fbc29bb43d
refactor: use indirectDataAlignment from gen cmds
...
Related-To: NEO-10641
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-25 21:02:36 +02:00
a3c3b6533a
performance: improve pool handling
...
Related-To: NEO-11731
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-06-25 17:04:17 +02:00
2ec2f8c085
refactor: add heaplessStateInitEnabled bool to dispatch walker args
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-25 15:53:19 +02:00
1cba900ad9
refactor: Add dc flush mitigation infrastructure
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-06-25 14:53:24 +02:00
bbe11205e3
build: add cmake flags to control platform support
...
Related-To: NEO-6683
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2024-06-25 09:08:03 +02:00
29e3eb512c
performance: non-usm copy through staging buffers
...
Related-To: NEO-11501
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-06-25 07:18:53 +02:00
fed90f5c8e
fix: Add infrastructure to force dc flush when mitigate dc
...
-force dc on next tag update after RT kernel
-force dc when release shared object
Related-To: NEO-10556
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-06-24 17:15:03 +02:00
773da10099
fix: Copy hostptr using BCS when mitigate dc flush
...
Related-To: NEO-10556
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-06-24 16:26:44 +02:00
7136dfbd38
Revert "performance: improve pool handling"
...
This reverts commit 5f0b9efd2b
2024-06-24 12:47:19 +02:00
9513df52a6
refactor: Explicitly delete unused functions of BarrierCommand
...
Comply with the rule of five.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-06-24 11:18:17 +02:00
0c019c9f2b
performance: don't check multiple times if gpgpu is initialized
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-24 10:12:46 +02:00
2f6eaf149a
fix: Update SIP kernel initialization logic
...
Initialize SIP kernel when shared device is being initialized
instead of api-specific device.
Initialize debugger when shared device is being initialized
instead of during platform or driver initialization.
Add missing makeResident calls for SIP kernel in heapless paths.
Related-To: HSD-18038645398, HSD-18038819112
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-06-20 18:30:46 +02:00
78c7d8878d
refactor: change method to get indirect data address
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-20 14:24:51 +02:00
ce0047de39
fix: Use proper GA object to check shared handle in debug break
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-06-19 11:08:37 +02:00
daec249430
refactor: remove not needed createGraphicsAllocationFromNTHandle method
...
Related-To: NEO-11498
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2024-06-18 14:25:00 +02:00
b6d86d2648
refactor: tests for buffer pool
...
add support for future AIL
Related-To: NEO-11694
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-06-18 13:55:21 +02:00
5f0b9efd2b
performance: improve pool handling
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
Resolves: NEO-11731
2024-06-14 12:02:34 +02:00
730fed3206
fix: add missing tracing to all functions in api.cpp
...
Related-To: NEO-11576
Signed-off-by: Alicja Lukaszewicz <alicja.lukaszewicz@intel.com>
2024-06-13 14:55:13 +02:00
76a05c1cab
refactor: pass arrayIndex to Wddm::openNTHandle function
...
Related-To: NEO-11498
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2024-06-12 12:11:35 +02:00
5ae2709e6e
fix: Remove allow-zebin and enable-zebin compile options
...
Zebin is enabled by default.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-06-10 14:08:40 +02:00
da9c009b88
feature: assign unique interrupt to queue
...
Related-To: NEO-8179
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-07 10:06:31 +02:00
0ac1be7669
refactor: pass arrayIndex to Wddm::openSharedHandle function
...
Related-To: NEO-11498
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2024-06-07 09:51:26 +02:00
b4c31492d3
fix: add missing tracing to all functions in api.cpp
...
Related-To: NEO-11576
Signed-off-by: Alicja Lukaszewicz <alicja.lukaszewicz@intel.com>
2024-06-06 12:14:21 +02:00
e88127dcc3
refactor: remove not used multi context per engine code
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-06 11:41:15 +02:00
bc37e14e87
refactor: fallback paths for secondary context debug flags
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-05 12:02:16 +02:00
88ed909e57
feature: assign secondary BCS engines at queue creation
...
Related-To: NEO-7824
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-03 09:41:43 +02:00
8e79e7a174
refactor: fix gpu address formatting in logs
...
