2aa0ae0eca
refactor: linux cl_cache eviction mechanism
...
Refactored eviction mechanism works as follows:
- eviction is needed only if
total size of cache binaries + size of the new binary exceed cache limit
- single evition call removes files with a summed size of 1/3 of the cache limit
- if new binary can not fit in the cache size limit
even after eviction, it will not be saved
- cache limit applies only to
files in cache directory with .cl_cache/.l0_cache extension.
Only these files are counted and only these files are removed
Minor:
- rename variables for better readability
- add `const` where possible
Related-To: NEO-4262
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-11-17 09:48:42 +01:00
27000c06cb
Revert "refactor: Store AIL in root device environment"
...
This reverts commit 02ef252b7d
2023-11-16 19:37:42 +01:00
c68f55e4f6
Revert "feature: enable bindless mode in L0 on dg2"
...
This reverts commit d1d4f9c9f3
2023-11-16 19:13:05 +01:00
d1d4f9c9f3
feature: enable bindless mode in L0 on dg2
...
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-11-16 17:19:46 +01:00
f91757c093
fix: enable 4KB allocation alignment through KMD on Windows
...
Related-To: NEO-9446
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-11-16 13:04:23 +01:00
2981c78d34
fix: check RCS support in OS agnostic path
...
Related-To: HSD-18035019656
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-11-16 12:59:42 +01:00
140532f8b6
fix: fix issues with clang-tidy on Windows
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-16 12:30:11 +01:00
7f61217a44
Revert "performance: optimize svm allocation tracking"
...
This reverts commit e91ce78ec8
2023-11-16 11:03:19 +01:00
8f06f3f50a
performance: add override cacheable to gmm
...
add attribute to override cacheable attribute to gmm constructor
enable this override for command buffers on mtl
change command buffers back to allocation by kmd
this keeps the quicker allocation which is needed to keep enqueue times
low
Related-To: NEO-8152
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-11-16 10:00:45 +01:00
e91ce78ec8
performance: optimize svm allocation tracking
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-11-15 13:58:05 +01:00
a0f8e8accc
fix: initialize max capability values for ARL
...
setup max values when overriding hw info with debug key
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-15 13:44:11 +01:00
02ef252b7d
refactor: Store AIL in root device environment
...
Instead of storing AIL configurations in global table, store it
in root device environment.
This also prevents potential scenario with accessing deleted memory due
to symbol collision when application uses both OCL/L0 libraries.
- AIL is now stored in root device environment, and gets initialized
with other helpers
- Minor: corrected naming in ULTs
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
Related-To: NEO-9240
2023-11-15 13:17:56 +01:00
961a8d91d0
refactor: move gmm constructor flags to struct
...
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-11-15 09:26:13 +01:00
c454e0d33e
fix: handle not exisiting wsl compute helper library
...
https://github.com/intel/compute-runtime/issues/688
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-14 16:06:14 +01:00
9a8138725a
fix: Deferred SVM allocations look up by gpu address
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-11-14 15:27:01 +01:00
fee423fa15
fix: Add PVC device id 0x0B6E for Intel(R) Data Center GPU Max 1100C
...
Resolves: NEO-9440
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2023-11-14 08:03:51 +01:00
cec6492cd9
fix: fix issues with ubsan in shared and ocl
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-13 12:40:57 +01:00
b3a7f5dccb
Revert "fix: support alignments in WSL2 device and shared memory allocation"
...
This reverts commit ae86635307
2023-11-11 16:25:52 +01:00
ae86635307
fix: support alignments in WSL2 device and shared memory allocation
...
Related-To: NEO-8431
Signed-off-by: Lu, Wenbin <wenbin.lu@intel.com>
2023-11-09 19:47:11 +01:00
fbe61cf547
fix: add kmd wait on cpu when wait on paging fence when needed
...
add storing of throttle hint value for direct submission
Related-To: NEO-9123
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-11-09 19:22:15 +01:00
506e03e00c
refactor: reposition ail application map
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-11-09 16:59:01 +01:00
30777d4d4c
feature: use indirect semaphore for 64b values
...
Related-To: NEO-8145
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-11-09 16:58:45 +01:00
c160e6ff93
fix: sporadic in software tags test
...
