e08668b982
refactor: remove not needed code.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-03-07 13:02:29 +01:00
fe377b6597
feature: add out cmd pointer to store data imm encoder
...
Related-To: NEO-10385
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-03-07 12:52:08 +01:00
79d80047ef
refactor: improve mmap logging logic
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-03-07 12:15:39 +01:00
a22cefdaed
fix: don't program dummy blit when no copy command was programmed
...
Related-To: NEO-9996, NEO-10571
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-07 09:01:16 +01:00
660539fe4e
refactor: remove not needed code.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-03-06 20:13:57 +01:00
debbf87671
fix: move ARL-U device id to MTL-M release
...
Related-To: NEO-10404
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-06 17:33:00 +01:00
033ff28609
performance: enable cmd buffer preallocate xehp+
...
For L0 immediate cmdlists try to use reusable allocations if available.
Related-To: NEO-10526
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-03-06 16:53:01 +01:00
8ae4a3bc7a
fix: pass Sku/Wa tables for gmm without additional translations on Windows
...
Related-To: NEO-10623
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-06 14:58:58 +01:00
fcd57f94cf
refactor: capability to print mmap and munmap calls
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-03-06 14:29:01 +01:00
7a0d2df2fe
fix: Handle Pat Index Ext not supported on Xe
...
Xe does not support VmBindPatIndexExtension. This patch
fixes the handling of this case and prevents corrupting
other extensions
Related-to: NEO-9674
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-03-06 11:18:31 +01:00
d25026b263
refactor: Add getTotalMemBankSize function to ReleaseHelper
...
Minor refactor of ULTs to not use hard coded banks size.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-03-06 09:53:56 +01:00
a04c67ec52
performance(ocl): refactor pool allocators tests
...
add explicit tests for xe hpc
Related-To: NEO-9700
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-03-05 18:48:55 +01:00
8b4bca89bc
refactor: move ray tracing support capability to release helper
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-05 17:30:57 +01:00
5f7e56e78b
refactor: Unify aub config generation
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-03-05 11:09:34 +01:00
293858320e
Revert "performance: Fill reusable allocation list on xe and later"
...
This reverts commit 15934ceb43
2024-03-02 07:09:45 +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
51ae76a25f
refactor: improve handling of in-order atomic signaling
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-03-01 15:59:25 +01:00
bd6925d51a
refactor: Exclude thread dispatch algorithm for overdispatch to function
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-01 15:04:04 +01:00
a8fbed6120
feature: enable dummy blit WA for PVC
...
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-01 14:04:46 +01:00
ea2ad550a1
refactor: improve handling duplicated in-order host storage
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-03-01 13:54:28 +01:00
80aa55a3cb
fix: don't program dummy blit prior to MI_FLUSH_DW without postsync
...
add missing dummy blits before MI_FLUSH_DW with postsync
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-03-01 12:36:13 +01:00
6751d19c19
fix: decanonize pointer to match GPU heap address space
...
* `zeVirtualMemReserve` `pStart` address may be passed in a canonizated form.
Resolves: NEO-10086
Signed-off-by: Kozlowski, Marek <marek.kozlowski@intel.com>
2024-03-01 12:18:11 +01:00
bbe1043f08
feature: initial support for pooling in-order counter allocations
...
Related-To: NEO-10507
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-03-01 12:08:02 +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
15934ceb43
performance: Fill reusable allocation list on xe and later
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-03-01 09:41:19 +01:00
5fce046877
Revert "fix: don't program dummy blit prior to MI_FLUSH_DW without postsync"
...
This reverts commit d796fb559d
2024-03-01 01:43:35 +01:00
e5db84f370
performance: Use GEMCreateExt when allocate by KMD
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-29 18:01:55 +01:00
409e19a832
performance: Enable cmd buffer preallocation per CmdQ on xe and later
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-29 17:41:58 +01:00
00964275fb
fix: create preemption allocation for Root Csr
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-29 16:46:24 +01:00
06e9c7f79f
Revert "fix: Add ATS-M device id"
...