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-05-31 13:55:26 +02:00
5e92d530de
performance: Reuse GPU timestamps by default on Windows
...
Related-To: NEO-10615
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-28 12:25:30 +02:00
387ec34207
fix: correct timestamps if cpu diff below resolution
...
Related-To: NEO-10615
Currently if cpu diff is equals to zero, gpu timestamp
will be decreased relatively to submit timestamp.
This commit fixes that so timestamps will be aligned.
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-28 11:12:37 +02:00
0b2c9e92e7
Revert "performance: Reuse GPU timestamps by default on Windows"
...
This reverts commit bca3fecaa0
2024-05-25 07:59:00 +02:00
bca3fecaa0
performance: Reuse GPU timestamps by default on Windows
...
Related-To: NEO-10615
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-24 20:11:45 +02:00
0a74d718f2
refactor: allow using different engine types for secondary contexts
...
Related-To: NEO-7824
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-05-24 09:39:46 +02:00
59829aeb11
fix(ocl): Force rebuild if binary contains bindless kernel
...
Related-To: NEO-7063
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2024-05-20 14:15:17 +02:00
90df4b298b
fix: cache flush dependency for queue blocked
...
Related-to: NEO-9872, HSD-18038461954
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-05-20 11:55:24 +02:00
8989bf4078
fix: set timestamp diff correctly if lower than resolution
...
Related-To: NEO-10615
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-17 20:15:58 +02:00
a236171f0d
performance(ocl): enable device usm alloc reuse
...
Enabling on MTL+
Limited to use max 2% of global device memory.
Related-To: NEO-6893, NEO-11463
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-05-17 13:32:45 +02:00
4c5d567b40
Revert "fix: remove not needed check in OCL CPU copy path 2"
...
This reverts commit 0a27aa9f7b
2024-05-17 10:52:17 +02:00
34f53d5d94
Revert "performance: Reuse GPU timestamps by default"
...
This reverts commit 7aceed58ca
2024-05-16 21:52:10 +02:00
0a27aa9f7b
fix: remove not needed check in OCL CPU copy path 2
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-05-16 12:38:39 +02:00
7aceed58ca
performance: Reuse GPU timestamps by default
...
Related-To: NEO-10615
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-15 17:51:42 +02:00
b4d839fe29
performance(usm): l0, add usm host memory pooling
...
Disabled by default.
Related-To: NEO-11356
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-05-15 15:20:51 +02:00
ae8c7589dc
refactor: move implicit arg has indirect access
...
Move implicit arg has indirect access boolean to kernelAttributes
Related-To: NEO-11396
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-05-15 13:11:04 +02:00
fd47030ad6
fix: use igc indirect detection v3
...
Update to use igc indirect detection v3. Fix for not detecting indirects
passed as implicit arguments.
Related-To: NEO-11396
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-05-15 06:35:42 +02:00
4c43ca518b
Revert "fix: remove not needed check in OCL CPU copy path"
...
This reverts commit 92f9c8be96
2024-05-14 20:12:28 +02:00
92f9c8be96
fix: remove not needed check in OCL CPU copy path
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-05-14 17:05:55 +02:00
e35b951a00
performance: Allow indirect allocs as pack on OpenCL
...
Related-To: NEO-11228
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-10 17:57:42 +02:00
e39893485c
fix: add cache flush as dependency for bcs ccs synchronization
...
Related-to: NEO-9872
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-05-09 13:43:39 +02:00
10ed479b16
performance: share inter-module ISA allocations
...
Related-To: NEO-10258
Currently each module has it's own GA
for kernel ISA's. This change allows new modules to
reuse existing allocation.
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-09 08:43:55 +02:00
4667f55ea2
fix: add missing checks to return proper OpenCL error from API
...
changes affect clEnqueueNDCountKernelINTEL and
clGetKernelMaxConcurrentWorkGroupCountINTEL
Related-To: NEO-9688
Signed-off-by: Aleksander Czerwionka <aleksander.czerwionka@intel.com>
2024-05-07 20:32:36 +02:00
d6c16c1640
fix: remove compiler cache legacy implementation
...