Related-To: NEO-9272
Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
2023-11-09 15:50:34 +01:00
781533565e
fix: fix issues with ubsan in shared and OCL tests
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-09 12:39:29 +01:00
3ad68cb7d6
fix: setting flush stamp to not have zero value
...
when direct submission and monitor fence is not required then use
current fence value to update flush stamp
Related-To: NEO-9123
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-11-09 08:34:21 +01:00
7a6fc209dd
performance: prealloc cmdbuffer on mtl
...
Preallocate 2 command buffers allocations per command queue initialized
on MTL.
Related-To: NEO-8152
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-11-08 17:21:13 +01:00
c558fc1b06
performance: enable v2 tg dispatch size algorithm
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
Related-To: NEO-6989
2023-11-08 16:39:49 +01:00
a0beb96db8
feature: initial support for implicit convertion to CounterBased Events
...
Related-To: NEO-8145
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-11-08 14:59:12 +01:00
06e2fdb2e9
fix: remove copy paste from WddmDirectSubmission methods
...
instead of use updateTagValueImpl to avoid missing parts
Related-To: NEO-9123
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-11-08 08:45:10 +01:00
cdf2cd5699
Revert "feature: enable illegal opcode exception"
...
This reverts commit 02b6b3bbaa
2023-11-08 01:40:23 +01:00
f36e86f121
fix: program bindless surface state size from sba properties
...
- surfaceStateSize is in pages, bindless size needs to be programmed in
surface state units
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-11-07 17:45:54 +01:00
1c37da280c
fix: fix bindless offset patching for images
...
- usingSurfaceStateHeap indicates if any of the args is using local ssh
in bindless kernels:
without global allocator - ssh is used for all args
with global bindless allocator - ssh used only for buffer with offset
set in surface state, otherwise not used
When any of the args is using ssh - getSurfaceStateHeapDataSize() returns
non-zero size.
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-11-07 11:39:49 +01:00
f0175b3916
feature: set device allocation chunking as default
...
Device allocation chunking only applies for multi-tile mode for implicit scaling
Related-To: NEO-9051
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2023-11-07 10:58:17 +01:00
3782b4bd0e
feature: add functions to get/set VA space
...
Added an extension version of zeContextGetVirtualAddressSpaceIpcHandle
and zeContextPutVirtualAddressSpaceIpcHandle, which return
ZE_RESULT_ERROR_UNSUPPORTED_FEATURE for now.
Related-To: NEO-8259
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2023-11-06 20:08:45 +01:00
02b6b3bbaa
feature: enable illegal opcode exception
...
Related-To: NEO-9088
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-11-06 16:09:29 +01:00
20c3f45998
refactor: add ulls diagnostic flag to select monitor fence input
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-11-06 15:09:36 +01:00
e0ce08bb77
fix: detect gpu hang or page fault at direct submission flush to gpu
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-11-06 14:22:02 +01:00
ed897c302d
performance: Implement V2 version of tg dispatch size algorithm.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
Related-To: NEO-6989
-Prevent imbalance in multi dimensional dispatches
-Make sure to utilize as much Eus as possible
-Prefer highest possible tg dspatch count possible
-Make sure that xe_core doesn't have uneven workgroups
2023-11-03 15:54:04 +01:00
098ea3a997
fix: add log about printing assertion failure from kernel
...
Related-To: NEO-9237
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-11-03 15:32:07 +01:00
6510c725e3
build: build aub_stream_stubs even if AubStream is available
...
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2023-11-03 14:50:35 +01:00
19586277ca
refactor: add debug flag to control delay after waiting for paging fence on cpu
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-11-03 12:49:39 +01:00
ae607502a0
feature: Add indirect data and scratch pointer to zeinfo
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-11-03 12:01:58 +01:00
73bb139e17
refactor: add applyExtraInternalOptions function
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2023-11-03 09:43:37 +01:00
bcc5a8502b
Revert "feature: add functions to get/set VA space"
...
This reverts commit 0550c80d4f
2023-11-03 02:06:36 +01:00
0550c80d4f
feature: add functions to get/set VA space
...
Added an extension version of zeContextGetVirtualAddressSpaceIpcHandle
and zeContextPutVirtualAddressSpaceIpcHandle, which return
ZE_RESULT_ERROR_UNSUPPORTED_FEATURE for now.
Related-To: NEO-8259
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2023-11-02 18:42:27 +01:00
43841fd2ef
fix: clear AllocationsList tail on free all
...