This reverts commit 588921ed9b
2024-02-29 14:34:40 +01:00
d796fb559d
fix: don't program dummy blit prior to MI_FLUSH_DW without postsync
...
add missing dummy blits before MI_FLUSH_DW with postsync
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-29 13:30:09 +01:00
a27dafd2e1
fix: cl_cache store binary and debug data in one file
...
Related-To: NEO-10045
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-02-29 10:13:15 +01:00
676644bc50
performance: Enable internal heap preallocation on xe and later
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-28 17:58:52 +01:00
39a44628a3
performance: Enable timestamp wait for queues on xe and later
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-28 14:26:59 +01:00
d1dd34d0c7
performance: Enable timestamp wait for events on xe and later
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-28 14:18:14 +01:00
64232ec370
fix: choose proper csr for low priority immediate command lists
...
Resolves: NEO-10168
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-02-28 12:45:02 +01:00
588921ed9b
fix: Add ATS-M device id
...
Add device id 0x56C2
Signed-off-by: Hazubski, Filip <filip.hazubski@intel.com>
2024-02-28 11:46:55 +01:00
ffecca86ac
feature: brand string update
...
Related-To: NEO-7929
Updating device brand strings
Based on public support in Windows driver 31.0.101.5252
https://www.intel.com/content/www/us/en/download/785597/
Signed-off-by: ocldev <ocldev@intel.com>
2024-02-28 10:52:27 +01:00
bf9805b0bb
fix: override reset_stat IOCTL macro for prelim
...
Modified to return DRM_IOCTL_I915_GET_RESET_STATS of prelim headers
as the macro values used for non-prelim is different from the prelim
value due to sizeof() embedded in _IOWR()
Related-To: GSD-5673
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-02-28 10:09:27 +01:00
fa4b737326
feature: Implement metadata attaching for vm_bind in xe
...
Related-to: NEO-9674
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-02-28 01:36:20 +01:00
8483a922a7
feature: simplify in-order allocation overflow
...
Related-To: NEO-10507
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-27 18:25:26 +01:00
219470f60d
build: remove static_assert for drm header change
...
Removed static_assert for reset_stats before updating
drm header to v2.0-r23.
Related-To: GSD-5673
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-02-27 17:42:01 +01:00
b6b53daa3f
fix: don't program dummy blit prior to MI ARB CHECK
...
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-27 15:46:46 +01:00
9f01a831a2
fix: correct command for dummy blit on PVC
...
use MEM_SET command
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-27 14:27:47 +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
9cbc33e23d
fix: setup correct render/display core family for gmmlib initialization
...
pass values got from adapter info
Related-To: NEO-10482
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-26 14:49:04 +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
459da6a482
refactor: cleanup xe hpg logic related to dummy blit wa
...
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-26 13:32:18 +01:00
3e65e7bdba
fix: correct number of max work group count for concurrent kernel on PVC
...
for single-CCS mode use all EUs
Related-To: NEO-8377
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-26 10:42:50 +01:00
7729eb8127
refactor: move flush task submission to a function
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-23 18:11:57 +01:00
6cdd2d5dca
fix: add missing gt_id when creating XE context
...
Related-To: GSD-8046
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-23 16:50:32 +01:00
1995e6aa40
feature: store cpu pointer of command buffer pointing to post sync command
...
Related-To: NEO-10064
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-02-23 13:12:15 +01:00
55f2b31f2a
refactor: adjust device page fault state print
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-23 12:50:40 +01:00
ef2d3b538b
performance: move timestampPacketTagBuffer to local memory
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
Resolves: NEO-7765
2024-02-23 09:55:48 +01:00
10d610d163
refactor: move process barrier with post sync to a function
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-23 09:32:48 +01:00
01a721df3e
refactor: move preparing flush task batch buffer to a function
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-23 09:18:58 +01:00
0fa730e524
build: Update debugger uapi headers to latest
...
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-02-22 16:07:06 +01:00
a4ed483238
refactor: move update task count and completion stamp to function
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-22 14:56:25 +01:00
7b689aa464
refactor: move handle batched dispatch implicit flush code to function
...
Related-To: NEO-7824
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-22 14:56:10 +01:00
d795a66f81
fix: Add new DG1 and RPL-S device IDs
...