Related-To: NEO-10679
Signed-off-by: Weronika Kapusta <weronika.kapusta@intel.com>
2024-05-06 18:28:35 +02:00
83e8ae4a20
performance: Reuse GPU timestamp instead of KMD escape
...
This can be enabled only if related
debug flag will be set.
Related-To: NEO-10615
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-06 14:46:30 +02:00
8342c0ae2f
Revert "fix: add cache flush as dependency for bcs ccs synchronization"
...
This reverts commit 5e57bb2a32
2024-05-01 03:05:47 +02:00
3ded04341c
refactor: remove not needed code.
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2024-04-30 16:24:21 +02:00
03dcff1398
refactor: remove not needed code.
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2024-04-30 15:10:34 +02:00
ee71157f7f
fix: opencl support for bindless kernels
...
Related-To: NEO-11156
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2024-04-30 12:02:17 +02:00
5e57bb2a32
fix: add cache flush as dependency for bcs ccs synchronization
...
Related-to: NEO-9872
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-04-30 11:57:49 +02:00
cbc868c4ed
refactor: add mock_aubstream
...
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2024-04-25 20:08:30 +02:00
d122e1c906
fix: Flush render state cache on release shared object
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-04-22 17:37:42 +02:00
ae139aeffd
refactor: Passing information about the engine
...
Extension of the interface with information
about the engine type passed to the function
Related-To: NEO-10678
Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2024-04-22 13:33:56 +02:00
a2e0f9ac09
fix: Add AUB/TBX writable for clEnqueueWriteBuffer on SVM hostptr
...
Related-To: NEO-11082
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2024-04-18 12:17:10 +02:00
ea057abd36
fix: allow empty set to be passed to clSetKernelExecInfo
...
Related-To: GSD-8538
Signed-off-by: Jaroslaw Warchulski <jaroslaw.warchulski@intel.com>
2024-04-16 14:11:04 +02:00
ce3bb1327e
feature: add method to switch enable/disable mid thread preemption
...
Resolves: NEO-8089
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-04-15 16:26:52 +02:00
4bb30e51a2
fix: use default csr for scratch in OCL
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-04-11 16:58:35 +02:00
cfc3b6a8c2
refactor: add heaplessModeEnabled argument to isHeaplessStateInitEnabled
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-04-11 10:08:10 +02:00
cb2b572e94
feature: add support for null aub mode
...
In this mode AUB csr will be created, however, no aub file will be created
Related-To: NEO-11097
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-04-09 16:59:42 +02:00
9568ee47e7
Revert "fix: remove compiler cache legacy implementation"
...
This reverts commit 864f42116c
2024-04-09 02:06:51 +02:00
864f42116c
fix: remove compiler cache legacy implementation
...
Related-To: NEO-10679
Signed-off-by: Kapusta, Weronika <weronika.kapusta@intel.com>
2024-04-08 16:40:57 +02:00
0d69dfe165
refactor: remove comment
...
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-04-08 11:43:19 +02:00
35ca2bbea9
refactor: refactor logic for querying atomic FP capabilities
...
- Move logic from product helper to compiler product helper
- Add method for adjusting fp16 and extra capabilities using release
helper (if present).
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-03-28 15:27:45 +01:00
bcaa62bed3
build: refactor linux kernel headers
...
Add cmake flags to provide path to headers to drm / i915 /i915 prelim / xe
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-28 14:48:09 +01:00
436579ca8c
fix: Disable async release of buffers with external host ptr
...
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-27 15:07:14 +01:00
707796a50d
Revert "fix: Disable async release of buffers with external host ptr"
...
This reverts commit 9b715c3ffc
2024-03-27 07:49:54 +01:00
fce016ee7a
refactor: add new semaphore param
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-03-26 15:46:47 +01:00
78a4a92b44
refactor: reorder members to reduce internal padding in structs
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-25 15:50:00 +01:00
9b715c3ffc
fix: Disable async release of buffers with external host ptr
...
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-25 12:55:57 +01:00
07b9117b44
refactor: Explicitly delete copy c-tor and copy assignment of GlBuffer
...
Comply with the rule of three.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-03-25 10:55:02 +01:00
e9b866ab11
Revert "fix: Disable async release of buffers with external host ptr"
...