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-11-02 18:06:13 +01:00
93cf33fda0
performance: remove redundant tlb flush on monitor fence
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-11-02 12:39:05 +01:00
4a5d9eeae7
refactor: do not trigger debug break when mkdir fails with EEXIST
...
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-11-02 12:26:32 +01:00
99abb40a45
feature: Add extensions to expose dot product capabilities
...
- Add new extension property for user to query platform DP support.
- Add new blackbox and ULTs for extension.
Related-To: NEO-8786
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2023-10-31 21:54:39 +01:00
db10e85526
refactor: add new diagnostic mode for device state
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-31 16:02:53 +01:00
c9d6615231
Revert "feature: Add extensions to expose dot product capabilities"
...
This reverts commit e988fe66e3
2023-10-31 05:06:06 +01:00
060fc40938
performance: move constants out of the loop.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2023-10-30 18:16:35 +01:00
d56abe6f60
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-30 17:26:20 +01:00
e988fe66e3
feature: Add extensions to expose dot product capabilities
...
- Add new extension property for user to query platform DP support.
- Add new blackbox and ULTs for extension.
Related-To: NEO-8786
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2023-10-30 15:15:51 +01:00
036d1e4814
refactor: correct variable naming
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-30 12:48:51 +01:00
f8ad191b16
feature: Caller ID introduced to aubstream
...
... to distinguish environment of capturing.
Related-To: NEO-9235
Signed-off-by: Tomasz Kordek <tomasz.kordek@intel.com>
2023-10-30 12:37:49 +01:00
80e59ff344
fix: don't call virtual method in ctor
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-30 12:26:57 +01:00
80e3632c41
performance: do not free deferred allocations when not needed
...
Level Zero doesn't use deferred allocations so no point in paying the
price to check for them in cleanAllocationList.
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2023-10-27 18:02:43 +02:00
39cf653959
performance(ocl): cmd buffer prealloc per cmdqueue
...
Add mechanism to preallocate cmd buffer allocations in command stream
receiver reusable allocations list per command queue initialized.
This should limit additional allocations during hot loop.
Needs to be enabled in subsequent commits by setting product helper
method.
Related-To: NEO-8152
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-10-27 16:56:29 +02:00
1e18bf0392
fix: define timestamp mask based on timer resolution
...
Related-To: HSD-18034577551
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-27 11:55:20 +02:00
2eebbcd41e
fix: don't transfer FtrTile64Optimization to gmmlib
...
Related-To: HSD-18034338825
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-27 08:07:58 +02:00
5d572b9c8f
feature: allow freeing memory in aubstream
...
Related-To: NEO-2707
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-26 17:16:23 +02:00
fca2159430
Revert "fix: if device hierarchy is flat then getSubDevicesCount return 1u"
...
This reverts commit cb0bb57f49
2023-10-26 15:40:29 +02:00
cb0bb57f49
fix: if device hierarchy is flat then getSubDevicesCount return 1u
...
Related-To: NEO-9167
Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
2023-10-25 15:51:52 +02:00
c4a24d8f31
fix: Avoiding races when modifying queue and Tag data
...
Related-To: NEO-8196
Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2023-10-25 14:20:57 +02:00
1352bde5c8
fix: use pointer instead of std::function
...
MSVC Compiler found an issue that there could be an attempt to
reference a deleted function when using std::function.
As the functionality of ioctlHelper::getGpuTime is very straightforward,
simple function pointer should be sufficient to make the job and
it mitigates overhead of std::function.
Related-To: NEO-8324
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2023-10-25 06:23:43 +02:00
69f614a8c2
Revert "fix: allow legacy device binary validation logic for Blender on DG2 p...
...
This reverts commit d3d15542fb
2023-10-24 21:00:19 +02:00
ac5f64f5c6
fix: fix compilation error in clang on Windows (2/n)
...
Signed-off-by: Jablonski, Mateusz <mateusz.jablonski@intel.com>
2023-10-24 15:59:06 +02:00
6d2d16d68e
fix: avoid overflow of gpu time stamp in ns
...
Related-To: NEO-8394
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-24 14:56:15 +02:00
1fd9d29f54
feature: update Xe KMD header
...
xe_drm.h header is generated from the series "uAPI Alignment - take 1 v4"
from https://patchwork.freedesktop.org/series/124387/
Related-To: NEO-8324
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Kamil, Kopryk <kamil.kopryk@intel.com>
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2023-10-24 12:03:45 +02:00
d3d15542fb
fix: allow legacy device binary validation logic for Blender on DG2 platforms
...
