Commit Graph

670 Commits

Author SHA1 Message Date
4b42b066f8 Use dedicated using type for TaskCount
Related-To: NEO-7155

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2022-11-28 16:44:44 +01:00
914939c377 Fix execution of cooperative kernels on multi-tile device
Add flag for forcing execution of kernels on single tile
Force cooperative kernels to use only single tile

Related-to: NEO-6729
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2022-11-28 14:36:21 +01:00
bc619fcbec Queue stall mode for RelaxedOrdering
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-11-23 12:09:52 +01:00
bb308c04ed Refactor aubstream include interface
set include path to third_party/aub_stream
rename third_party/aub_stream/headers -> third_party/aub_stream/aubstream

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-11-23 10:30:13 +01:00
f19abda0e2 Set root device index in OsContext
- correclty choose default engine context accounting for root device
index and  subdevices bitfield

Related-To: NEO-7516

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2022-11-16 23:02:19 +01:00
59b3d3fbea Move code from header files to cpp files
Moved code from:
- shared/test/common/mocks/mock_execution_environment.h
- shared/test/common/fixtures/mock_aub_center_fixture.h

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-11-16 15:06:07 +01:00
a66e69abc9 Prealloc cmd buffer for CSR only when being used
Related-To: NEO-7361

Currently additional command buffer is
preallocated for all CSRs, even for those which
won't be used by application. This PR changes that

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2022-11-15 20:06:29 +01:00
0e47bcde1d Move ClCoreHelper ownership to RootDeviceEnvironment 4/n
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>

Use RootDeviceEnvironment getHelper<ClCoreHelper> for
- isSupportedKernelThreadArbitrationPolicy
- getSupportedThreadArbitrationPolicies
2022-11-15 17:24:11 +01:00
9564af14f5 Move ClCoreHelper ownership to RootDeviceEnvironment 3/n
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>

Use RootDeviceEnvironment getHelper<ClCoreHelper> for
- getQueueFamilyName
- getKernelPrivateMemSize
- preferBlitterForLocalToLocalTransfers
2022-11-15 15:45:33 +01:00
5f8cc9b99b Remove commented code
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-11-15 14:20:17 +01:00
1d4240a0c8 Move ClCoreHelper ownership to RootDeviceEnvironment 1/n
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>

Use RootDeviceEnvironment getHelper<ClCoreHelper> for
- requiresNonAuxMode
- requiresAuxResolves
2022-11-15 10:35:22 +01:00
0a07ea94c7 Enable bcs split for H2H transfers
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-11-14 14:23:02 +01:00
25a5ed0dca Allocate buffers in local memory for PVC multi root device platforms (1/n)
PVC platform with no support for atomic operations on system memory
must always allocate buffers in local memory to avoid atomic access violation.
Note: the feature is being implemented under the new registry key
AllocateBuffersInLocalMemoryForMultiRootDeviceContexts (disabled by default)

Related-To: NEO-7092

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2022-11-14 13:56:50 +01:00
e75d62af5d Set as default use of device based timestamps
Related-To: NEO-7042
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2022-11-10 16:39:56 +01:00
c0ce5f4684 Revert "Set as default use of device based timestamps"
This reverts commit 2d229f3fea.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-11-10 11:21:00 +01:00
57cea7365e Return submission status from flushTagUpdate method
Related-To: NEO-7412
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-11-09 14:04:16 +01:00
f77f47099c OCL: Fix error for too big dimensions
- cases with null lws should only fail when computed
lws sizes result in too big number of workgroups

Related-To: NEO-6976

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2022-11-08 16:11:41 +01:00
2d229f3fea Set as default use of device based timestamps
Related-To: NEO-7042
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2022-11-08 13:34:58 +01:00
68300a9605 Correct typo - createFunc
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2022-11-08 09:16:43 +01:00
1c3d5c3892 Prepare mechanism for returning GPU execution error on OCL API
translate task count value to OCL error

Related-To: NEO-7412
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-11-04 15:54:19 +01:00
91c69e0fe7 Patch global variables and constants once
This change replaces mechanism of patching global constants and
variables in kernel per relocation to patching them only once. This
would improve linking time performance for kernels with multiple global
symbols.