Added DG1 device ID: 0x4909
Added RPL-S device ID: 0x468B
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-02-21 13:58:05 +01:00
b44729771c
fix: Extend MTL's overridePatIndex to XE LPG
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-21 13:21:30 +01:00
964f0166d7
fix: Reuse freed chunk from left even if not aligned
...
Related-To: NEO-10416, NEO-10418, NEO-10437
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-02-21 12:31:54 +01:00
db9d0c9a58
fix: remove heap resource leak after command list reset
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-02-20 14:38:19 +01:00
915b19b0be
refactor: remove not needed debug_break_if
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-19 16:28:58 +01:00
27f4eab52f
fix: restore previous order of variables
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
Resolves: NEO-10439
2024-02-19 14:13:54 +01:00
f31c88d05f
fix: size estimation for tlb flush before copy
...
Related-To: HSD-18036669673
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-19 13:35:35 +01:00
07639401c5
performance: enable pat index, mtl linux
...
Enable programming pat indexes on mtl linux by default.
Related-To: NEO-7896
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-16 18:31:21 +01:00
0120d8a58d
performance: program pat index on mtl linux
...
Enable programming pat indexes on mtl linux for device buffers.
Change DrmMemoryManager::allocateMemoryByKMD to use gemCreateExt.
Set mmap flags based on coherency.
Map as write back on legacy and coherent.
On non-coherent map as write combined.
Changes currently disabled, to enable use debug keys:
DisableGemCreateExtSetPat=0
UseGemCreateExtInAllocateMemoryByKMD=1
Reorder BufferObject to decrease padding.
Related-To: NEO-7896
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-16 17:33:07 +01:00
be7b80746b
fix: update incorrect debug_break
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-16 16:55:59 +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
cc1732c930
performance: make resident before lock
...
Resolves: NEO-10369
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-16 12:00:38 +01:00
4d159bd06c
Revert "performance: make resident before lock"
...
This reverts commit 7e7fac01e3
2024-02-16 09:23:49 +01:00
ed011de03e
performance: program pat index on mtl linux
...
Enable programming pat indexes on mtl linux for device buffers.
Change DrmMemoryManager::allocateMemoryByKMD to use gemCreateExt.
Changes currently disabled, can be enabled with flag
DisableGemCreateExtSetPat=0
Related-To: NEO-7896
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-15 17:15:28 +01:00
405e9d220a
fix: Add RPL device ids
...
Add device IDs: 0xA7AA, 0xA7AB, 0xA7AC, 0xA7AD.
Resolves: NEO-8274
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-02-15 12:34:47 +01:00
7e7fac01e3
performance: make resident before lock
...
Resolves: NEO-10369
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-15 11:56:36 +01:00
25b3a3dbfa
fix: user proper settings for caches.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-02-15 11:38:34 +01:00
b58717b9e3
feature: Add support for legacy acronyms in ocloc's fatbinary
...
Expands support for deprecated acronyms to fatbinary. Previously,
these were allowed only in single-target builds.
Related-To: NEO-10190
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2024-02-15 10:14:49 +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
d22b2a8a38
Revert "feature: add support for the cl_khr_extended_bit_ops extension"
...
This reverts commit 6dec2143df
2024-02-15 05:34:10 +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
7b340775c6
Revert "performance: program pat index on mtl linux"
...
This reverts commit 8e0b23db84
2024-02-15 02:06:03 +01:00
88c5872682
feature: debug flag to flush tlb before copy
...
Related-To: HSD-18036669673
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-14 20:05:57 +01:00
8e0b23db84
performance: program pat index on mtl linux
...
Enable programming pat indexes on mtl linux for device buffers.
Change DrmMemoryManager::allocateMemoryByKMD to use gemCreateExt.
Related-To: NEO-7896
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-14 18:42:04 +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
6dec2143df
feature: add support for the cl_khr_extended_bit_ops extension
...
Related-To: NEO-10337
Signed-off-by: Ben Ashbaugh <ben.ashbaugh@intel.com>
2024-02-14 09:11:44 +01:00
233f898b59
fix: split freed chunk from right
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-10280
2024-02-13 16:14:39 +01:00
bb5f6d9660
fix: don't query vm bind support on i915 prelim for pre-Xe platforms
...