Temporarily opt-out from additional compatibility checks
on DG2 for Blender AOT-compiled kernels.
This prevents a long kernel recompilation.
Additionally, same behavior can be enforced for other applications
manually via NEO debug key named DoNotUseProductConfigForValidationWa.
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
Related-To: NEO-9240
2023-10-23 18:20:37 +02:00
0b42510f41
fix: add l1 cache flush to barrier operations when required
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-23 18:18:22 +02:00
52b0f32688
fix: offset cpu address when writing chunk in simulated csr
...
- not only gpuAddress is offset but also cpu address with data needs
to be offset while writing memory.
Related-To: GSD-6604
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-23 17:01:25 +02:00
8da4a9cbc7
fix: add debug flag to control non walker signalling in in-order cmdlist
...
set to false by default
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-23 14:43:40 +02:00
875f653952
Revert "feature: support UUID feature for windows"
...
This reverts commit cb2b4214b4
2023-10-23 14:08:03 +02:00
2e09b5ff66
refactor: reposition preamble helper implementation methods
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-20 13:18:29 +02:00
b8831e87b0
fix: iGPUs - increase size of reported global memory available on Linux to 94%
...
Related-To: NEO-8989, NEO-7229
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-20 10:51:47 +02:00
ede8663e41
fix: iGPUs - increase size of reported global memory available on Windows to 94%
...
Related-To: NEO-8989, NEO-7229
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-20 10:37:11 +02:00
55abd8dc9a
fix: reduce globalMemory by internalResourcesSize for iGPUs
...
internalResourcesSize is a constant 450 MB value.
Related-To: NEO-8989
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-20 10:10:41 +02:00
90987bd878
feature: add minimal interface for software tag injection
...
* Add new Software Tag `ArbitraryString`
* Add minimal interface for injecting software tags
Related-To: NEO-5550
Signed-off-by: Marek Kozlowski <marek.kozlowski@intel.com>
2023-10-20 01:49:33 +02:00
97faeae16f
feature: heapAssigner per root device
...
- create heapAssigner per root device in memory manager to allow per
device config
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-19 19:52:24 +02:00
25195ebc96
fix: capability to write memory chunk in aub/tbx mode
...
Related-To: GSD-6604
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-19 19:13:11 +02:00
4dfa12c8eb
fix: add mechanism to detect gpu timestamp overflows
...
unify naming CpuGpu to GpuCpu
Related-To: NEO-8394
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-19 16:31:06 +02:00
750b5ba89a
fix: flush necessary caches when dispatch pipe control
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-10-19 15:09:31 +02:00
58fa968273
fix: Calculate size of buffer surface state given mapped allocations
...
Related-To: NEO-8350
- given a virtual address part of a mapping to multiple physical
allocations, then the buffer surface state size is increased to
include the allocations which follow the current allocation, which
allows users access to the remainder of the mapped buffer.
Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
2023-10-19 13:38:51 +02:00
ff1a8770fe
fix: when gt type media on xe kmd then do not inizialize
...
also use proper size when query config
Related-To: HSD-18034189281
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-10-19 12:37:36 +02:00
456f07212d
fix: Return pageSize/Heap for reservation based on the size and devices
...
Related-To: NEO-9127,NEO-9142
- Change the heap/pageSize used based on the size of the reservation
required and the device heaps available.
- Return the page size required based on the size requested by the user
for virtual reservation and the devices on the system.
- Check the size passed in by the user in memory map and physical memory
allocation is valid for the heap and page size that is required.
Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
2023-10-19 10:44:13 +02:00
5a4fa180d6
feature: control bindless compilation mode based on release
...
- check releaseHelper support when selecting bindless mode, if not
disabled, prefer bindless mode in L0 API
- bindless mode can be forced with DebugVariable: UseBindlessMode
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-19 10:11:11 +02:00
096e424428
Revert "fix: initialize tile only when gt type main on xe kmd"
...
This reverts commit cbde47d638
2023-10-19 09:47:58 +02:00
f156a74f54
fix: split chunking prefetch flags
...