Signed-off-by: Luzynski, Sebastian Jozef <sebastian.jozef.luzynski@intel.com>
2022-11-03 17:45:09 +01:00
52b1d92193 Mock debug program instead of using binaries
Removes usage of precompiled binaries in debug program tests.

Related-To: NEO-7383

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
2022-11-02 17:50:42 +01:00
69bef975f0 OCL cache per thread data
Add caching mechanism for local ids in OCL.

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
2022-11-02 17:07:29 +01:00
565d820933 Replace virtual method call for DC flush with stored bool value 3/n
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2022-10-18 15:04:02 +02:00
c224fd0666 Require LWS to be in ascending format X >= Y >= Z
This change fixes problem with memory locality.
When calculating work group size do not take into account
work group sizes where there's bigger number of elements in
higher dimensions namely: Y>X or Z>Y.

Related-To: NEO-5719

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
2022-10-18 13:23:57 +02:00
945897cf55 Revert "Replace virtual method call for DC flush with stored bool value 3/n"
This reverts commit 9d94089a95.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-10-13 04:46:10 +02:00
9d94089a95 Replace virtual method call for DC flush with stored bool value 3/n
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2022-10-12 14:38:47 +02:00
1fedaee18c Wait on timestamps in Event::wait
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-10-10 13:04:21 +02:00
2f24ef6855 Error from clEnqueueNDRangeKernel() for too big group counts
Resolves: NEO-6976

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2022-10-05 12:35:16 +02:00
23eff82d0a OCL: optimize creating printf buffer
Dont create printf buffer when kernel doesnt require it

Related-To: HSD-18023825570
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-09-30 12:25:57 +02:00
5986a7199a Share front end state updates between regular and immediate command lists
Related-To: NEO-5019

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2022-09-23 09:46:35 +02:00
efac290ba3 Do not use selector copy engine
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-20 21:49:00 +02:00
e00a5e0a1e Release main copy engine from device and sub device
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-20 17:12:34 +02:00
3d5e34f727 Reduce the size of masks to 4.
32 is not required.

Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2022-09-19 21:53:40 +02:00
0192e8038f Check for GPU hang in path with wait for timestamps
Related-To: NEO-6868

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2022-09-19 15:01:46 +02:00
3a7f266d66 Enable BCS split in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-08 15:56:30 +02:00
f65d2aeb87 Split copy along single dimension
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-08 12:39:06 +02:00
c0ce477f85 Revert "Enable BCS split WA in OCL"
This reverts commit abfcaf1265.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-09-06 20:42:57 +02:00
16d9000429 Add option to change GRF mode
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-09-06 13:00:17 +02:00
abfcaf1265 Enable BCS split WA in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-05 13:34:11 +02:00
0d6bef0753 Add BCS split to api specific config
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-05 11:13:10 +02:00
20f49481f2 Revert "Enable BCS split WA in OCL"
This reverts commit d672920121.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-09-03 20:25:10 +02:00
fa6bccdb30 Add new mt test for scenario with blitter
also change in other EnqueueKernelTest to use a proper
retValue per thread
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
2022-09-02 17:31:48 +02:00
01dc470d26 Fix BCS split ULTs on 32 bit
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-02 09:56:21 +02:00
d672920121 Enable BCS split WA in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-01 16:26:00 +02:00
399758ef17 Change default engines for BCS split
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-08-31 21:34:36 +02:00
a3dedcc7ee Add minimal transfer size for BCS split
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-08-31 21:28:40 +02:00
f656707fc0 Use hardware support flags for state compute mode state changes
Related-To: NEO-5019

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2022-08-25 18:46:37 +02:00
f7b3b20f81 Add warning when SLM is not enough for kernel
Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
2022-08-24 01:56:41 +02:00
595cfebaef Refactor PIPE_CONTROL programming
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-08-23 13:55:25 +02:00