engine to command queue with round robin 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-11-15 13:13:40 +01:00
Maciej Dziuban
b8a03cdea1 Remove getAnyBcs() method 
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-11-10 18:55:37 +01:00
Compute-Runtime-Validation
908a7721b2 Revert "Assign engine to command queue using round robin algorithm" 
This reverts commit 2fff0f9059.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-11-10 07:25:44 +01:00
Lukasz Jobczyk
2fff0f9059 Assign engine to command queue using round robin algorithm 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-11-09 11:05:16 +01:00
Compute-Runtime-Validation
9058de77cc Revert "Assign engine to command queue using round robin algorithm" 
This reverts commit 1c68ac1cbc.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-11-08 16:36:18 +01:00
Maciej Dziuban
4c4b37f8d2 Implement BCS selection heuristic for OpenCL CommandQueue 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-11-08 12:58:14 +01:00
Lukasz Jobczyk
1c68ac1cbc Assign engine to command queue using round robin algorithm 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-11-03 17:16:54 +01:00
Maciej Dziuban
a582f34c04 Reuse graphics allocations in readBufferRect/writeBufferRect 
Related-To: NEO-6352
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-11-03 14:58:51 +01:00
Kamil Diedrich
5fdcb14d57 WSL fallback to staging buffer on blocking reads 
Signed-off-by: Kamil Diedrich <kamil.diedrich@intel.com>
 2021-10-28 03:34:58 +02:00
Maciej Dziuban
19a6c9b1d3 Track separate task count for each BCS in OpenCL CommandQueue 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-10-13 12:06:27 +02:00
Maciej Dziuban
c910a58aa0 Store bcsEngine in an std::vector in OpenCL CommandQUeue 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-10-07 21:55:21 +02:00
Maciej Dziuban
c04f8e5e5b Pass copy engines to waitUntilComplete in OpenCL command queue 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-24 14:11:44 +02:00
Maciej Dziuban
6d1e048327 Rename an overload of waitUntilComplete to waitForAllEngines 
- Overloaded functions were quite different, they should have different names
- waitForLatestTaskCount function was redundant and hence its body was moved
inside waitForAllEngines

Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-23 09:43:11 +02:00
Maciej Dziuban
04b6a604ec Refactor BCS in OpenCL CommandQueue 
- use CopyEngineState class to hold task count and engine type
- pass engine type to updateBcsTaskCount

Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-22 10:39:46 +02:00
Maciej Dziuban
2707618fe3 Pass engine type to getBcsCommandStreamReceiver in OpenCL 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-21 16:27:07 +02:00
Maciej Dziuban
a4b3dc29e4 Remove unnecessary method 
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-21 11:34:27 +02:00
Maciej Dziuban
c7d86af500 Pass blitter CSR to event 
Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-15 12:49:22 +02:00
Maciej Dziuban
858727010f Add selectCsrForBuiltinOperation method to OpenCL CommandQueue 
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
Related-To: NEO-6057
 2021-09-10 12:26:47 +02:00