Related-To: NEO-9120
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2023-10-18 19:20:42 +02:00
cbde47d638
fix: initialize tile only when gt type main on xe kmd
...
also use proper size when query config
Related-To: HSD-18034189281
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-10-18 16:01:16 +02:00
713aa05f27
Revert "performance: limit monitor fence dispatch only to task count dispatches"
...
This reverts commit f26f027ee7
2023-10-18 11:15:40 +02:00
15484c6778
fix: initialize member before using it
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-18 08:38:22 +02:00
95dc224021
refactor: change default PVC unit tests runner
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-18 08:22:27 +02:00
75c4844987
feature(internal): logging kernel dispatch params
...
Use debug flag PrintKernelDispatchParameters to print params used in
thread group dispatch size heuristic when encoding kernel dispatch.
Related-To: NEO-6989
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-10-17 17:31:54 +02:00
af7bcbf99c
Revert "refactor: split CpuInaccessible MemoryPool types to Device and System"
...
This reverts commit 2e8cf5fdf5
2023-10-17 10:03:14 +02:00
0a787a0880
refactor: remove not used code
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-16 15:16:07 +02:00
8c6b936dac
fix: decanonize address passed to AubManager's freeMemory()
...
- the same address should be used for writeMemory() and freeMemory()
Related-To: NEO-2707
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-16 12:58:21 +02:00
2e8cf5fdf5
refactor: split CpuInaccessible MemoryPool types to Device and System
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-16 12:47:13 +02:00
30b066c40e
Revert "fix: synchronize host and device timers to avoid device timer overflow"
...
This reverts commit dae8c34f81
2023-10-16 11:16:23 +02:00
0592390e2b
refactor: print gmm compression settings
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-16 09:14:52 +02:00
57e8edc489
refactor: remove not needed code
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-16 08:51:29 +02:00
0b7e6d90a3
refactor: add ail context sync flag
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-15 15:10:13 +02:00
dae8c34f81
fix: synchronize host and device timers to avoid device timer overflow
...
Related-To: NEO-8394
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-13 17:40:45 +02:00
a3faf5dacc
feature: Add support for ARL-S
...
Related-To: NEO-8187
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-13 10:28:21 +02:00
06a02552ce
refactor: debug flag to override PAT index for given memory type
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-12 15:47:28 +02:00
a420e34b10
fix: explicitly remove assign operators when not needed
...
when class defines copy/move ctor then corresponding assign operator(s)
should be defined or deleted
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-12 10:25:15 +02:00
3fdcf049bf
fix: set default device hierarchy to composite for all platforms except xe hpc
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-12 10:09:50 +02:00
5c1d82349b
fix: set default Xe Hpc core device hierarchy to flat
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-11 16:18:14 +02:00
6e481535d0
fix: fix compilation issues when building with clang-16
...
Related-To: NEO-8284
Signed-off-by: Pawel Cieslak <pawel.cieslak@intel.com>
2023-10-11 15:08:01 +02:00
55585b1fd8
Revert "performance: Remove tlb flush on DG2"
...
This reverts commit 3ba8ca47b0
2023-10-11 11:02:41 +02:00
5558222337
fix: handle completion in OsAgnosticMemoryManager
...
- add pollForCompletion() for contexts that used allocation prior to
freeGraphicsMemory()
Related-To: NEO-2707
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-11 10:24:30 +02:00
af275ed341
fix: handle failure on set cache region
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-11 09:07:40 +02:00
bede264d0d
fix: add unrecoverable to avoid undefined behavior
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-11 08:41:44 +02:00
dcbf147a52
Revert "fix: add fallback in setting hw ip version for MTL"
...
This reverts commit 2a5691f340
2023-10-11 05:37:11 +02:00
dee5ecfdf3
fix: ReturnSubDevicesAsApiDevices flag being ignored
...
Proper subdevice count being returned now in GfxCoreHelper
path, as previous method ignored the usage of the
ReturnSubDevicesAsApiDevices flag.
Related-To: LOCI-4859
Signed-off-by: Latif, Raiyan <raiyan.latif@intel.com>
2023-10-10 17:05:00 +02:00
c7287f9feb
fix: populate map of indices using push_back methods
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 15:50:27 +02:00
420f273a6c
fix: don't wait on condition in unit tests
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 15:14:30 +02:00
3ba8ca47b0
performance: Remove tlb flush on DG2
...
Resolves: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-10-10 14:36:12 +02:00
f26f027ee7
performance: limit monitor fence dispatch only to task count dispatches
...