This reverts commit 70a62d89e3
2024-03-23 11:49:42 +01:00
70a62d89e3
fix: Disable async release of buffers with external host ptr
...
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-22 18:11:27 +01:00
da7b03dd15
fix: to always use grfs count in calculateNumThreadsPerThreadGroup
...
grf size != grf count
Related-To: GSD-8437
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-03-22 11:03:18 +01:00
dd1d52259e
refactor: add param rootDeviceEnvironment to calculateNumThreadsPerThreadGroup
...
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-03-21 22:25:14 +01:00
0cec5ccc32
fix: check if any of devices has BindlessHeapHelper enabled
...
- report Bindless_images extension in driver only when at least one
device has global bindless heaps enabled
Related-To: NEO-10352
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-03-20 20:50:58 +01:00
7db5f6d5bf
fix: add texture cache flush on image dtor
...
Related-To: NEO-9794
Signed-off-by: Bartlomiej Wolny <bartlomiej.wolny@intel.com>
2024-03-18 17:03:17 +01:00
eb259c1f52
fix: set kernel LWS prior to obtaining indirect heaps
...
When calculating the size of the indirect object heap,
the local work group size from kernel implicit args is taken into account.
If the LWS is not set before this calculation,
it can lead to insufficient ioh allocation size.
Such a problem is seen when local ids are generated by the runtime
and then written to ioh. The write fails due to lack of space in the allocation.
Related-To: IGC-7708
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-03-14 10:38:46 +01:00
e00230a6c2
fix: correctly report support for SPIR-V 1.0 through 1.3
...
Related-To: NEO-10336
Signed-off-by: Ben Ashbaugh <ben.ashbaugh@intel.com>
2024-03-12 17:54:09 +01:00
87f2357868
fix: Update CL_DEVICE_LATEST_CONFORMANCE_VERSION_PASSED value
...
Signed-off-by: Grzegorz Wawiorko <grzegorz.wawiorko@intel.com>
2024-03-12 08:42:21 +01:00
f71f6d2b72
refactor: remove not needed code
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2024-03-08 18:18:55 +01:00
5e15543b14
test: improve unit tests - use virtual file system
...
- use virtualFileSystem in ULTs, writeDataToFile() does not create file
but instead saves filename. Call to fileExists() checks if file was
previously written
Related-To: NEO-7006
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-03-08 13:34:19 +01:00
168445784e
feature: introduce states programming at driver init heapless ocl
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-03-08 12:29:44 +01:00
88a8bc8ac6
fix: Download BCS allocations when timestamps are completed
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-08 10:47:53 +01:00
f0281202bf
feature: Signal to OGL creating/destroying shared buffer
...
Related-To: NEO-9151
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-03-06 16:28:28 +01:00
895c951a7f
fix: Unlock CmdQ before download allocations
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-05 14:53:11 +01:00
bfbe5a048c
fix: verify retVal from poll function in gl sharing sync on Linux
...
unify logic of synchronization objects
add default iniialization of gl context guard members
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-05 11:26:27 +01:00
246c24f78f
fix: Download allocations when timestamps are complete
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-04 16:05:31 +01:00
8c55dd91a6
fix: don't use poll/close syscalls in gl sharing tests
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-04 14:09:46 +01:00
52430762ac
fix: cl_cache L0 env vars + refactor code structure
...
Added support for new Compiler Cache
environment variables in Level Zero.
Moved
`opencl/source/compiler_interface/default_cache_config.cpp`
`level_zero/core/source/compiler_interface/default_cache_config.cpp`
to shared directory
`source/compiler_interface/default_cache_config.cpp`
Switched enabling cache by default from per OS to per API.
Changed default state of cl_cache in Level Zero to disabled.
Related-To: NEO-10045
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-03-01 17:35:08 +01:00
e2c511bc00
feature(ocl): Improve Linux CL/GL sharing support
...
This commit is aimed at drastically improving the support for the CL/GL
sharing
extension on linux. The current support is not really usable as it only
supports a few texture format, and only on EGL contexts. It is also
pretty
buggy since it requires the texture to be bound when placing the CL call
to
share it which is just plain wrong and will not work in many
applications.