Related-To: HSD-18036843571
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-09 12:50:48 +01:00
ea7ae7564f
feature: Implement read/writeGpuMemory for Xe debugger
...
- makes prelim read/writeGpuMemory generic
- Implements Xe specific ioctls and fsyncs
- Refactors dbg IoctlHelper to use shared base class
for Xe and i915
Related-to: NEO-9668
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-02-08 22:09:59 +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
5e562ae7b0
fix: store the correct pagesize in SvmAllocationData
...
Also use the same alignment for both CPU & GPU in shared USM
Related-To: GSD-7103, NEO-9812
Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2024-02-08 10:10:22 +01:00
2b91286754
fix: fix load store uint16x16 avx2 for unaligned ptr
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-08 09:35:30 +01:00
97ef964bc4
feature: Add keys to override sync mode for immediate command list
...
Added OverrideImmediateCmdListSynchronousMode to override synchronous
mode for immediate command list
Related-To: NEO-10316
Signed-off-by: Yoon, Young Jin <young.jin.yoon@intel.com>
2024-02-08 08:35:32 +01:00
0b64240deb
Revert "feature: enable dummy blit WA for PVC"
...
This reverts commit fb9d225495
2024-02-08 04:27:00 +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
ce17580b28
fix: Use Rcs engine in blender on DG2
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-02-07 18:21:54 +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
5717a726ff
fix: Allow free of zero sized allocation
...
Related-To: NEO-9236
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-02-07 17:04:11 +01:00
923707a509
feature: initial support for local dispatch size query
...
Related-To: NEO-8070
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-07 14:47:05 +01:00
999ec9b2ca
refactor: Unify logic for getting atomic FP caps 1/n
...
- Separate logic for fp16/32/46 caps.
- Add aggregated constexprs for local & global caps of given type
- Pass arguments by reference
- Add hwInfo as argument for future refactors
- Add static_asserts in L0 to ensure there is no mismatch between
internal/external caps
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-02-07 11:39:36 +01:00
f6ca565323
Revert "feature: enable use of waitpkg intrinsic"
...
This reverts commit 2d15517fbe
2024-02-06 16:30:26 +01:00
b4a2e243dc
performance: accept AOT kernels for indirects
...
Use indirects detection mechanism for AOT kernels if the detection
version is at least 2.
Related-To: NEO-7712
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-02-06 15:59:42 +01:00
eb0b0c2c89
refactor: add missing xe logs
...
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2024-02-06 13:03:46 +01:00
fb9d225495
feature: enable dummy blit WA for PVC
...
cleanup redundant implementation for DG2
Related-To: NEO-9996
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-06 10:17:12 +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
9b649c1582
Revert "feature: enable bindless mode in L0 on dg2"
...
This reverts commit fbb8c5a98d
2024-02-06 01:41:03 +01:00
f31fafb1e2
refactor: improve debug flag to override bcs mocs
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-02-05 20:23:54 +01:00
fbb8c5a98d
feature: enable bindless mode in L0 on dg2
...
Related-To: NEO-7063
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-02-05 09:48:16 +01:00
a4f7dda98f
refactor: Add xe print debug key
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-02-02 16:39:51 +01:00
e6ba9766bd
feature: add debug flags to force pat index
...
for cached recouces: OverridePatIndexForCachedTypes
for uncached resouces: OverridePatIndexForUncachedTypes
Related-To: NEO-10157
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-02-02 16:11:34 +01:00
27c089d60d
feature: Register ELF for xe debugger
...
Related-to: NEO-9674
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-02-02 09:19:19 +01:00
00b1f1c5b5
fix: set runalone mode in xe only for render and compute
...
Runalone mode in XE is supported only for RENDER and COMPUTE.
Related-To: NEO-9139
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-02-02 09:13:17 +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
2237961deb
performance: add macro for ULT-only unrecoverable if
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-02-01 15:09:31 +01:00
e311ba5597
refactor: Move ownership of engine type to caller of setDefaultEngine
...