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-10 14:02:18 +02:00
a7bdd6ee0a
fix: add early skip for negative file descriptor in Drm::discoverDevices
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 10:57:19 +02:00
a31dd7b454
fix: add unrecoverable to avoid out of bound access
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 10:45:30 +02:00
d76145ee65
refactor: correct printf formats
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 10:40:55 +02:00
91aa7fb2fe
refactor: print allocation info to stdout if flag is set
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-10-10 10:22:28 +02:00
2a5691f340
fix: add fallback in setting hw ip version for MTL
...
setup hw ip version based on device id and revision id
Related-To: NEO-8231
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 09:03:44 +02:00
92a2d6df27
feature: add bindless addressing support query to releaseHelper
...
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-09 16:42:56 +02:00
099a3f30e3
fix: add FileDescriptor class to ensure file descriptor is closed
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-09 16:23:28 +02:00
c2d69e5857
feature: allocate SPECIAL_SSH heap in front window from EXTERNAL heap
...
- SPECIAL_SSH is used for debug surface SurfaceState which must be
located at bindless offset zero
- limit size of external front window
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-09 14:54:39 +02:00
8b4242eb32
refactor: move setting GpuBaseAddress to mapGpu call
...
- set base address of heap after mapping allocation to gpu va
- ensures the same heapIndex is used while choosing heap range and
setting base
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-09 12:21:23 +02:00
50b2262339
fix: stop direct submission blocking on platform destruction
...
Resolves: GSD-6341
Signed-off-by: Venevtsev, Igor <igor.venevtsev@intel.com>
2023-10-06 17:03:38 +02:00
85eafc9e61
fix: query drm info to aligned storages
...
xe topology info to byte aligned storage
xe engine info to 2 byte aligned storage
system info to 4 byte aligned storage
all other info to 8 byte aligned storage
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 16:11:40 +02:00
fd7c750cf7
fix: ensure local variable address is not exposed outside of function
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 15:59:16 +02:00
ece03e6bbf
fix: add checks to avoid invalid behavior
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 15:45:33 +02:00
0c8a514349
fix: Switch default device hierarchy to FLAT
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2023-10-06 15:24:50 +02:00
6eeb9322b9
refactor: remove not needed method
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 15:22:40 +02:00
2ab4aeda85
fix: add static casts to destination type to avoid overflows in multiplication
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 14:55:24 +02:00
83c306e927
fix: avoid memory leak
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 13:16:56 +02:00
08e92d154f
fix: Add getDefaultDeviceHierarchy call to GfxCoreHelper
...
Added getDefaultDeviceHierarchy call that describes default device
hierarchy for a gfx core. Refactored L0 and OCL paths to use this
value by default and override this value when user sets
ZE_FLAT_DEVICE_HIERARCHY environment variable or
ReturnSubDevicesAsApiDevices debug key.
Updated ReturnSubDevicesAsApiDevices to force COMPOSITE device hierarchy
when set to 0.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2023-10-06 12:32:41 +02:00
9134a4e1bc
fix: call heapFree with gpu address for front window allocations
...
- when heapAllocate is used to get gpu address, heapFree should be
called on memory free
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-05 16:40:35 +02:00
382fc952f2
refactor: add NonAssignableClass to define classes without assign operator
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 15:16:58 +02:00
712ba60452
fix: add unrecoverable to avoid nullptr access
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 13:20:21 +02:00
72182c28e9
refactor: add NonCopyableOrMovableClass to classes that don't need copy ctors
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 13:11:01 +02:00
038c287656
fix: avoid double free when wddm initialization fails
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 13:03:49 +02:00
90e24a433d
Revert "performance: Change thread group dispatch size algorithm"
...
This reverts commit ac7cd9c4c5
2023-10-05 12:32:09 +02:00
e676ac49bb
fix: front window allocations in device pool with correct gpu address
...
- use correct FRONT_WINDOW heap address when flag use32BitFrontWindow is
set while allocating from Device Pool
- applies to Windows OS
Related-To: NEO-4550, NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-10-05 12:19:20 +02:00
6d259ac4b7
fix: add unrecoverable to avoid out of bound access
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 12:03:28 +02:00
d5f90ae155
Revert "fix: query drm info to 8 byte aligned storage"
...