This new version makes used of the "official" interop extension from
MESA
which is available for GLX and EGL contexts, allows sharing of buffers
and
not just texture and supports many more formats.
This is still far from being a fully compliant / full featured version
of
the extension, but it's a big step forward in my opinion and allows to
run
some real applications.
I've tested gr-fosphor (SDR spectrum display) and Davinci Resolve as
examples.
Both of theses don't work without theses improvements.
Fixes: https://github.com/intel/compute-runtime/issues/659
Fixes: https://github.com/intel/compute-runtime/issues/667
https://github.com/intel/compute-runtime/pull/673
Related-To: NEO-3599
Signed-off-by: Sylvain Munaut <tnt@246tNt.com>
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-01 13:38:56 +01:00
4baee71974
refactor: add out cmd argument to semaphore wait encoder
...
Related-To: NEO-10065
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-03-01 11:43:36 +01:00
373ef608bc
refactor: unify calculating max group size between OCL and L0
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-27 13:32:10 +01:00
0bf8e8727e
refactor: add output buffer argument to store register to memory encoder
...
Related-To: NEO-10064
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-02-27 13:31:55 +01:00
cfd3edfb2c
fix: Align IOH entry
...
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-26 14:36:31 +01:00
0c5cba8ebd
refactor: use common indirectDataAlignment static constexpr value
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-16 13:55:00 +01:00
57c946b61c
Revert "fix: align indirect data pointer to cacheline size in heapless mode"
...
This reverts commit 004e6e647f
2024-02-15 05:49:19 +01:00
9570d02134
Revert "fix: correctly report support for SPIR-V 1.0 through 1.3"
...
This reverts commit 5120ec2f93
2024-02-15 04:00:31 +01:00
cccd9a3703
refactor: Add method for retrieving extra device info
...
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-02-14 16:38:15 +01:00
004e6e647f
fix: align indirect data pointer to cacheline size in heapless mode
...
Align indirect data pointer to cacheline size in heapless mode,
restore debug_break_if if avx2 load/store operation
gets unaligned pointer,
remove fallback to mm256 loadu/storeu unaligned operation
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-14 10:00:15 +01:00
5120ec2f93
fix: correctly report support for SPIR-V 1.0 through 1.3
...
Related-To: NEO-10336
Signed-off-by: Ben Ashbaugh <ben.ashbaugh@intel.com>
2024-02-14 09:21:06 +01:00
4656e2ec12
Revert "refactor: remove not needed check for cpu transfer in ocl"
...
This reverts commit 098e2e76fb
2024-02-13 21:16:43 +01:00
098e2e76fb
refactor: remove not needed check for cpu transfer in ocl
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-13 18:47:14 +01:00
2e997a2542
refactor: Use shared method for setting FP16/32 caps in OCL
...
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-02-09 08:47:20 +01:00
59f661356c
feature: use heapless builtins in OCL if supported
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-08 15:49:58 +01:00
486cc71b76
refactor: Add GDI profiling
...
Resolves: NEO-9236
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-07 18:44:11 +01:00
371788210d
performance: limit usm host allocation recycle
...
Query system total memory size and limit usm host allocation recycle to
use at most x%.
x is read from ExperimentalEnableDeviceAllocationCache for device and
ExperimentalEnableHostAllocationCache for host.
Related-To: GSD-7497
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-07 17:45:41 +01:00
ab1ffea592
refactor: Create function to check if OCL2.1 caps are enabled or enforced
...
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-02-06 08:27:09 +01:00
2cad595a0d
performance: debug flag for usm host alloc recycle
...
set ExperimentalEnableHostAllocationCache=1 to recycle host usm
allocations
Related-To: GSD-7497
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-01 16:47:59 +01:00
6d3a53fe7f
refactor: Improve scratch programming in heapless mode
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-31 10:39:39 +01:00
fb46066abc
Revert "fix: enable cache env variables for level-zero"
...
This reverts commit 743904d2df
2024-01-31 08:33:05 +01:00
743904d2df
fix: enable cache env variables for level-zero
...