Related-To: GSD-7097
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
2024-02-01 14:20:20 +01:00
e7b7eb06e4
Revert "fix: store the correct pagesize in SvmAllocationData"
...
This reverts commit a104d9199d
2024-02-01 05:00:45 +01:00
8ca9141019
fix: remove wa with override pat index on xe_lpg
...
Related-To: NEO-9657
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-31 16:30:12 +01:00
d0b009901c
fix: use proper gmm resource type for uncache resources
...
when new coherency model
Resolves: NEO-9657
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-31 15:26:11 +01:00
d920753ca6
fix: Disable related logic when EnableHostAllocationMemPolicy is not set
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-01-31 13:45:52 +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
a104d9199d
fix: store the correct pagesize in SvmAllocationData
...
Related-To: GSD-7103, NEO-9812
Signed-off-by: Lu, Wenbin <wenbin.lu@intel.com>
2024-01-31 09:12:20 +01:00
fb46066abc
Revert "fix: enable cache env variables for level-zero"
...
This reverts commit 743904d2df
2024-01-31 08:33:05 +01:00
cbe35d70a5
fix: initialize libnuma only when flag is set
...
Modified in memory_info.cpp to initialize libnuma only when
EnableHostAllocationMemPolicy is set.
Related-To: NEO-8276
Signed-off-by: Yoon, Young Jin <young.jin.yoon@intel.com>
2024-01-30 18:27:43 +01:00
564e0f0319
performance: Align host mem to 2MB when range is not limited
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-10217
2024-01-30 14:43:13 +01:00
278ced35dc
fix: Use capability table to determine engine type for defaultEngine
...
Related-To: GSD-7097
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
2024-01-30 14:28:09 +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
620ad5fa89
fix: change freed chunk size when ptr is aligned
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-9945
2024-01-30 12:22:28 +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
da16dad344
fix: don't limit vm bind support based on platform
...
Related-To: GSD-7097
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-29 19:43:15 +01:00
69c9cacd3e
feature: Enable ULLS on wddm 2.3
...
Related-To: NEO-4843
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-29 17:33:28 +01:00
58eaece6c9
fix: Make DirectSubmissionInsertExtraMiMemFenceCommands able to force fence
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-29 16:43:24 +01:00
c51b656d2c
fix: request instruction cache invalidation on module destroy
...
Invalidation is requested on both linux and windows,
on Csr's that used Isa allocation.
Related-To: NEO-10045
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-01-29 16:00:34 +01:00
64175d8bb6
feature: Add ULLS support for WDDM 2.3
...
Resolves: NEO-4843
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-29 15:45:43 +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
7728123907
fix: Do not use 2mb alignment for host ptr allocs
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-9945
2024-01-29 11:01:00 +01:00
4704cd49a3
fix: Remove fence handling when reuse cmd buffer
...
Resolves: NEO-10163
Related-To: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-29 09:08:19 +01:00
63a5b64c7e
Revert "fix: Remove fence handling when reuse cmd buffer"
...
This reverts commit f3bbd70a58
2024-01-27 08:28:57 +01:00
46fb73026e
fix: enable direct submission on release 1274
...
Related-To: NEO-8187
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-26 16:00:03 +01:00
eec01e500a
fix: non-coherency issue on arl
...
Resolves: HSD-15015200338
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-26 10:26:33 +01:00
f3bbd70a58
fix: Remove fence handling when reuse cmd buffer
...
Resolves: NEO-10163
Related-To: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-26 10:06:24 +01:00
7d6845f2aa
Revert "performance: Remove tlb flush on DG2 Linux"
...
This reverts commit 9215f3acb5
2024-01-26 07:13:22 +01:00
b4d2170a6d
fix: add missing gmm type to getUsageTypeString
...
Related-To: HSD-18031172224
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-25 14:12:31 +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
fdb5a53f85
fix: fix scratch programming in heapless mode l0
...
Related-To: NEO-10107
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-25 10:50:37 +01:00
9636c2f0d5
fix: Avoid double free when freeing sip kernels
...