This reverts commit 9b344280d6
2023-10-05 06:07:27 +02:00
ffab8fd9cc
fix: add concurrent atomic access with KMD migration
...
Related-To: NEO-8219
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2023-10-05 03:13:22 +02:00
ad2701ad26
fix: add unrecoverable to avoid out of bound access
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 15:59:18 +02:00
95eb5df978
refactor: use reference in for-range loops
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 15:32:26 +02:00
ec9fa23b2e
refactor: change order of fields of EncodeDispatchKernelArgs structure
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-04 15:00:29 +02:00
fc508212de
refactor: pass big parameters as reference instead of by value
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 14:53:13 +02:00
6b3ad5b3e3
fix: add unrecoverable in case of nullptr
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 14:38:05 +02:00
747d44f8fc
fix: add unrecoverable in case of allocation type unknown
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 14:02:36 +02:00
8042df8bb4
Revert "fix: support alignments in device and shared memory allocation on WSL2"
...
This reverts commit dd46bf1e90
2023-10-04 02:25:25 +02:00
dd46bf1e90
fix: support alignments in device and shared memory allocation on WSL2
...
Related-To: LOCI-4334
Signed-off-by: Lu, Wenbin <wenbin.lu@intel.com>
2023-10-03 19:22:23 +02:00
ac7cd9c4c5
performance: Change thread group dispatch size algorithm
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2023-10-03 19:04:22 +02:00
895a586083
refactor: use reference in for-range loops
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 18:56:53 +02:00
9b344280d6
fix: query drm info to 8 byte aligned storage
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 18:43:53 +02:00
8a01619310
refactor: Enable CSR heap sharing on Older Generation platforms
...
Related-To: LOCI-4312
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-10-03 18:19:50 +02:00
5e4ea627f7
refactor: correct printf formats
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 18:14:20 +02:00
d7d577ba48
feature: enable cl_cache by default on Windows
...
Related-To: NEO-8092
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-03 16:57:10 +02:00
110164a52a
fix: remove invalid std::forward
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 16:41:41 +02:00
1f1af5bb36
refactor: windows cl_cache eviction mechanism
...
Refactored eviction mechanism works as follows:
- eviction is needed only if
total size of cache binaries + size of the new binary exceed cache limit
- single evition call removes files with a summed size of 1/3 of the cache limit
- if new binary can not fit in the cache size limit
even after eviction, it will not be saved
- cache limit applies only to
files in cache directory with .cl_cache/.l0_cache extension.
Only these files are counted and only these files are removed
Related-To: NEO-8092
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-03 16:20:28 +02:00
8fa0b90f35
Revert "fix: query drm info to 8 byte aligned storage"
...
This reverts commit d0e615820c
2023-10-03 15:41:11 +02:00
5a018385aa
feature: Add BCS engine as internal engine for dg1
...
Related-To: NEO-9033
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-10-03 14:39:31 +02:00
0a99384936
fix: set flushed task count for all cases of post sync task count operations
...
- set monitor fence dispatch for all cases task count post sync operation
- stand alone flush task count will not happen when already flushed and so
monitor fence
- monitor fence then must be dispatched together with task count post sync
Related-To: NEO-8395
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-03 12:31:45 +02:00
d0e615820c
fix: query drm info to 8 byte aligned storage
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 11:13:38 +02:00
7531ced0e3
refactor: remove not needed error handling for make_unique
...
make_unique does not return empty object on failure
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 10:56:15 +02:00
1963ea69e5
fix: add missing member initializations
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 08:41:46 +02:00
0461af492d
fix: unify path for getting number of grfs per thread
...
Related-To: NEO-8043
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2023-10-03 08:17:46 +02:00
9337911742
fix: add self-assign check in operator=
...
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 08:09:16 +02:00
7c80f49176
fix: refactor Windows cl_cache and add extra safety layers
...
What's changed:
- Add early return when open existing config
fails due to different error than `ERROR_FILE_NOT_FOUND`
- Swich `ReadFileEx` to `ReadFile`
- Add `SetFilePointer` to make sure we're reading
from the beginning of the file
- Pass `overlapped` to `WriteFile` to make sure
we're writing from the beginning of the file
Related-To: NEO-8092
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2023-10-02 19:04:14 +02:00
d27d81f206
fix: dispatch monitor fence when stalling command dispatched
...