Related-To: NEO-10045
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-01-30 14:01:42 +01:00
fa9c79fb63
Revert "refactor: Add GDI profiling"
...
This reverts commit 524ae7713a
2024-01-30 10:47:34 +01:00
dcab4863d5
performance(ocl): calculate max buffer pool count
...
Set max buffer pool count to use at most 2 percent of device total memory.
Related-To: NEO-9690
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-30 07:04:36 +01:00
d2c6283879
fix(ocl): add support for deprecated value of CL_MEM_DEVICE_ID_INTEL
...
Resolves: NEO-10184, NEO-10195, NEO-10196
Resolves: NEO-10200, NEO-10205, NEO-10207
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-29 17:07:26 +01:00
524ae7713a
refactor: Add GDI profiling
...
Resolves: NEO-9236
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-29 11:36:04 +01:00
327d4c4d48
fix: update OpenCL headers to v2023.12.14
...
https://github.com/KhronosGroup/OpenCL-Headers/releases/tag/v2023.12.14
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-25 16:42:14 +01:00
67b0b18be3
fix: osAgnostic path for allocate with alignment
...
Resolves: NEO-9334
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-25 11:03:34 +01:00
6d1df09e58
fix: fix exported function address when heapless mode is enabled in OCL
...
Related-To: IGC-8472
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-24 16:21:42 +01:00
6e434e0424
performance(ocl): increase buffer pool size
...
increase pool size to 2MB and threshold to 1MB
add limit to the number of pools, set to 2
Related-To: NEO-9690
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-24 10:55:29 +01:00
87d13fcb6e
fix: fix scratch programming in heapless mode
...
Related-To: NEO-10107
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-23 15:26:56 +01:00
a697a3f718
refactor: create new members for storing spill and private memory in scratch
...
rename private scratch space into scratch space slot 1 as it can be generic
Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-23 12:42:25 +01:00
f9f9035b95
Revert "refactor: create new members for storing spill and private memory in ...
...
This reverts commit 87eb5f554a
2024-01-23 09:13:00 +01:00
e949ba7144
Revert "refactor: Add GDI profiling"
...
This reverts commit 8d56f8fb6b
2024-01-23 06:13:02 +01:00
87eb5f554a
refactor: create new members for storing spill and private memory in scratch
...
rename private scratch space into scratch space slot 1 as it can be generic
Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-22 19:48:48 +01:00
b77e1a6a71
feature: improve reporting max cooperative group count
...
Related-To: NEO-8210
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-22 14:56:15 +01:00
8d56f8fb6b
refactor: Add GDI profiling
...
Resolves: NEO-9236
Related-To: NEO-10036
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-22 14:24:08 +01:00
6f4ed10919
refactor: unify getMaxWorkGroupCount logic
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-22 11:16:45 +01:00
7a09c51f3d
fix(ocl): querying memobj offset
...
Querying buffer offset via clGetMemObjectInfo should not modify its
value.
Related-To: NEO-9690
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-19 15:48:46 +01:00
b266f1f3cc
refactor: improve implicit scaling interface
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-19 14:09:04 +01:00
e0ccf22557
fix: indirect access in external functions
...
Read indirect_stateless_count in module external functions.
If greater than 0, mark all kernels that have the has_stack_calls flag
set from this module as having indirect accesses.
Related-To: NEO-7712
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-18 15:29:41 +01:00
36dcfc0b42
feature: add stateless heapless builtins
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-16 11:11:31 +01:00
c49695fa6e
fix: flush L3 cache and wait for flush to complete when event is completed
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-16 07:05:35 +01:00
b3b402cad2
feature(zebin): read indirect detection version
...
Read indirect detection version intel compat notes from zebin.
This is to prepare for enabling indirect access optimization in AOT
built kernels.
Related-To: NEO-7712
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-12 14:20:52 +01:00
f99edf72e1
refactor: Add common HardwareCommandsHelper enablers
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-12 09:39:12 +01:00
a73fb4d2fe
fix: correct reporing kernel private size on L0
...
unify the logic across APIs
Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-09 09:54:05 +01:00
9b52d52062
performance(ocl): enable usm pool allocator
...
