intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-22 01:48:50 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,206 Commits 42 Branches 655 Tags
b59b0b6b36eb44c785a457eeec2a2b98c582e9c2
Commit Graph

153 Commits

Author SHA1 Message Date
Lukasz Jobczyk
b59b0b6b36 Download timestamps before checking completion 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-28 08:14:27 +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
Filip Hazubski
64aec8dc4e Rename functions 
Rename getEngines to getAllEngines
Rename engines to allEngines
Rename getEngineGroups to getRegularEngineGroups
Rename engineGroups to regularEngineGroups

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-12-13 14:27:02 +01:00
Filip Hazubski
f137e927c5 Add EngineUsageHint debug variable 
Related-To: NEO-6219

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-12-09 16:06:23 +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
Filip Hazubski
2098b0c3fa Refactor Device::engineGroups to store only available engine groups 
Simplify logic around engine groups.
Remove no longer needed code.
Ensure correct device is used when verifying engine groups.

Related-To: NEO-6219

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-12-06 18:27:31 +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
c455c0f9c6 Remove "Update Device::engineGroups" 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-12-03 10:16:40 +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
Filip Hazubski
4461b8ea3f Refactor: Update Device::engineGroups to store only available engine groups 
Simplify logic around engine groups.
Remove no longer needed code.

Related-To: NEO-6219

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2021-12-02 15:10:22 +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
Mateusz Jablonski
3a2b018eb6 Enable blitterOperationsSupported on DG1 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-10-28 14:16:19 +02:00
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
f1b6b733f0 Reuse graphics allocation from mapped buffers in OpenCL 
Related-To: NEO-6352
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-10-27 15:53:10 +02:00
Rafal Maziejuk
811d107ea9 Don't allow blit enqueue for images with 64KB tiling & 3D surface type 
Signed-off-by: Rafal Maziejuk <rafal.maziejuk@intel.com>
Related-To: NEO-6142
 2021-10-19 16:03:48 +02:00
Zbigniew Zdanowicz
24ff191e61 Verify completion on all tiles 
Related-To: NEO-6244

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-10-15 15:43:28 +02:00
Katarzyna Cencelewska
1c8a6d895a Use hwInfoConfig to check blitter support for image 
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2021-10-13 17:51:00 +02:00
Maciej Dziuban
75b7adbe95 Skip transfer when CL_MAP_INVALIDATE_REGION is specified 
Resolves: NEO-5490
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-10-13 17:13:33 +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
Bartosz Dunajski
5560663b01 Revert "Disabled forced cross engine synchronization on single queue" 
This reverts commit 4b5432967eb9f484a491323b6766efe14929c5e9.

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-10-06 17:49:48 +02:00
Mateusz Jablonski
5e201f40be Prevent nullptr dereference in aub dump subcapture mode 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-10-04 14:23:19 +02:00
Bartosz Dunajski
50bd8b5f19 Disabled forced cross engine synchronization on single queue 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-10-01 13:09:33 +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
Zbigniew Zdanowicz
3b35ba504f Adapt command stream receiver to multiple active partitions 
Related-To: NEO-6244

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-09-23 14:32:20 +02:00
Andrzej Koska
bd9457262e Removing dependent commandQueue kernels 
Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
Related-To: NEO-6212
 2021-09-23 14:04:53 +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
Mateusz Jablonski
d348526941 Simplify checkAndActivateAubSubCapture method 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-09-22 20:23:56 +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
Zbigniew Zdanowicz
cd4f3c221a Synchronize switching command buffers for all partitions 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-09-08 12:12:23 +02:00
Maciej Dziuban
3e6b3cd780 Revert "Create single point for selecting engine for builtin ops" 
This reverts commit 6513bd371a69cb821ea45c7c1964ea1f51dd75b2.

Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-02 11:58:46 +02:00
Compute-Runtime-Validation
94cd243360 Revert "Correct CSR used for hostptr allocations in builtins" 
This reverts commit 69ae9dc9c2.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-09-02 04:45:06 +02:00
Bartosz Dunajski
0345d9f707 Improve queries with number of SubDevices 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-09-01 14:01:57 +02:00
Maciej Dziuban
69ae9dc9c2 Correct CSR used for hostptr allocations in builtins 
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-09-01 13:19:49 +02:00
Bartosz Dunajski
92000bd75b Improve Device getter to support EngineInstanced Device with single Engine 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-08-31 15:50:23 +02:00
Maciej Dziuban
a03b5f8a95 Create single point for selecting engine for builtin ops 
- selectCsrForBuiltinOperation selects proper CSR
- selected CSR is passed to dispatchBcsOrGpgpuEnqueue
- Notifications such as notifyEnqueueReadBuffer are now made on correct engine
- Temporary allocs for hostptrs are now created on gpgpuCsr

Related-To: NEO-6057
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-08-31 13:29:17 +02:00