Resolves: NEO-9034
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-10-02 16:47:02 +02:00
56f05303c9
feature: add support for zeMemGet/SetAtomicAccessAttributeExp
...
Resolves: NEO-8219
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2023-10-02 15:59:17 +02:00
1ac37d4a49
Revert "refactor: Enable CSR heap sharing on Older Generation platforms"
...
This reverts commit 58ff9c6d94
2023-10-02 15:13:23 +02:00
cb903cbc03
refactor: Move disableRcs to releaseHelper
...
Related-To: NEO-8296
Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
2023-09-29 14:19:02 +02:00
8da92f56c7
refactor: code cleanup
...
- remove not needed branch and message
Signed-off-by: Hoppe, Mateusz <mateusz.hoppe@intel.com>
2023-09-29 13:40:51 +02:00
5c565efe28
feature: bindless global heap with debugger
...
- program debugSurface's SurfaceState at the beginning of Bindless Surface
State Heap - SPECIAL_SSH
- ensure SPECIAL_SSH is resident
Related-To: NEO-7063
Signed-off-by: Hoppe, Mateusz <mateusz.hoppe@intel.com>
2023-09-29 13:13:46 +02:00
ae90fd9e57
refactor: remove dead code
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-29 12:23:22 +02:00
a033df33ff
fix: remove preferSmallWorkgroupSizeForKernel method
...
Related-To: HSD-18033866078
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-29 11:55:09 +02:00
58ff9c6d94
refactor: Enable CSR heap sharing on Older Generation platforms
...
Related-To: LOCI-4312
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-09-29 11:54:51 +02:00
b2a8fa6e57
performance: allocate cmd buffer by umd on mtl
...
Default allocation by kmd is slower, this improves enqueue times.
Related-To: NEO-8152
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-09-29 11:30:56 +02:00
0f2a04fef4
feature: linux support for global ssh heap
...
Related-To: NEO-7063
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-09-29 11:18:01 +02:00
c5f5f60f8d
feature: cross CmdList and Event in-order data sharing [1/n]
...
Related-To: NEO-7966
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-09-29 11:14:18 +02:00
7d356795f0
fix: ensure memory placement key does not apply to unknown alloc type
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-28 08:43:30 +02:00
3a21b3b228
refactor: remove not needed code
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-28 07:52:39 +02:00
5f846d8a13
refactor: remove not needed code
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 18:17:04 +02:00
2a78a00855
fix: correct passing string in populateArgMetadata
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 18:00:33 +02:00
03874b8815
refactor: remove not needed code
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 17:45:54 +02:00
027551724e
fix: override value of MaxDualSubSlicesSupported when equal 0
...
when kmd is not set value of MaxDualSubSlicesSupported
then set it as half of MaxSubSlicesSupported
Related-To: NEO-8397
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-09-27 17:37:24 +02:00
4e8600d8d0
feature: initial support for RelaxedOrdering of in-order Events chaining
...
Disabled by default.
Related-To: NEO-7966
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-09-27 16:45:20 +02:00
5dc56c221f
refactor: remove not needed function
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 14:44:56 +02:00
09044dfbaa
refactor: remove not needed code
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 14:35:49 +02:00
60c30a05e7
refactor: remove not needed function
...
Related-To: NEO-7527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-27 14:15:11 +02:00
e71db368db
fix: use proper pointer inside appendWriteGlobalTimestamp
...
Resolves: NEO-8105
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2023-09-27 14:00:37 +02:00
3ceafa2259
fix: remove setting debug flags for ioctl helper xe
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-26 15:42:52 +02:00
160303924d
refactor: Correct logic for SIMD1
...
- For calculating number of threads per workgroup, for SIMD 1, return
local work size (each software thread should be mapped into a whole hardware
thread).
- Correct logic of calculating space for per thread data for SIMD 1.
- Minor: unit tests refactor.
- Corrected naming.
Related-To: NEO-8261
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2023-09-26 15:28:37 +02:00
65337482ff
Revert "feature: enable cl_cache by default on Windows"
...
This reverts commit e16220dc9f
2023-09-26 15:06:34 +02:00
eebf2bbd26
performance(ocl): timestamp packet count per gfx
...
Add support for different timestamp packet counts per gfx family.
Change all packet counts to 1 except for xe-hpc.
Related-To: NEO-8154
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2023-09-25 20:34:58 +02:00
Fabian Zwolinski