Enable on xe hpg and lpg platforms
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-05 16:17:48 +01:00
af1620a308
fix(ocl): allocation info from pool svm ptr
...
Fix querying allocation info from pooled svm ptr.
Handle requested allocation alignment.
Refactor sorted vector usage.
Do not associate device with host pool allocation.
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-05 15:20:01 +01:00
2a46350ba3
fix: fix programming indirect data pointer in heapless mode
...
Indirect data pointer should be offsetted by used offset.
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-04 07:51:31 +01:00
5535ef3049
Revert "performance(ocl): enable usm pool allocator"
...
This reverts commit 7bc8424a69
2023-12-29 05:54:07 +01:00
31e9b5e9fa
feature: add support for secondary contexts in group
...
Related-To: NEO-7824
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-12-28 13:31:08 +01:00
7bc8424a69
performance(ocl): enable usm pool allocator
...
Enable opencl usm pool allocator by default
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-12-28 13:14:41 +01:00
d238a68bae
fix(ocl): usm pool allocator correct size
...
Wrong debug flag was used for setting host allocation pool size
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-12-27 23:14:28 +01:00
df66a0276f
refactor: remove not used logic to check dynamic postsync layout
...
Related-To: NEO-8210
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-27 13:12:11 +01:00
2fe3804cc2
performance(ocl): add usm allocation pooling flag
...
EnableDeviceUsmAllocationPool and EnableHostUsmAllocationPool for device
and host allocations respectively.
Pool size will be set to flag value * MB.
Allocation size threshold to be pooled is 1MB.
Pools are created per context.
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-12-27 11:42:01 +01:00
239831f097
fix: return error for 0 size usm allocations
...
according to both level zero and opencl specs, usm allocations with
size=0 should return invalid/unsupported buffer size errors
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-12-22 17:26:39 +01:00
18fb432552
refactor: Stop using hard-coded BCS engine as default one
...
Do not rely on presence of BCS0 engine.
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2023-12-21 17:34:57 +01:00
a4888b39c6
build: add clang-tidy restriction for Enum case
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-21 08:58:51 +01:00
bf60d77e10
refactor: correct naming of enum class constants n/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-20 10:56:37 +01:00
138fb65401
refactor: correct naming of enum class constants 11/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-19 14:52:57 +01:00
de93bc6928
refactor: correct naming of enum class constants 10/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-19 11:30:39 +01:00
a6458433dc
refactor: correct naming of enum class constants 9/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-19 10:36:25 +01:00
dd1b9d6abc
refactor: correct naming of enum class constants 8/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-19 08:18:18 +01:00
7e795cd3c1
feature: Adding support for OCL C support queries to ocloc
...
Feature needed for automated OCL C compilation with ocloc as backend.
Added queries :
* CL_DEVICE_EXTENSIONS
* CL_DEVICE_EXTENSIONS_WITH_VERSION
* CL_DEVICE_PROFILE
* CL_DEVICE_OPENCL_C_ALL_VERSIONS
* CL_DEVICE_OPENCL_C_FEATURES
Sample command line:
ocloc query -device skl CL_DEVICE_OPENCL_C_FEATURES
Related-To: GSD-7420
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2023-12-18 15:19:16 +01:00
d99104d5bf
refactor: improve ImplicitArg struct handling
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-18 15:19:00 +01:00
fca28a930f
refactor: correct naming of enum class constants 7/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-18 13:05:56 +01:00
976c6d3acc
feature: initial register count query implementation
...
Adds a per-kernel and per-device query to determine the
number of GRF registers that a kernel was compiled for.
This is an informal query for now, but may be added to
a formally supported extension in the future.
Related-To: NEO-9807
Signed-off-by: Ben Ashbaugh <ben.ashbaugh@intel.com>
2023-12-18 11:45:01 +01:00
27fbdde4c5
refactor: correct naming of unified memory enums
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-13 15:58:21 +01:00
739d181026
refactor: correct naming of enum class constants 6/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-13 14:48:52 +01:00
8c90350f3c
refactor: correct naming of enum class constants 5/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-13 10:06:02 +01:00
432142c574
refactor: correct naming of enum class constants 4/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-13 08:08:51 +01:00
895519db38
refactor: correct naming of NEOImageType enum values
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-12 11:15:28 +01:00
b182917d9d
refactor: correct naming of allocation types
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-11 16:23:37 +01:00
beafea9b39
refactor: correct naming of enum class constants 2/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-11 13:13:35 +01:00
58323bfb12
refactor: improve PostSync helper methods
...
Related-To: NEO-8210
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-11 10:41:30 +01:00
a2994e9b29
Revert "performance(ocl): set pool allocator threshold 1MB"
...
This reverts commit fc1d93af8e
2023-12-09 07:02:42 +01:00
bec9874487
fix: Improved event profiling setup for bcs split enqueue
...
Fixes OpenCL Khronos failures in test profiling with bcs split
Related-To: NEO-8927
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2023-12-07 21:29:55 +01:00
aab3e7f7c5
refactor: improve getting postsync_data struct type
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-07 15:41:44 +01:00
7a14db7f9b
refactor: add max front end threads in EncodeWalkerArgs
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-12-07 11:38:46 +01:00
c8c3f862f4
refactor: Add key to force zero copy without coherency
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-12-07 07:56:54 +01:00
39ccf0297f
fix: Skip rebuild binary forced by flag when lack of ir
...
when flag RebuildPrecompiledKernels set and call clCreateProgramWithBinary
skip rebuild if ir binary not available
Resolves: HSD-18035219734
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-12-06 20:00:05 +01:00
fc1d93af8e
performance(ocl): set pool allocator threshold 1MB
...
Increase pool allocator threshold to 1MB
Remove stack allocations based on threshold in tests.
Related-To: NEO-9690
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-12-06 19:55:48 +01:00
9ce3713ace
refactor: improve Walker args handling
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-06 16:10:26 +01:00
da957d1a37
refactor: correct naming of enum class constants 1/n
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-05 14:26:42 +01:00
f8eefbd020
fix: return error code for usm param passed to clSetKernelExecInfo
...
Related-To: NEO-8202
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2023-12-05 09:14:00 +01:00
6849d33326
refactor: remove redundant definitions KB/MB/GB
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-05 08:55:18 +01:00
92838c05fd
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-04 19:02:36 +01:00
c48e57e2de
refactor: rename register offsets and constants
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-04 18:31:39 +01:00
87247e6949
fix: Add path for clCreateBuffer with host unified memory ptr
...
Related-To: NEO-9612
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2023-12-04 18:16:56 +01:00
9486cd2a26
refactor: rename WALKER_TYPE to DefaultWalkerType
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-04 16:29:32 +01:00
552c129c0b
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-04 15:14:02 +01:00
933e5ab818
refactor: remove dead code
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-12-04 14:31:00 +01:00
c3d3a4db1f
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-04 13:45:53 +01:00
fe0c7f1004
fix: when size is 0 then don't copy
...
Related-To: NEO-8381
Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
2023-12-04 11:18:00 +01:00
aa950a4a96
feature: Add heapless mode programming in l0 1/n
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-12-01 17:01:01 +01:00
cdcd834712
refactor: correct naming of builtin types
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-01 14:08:21 +01:00
e57d372608
refactor: correct naming of enum class constants
...
EngineGroupType
BlitDirection
PostBlitMode
WaitStatus
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-01 11:53:51 +01:00
b92b5892b8
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-01 08:34:19 +01:00
c3ac7b78bd
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-01 02:18:46 +01:00
c9664e6bad
refactor: rename global debug manager to debugManager
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-30 13:00:59 +01:00
36194c4e7d
refactor: correct variable namings
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-29 23:49:03 +01:00
aac8686095
fix: correct calculating submit cpu timestamp
...
Related-To: NEO-9590, HSD-18035219634
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-29 17:42:41 +01:00
ce7298d512
feature: Add heapless mode programming in ocl
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-11-24 12:53:39 +01:00
ac8c00048e
performance: optimize svm allocation tracking
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-11-23 10:54:01 +01:00
40fd1b0336
fix: report correct version of cl_khr_external_memory extension
...
Related-To: NEO-9530
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-11-17 15:49:56 +01:00
Kamil Kopryk