Reset sipKernels unique_ptr when freeing
Related-to: NEO-8402
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-25 08:45:45 +01:00
a25eedb5ac
feature: add print of cpu flags and address size upon detection
...
Related-To: NEO-9737
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-24 11:03:30 +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
2d15517fbe
feature: enable use of waitpkg intrinsic
...
Related-To: NEO-9737
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-24 10:46:28 +01:00
548ecec7f8
feature: Implement debugger open IOCTL
...
Related-To: NEO-8405
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-01-24 09:50:39 +01:00
76de854a69
feature: Set Debug Attach Available for Xe
...
Related-to: NEO-8402
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-24 09:04:11 +01:00
dd7083d710
feature(zebin): add support for spill/private size in execution env
...
add fallback to previous logic based on zeinfo version
Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-23 17:26:43 +01:00
c0686da2d6
fix: update uapi eudebug headers
...
- Update uapi eudebug headers in third_party/uapi-eudebug/drm
to 67590b534a037466f83ae023f31c6186a53d9d86 from
https://gitlab.freedesktop.org/miku/kernel/-/tree/eudebug-dev-pub
Related-To: NEO-9139
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-01-23 16:39:56 +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
7bbe57c671
feature: add debug info for logging pat indexes
...
Related-To: HSD-18031172224
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-23 13:34:35 +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
6cf71cce81
refactor: Allow for grouping BCS1+ copy engines in more engine group types
...
Do not group copy engines from BCS1+ in linked copy group by default.
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-01-23 12:13:09 +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
09dcc618c1
fix: prefer compression when allocationg by kmd
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-01-22 16:38:17 +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
e5618c3207
refactor: reposition implicit scaling functions into more direct hierarchy
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-22 13:31:41 +01:00
6e27727090
fix: bump zeinfo decoder version to 1.38
...
Related-To: NEO-10041
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-22 12:47:21 +01:00
6f4ed10919
refactor: unify getMaxWorkGroupCount logic
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-22 11:16:45 +01:00
3a09ea3436
Revert "refactor: reduce batch buffer struct size"
...
This reverts commit 97ecf58577
2024-01-19 16:06:57 +01:00
134c718a25
fix: support zeEventPool IPC handles from single process
...
For all execution paths where needed, use `BufferObjectHandleWrapper`
instances for registration of BO-handles and try to obtain shared
ownership. This allows both sides of IPC communication to be implemented
in the same process and avoid the double-free problem on a BufferObject
of the same handle.
Currently there are two pairs of such calls:
* `zeEventPoolGetIpcHandle()` + `zeEventPoolOpenIpcHandle()`
* `zeMemGetIpcHandle()` + `zeMemOpenIpcHandle()`
The capability of executing both sides from the same process is useful
for testing but not only.
Related-To: NEO-9837
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2024-01-19 14:49:38 +01:00
b5f698e0c5
feature: add umonitor and umwait synchronization function
...
Related-To: NEO-9737
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-19 14:20:19 +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
93e941fd73
refactor: simplify engine mapping array
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-19 12:51:12 +01:00
d7d3a6b76d
fix: use full address to sip if needed
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-19 12:28:46 +01:00
028a5ee2fc
fix: correct calculating highest enabled dual subslice
...
when no DSS is exposed then calculate highest enabled subslice instead
Related-To: NEO-9614
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-19 10:48:15 +01:00
9c7578f5f4
fix: change numa_library to read default policy
...
Changed NumaLibrary to read default policy instead of using
the address-based policy, and remove unnecessary argument.
Removed numaif.h from the repo as it is no longer required.
Related-To: NEO-8276
Signed-off-by: Yoon, Young Jin <young.jin.yoon@intel.com>
2024-01-19 08:31:41 +01:00
a084b1cf42
fix: change numa library string for SLES
...
Modified libnuma.so.1 to be loaded instead of libnuma.so for
SLES compatibility
Related-To: NEO-8276
Signed-off-by: Yoon, Young Jin <young.jin.yoon@intel.com>
2024-01-19 08:22:17 +01:00
a673347378
fix: don't allocate preemption surface for BCS engines
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-19 07:59:24 +01:00
3a5e6c0117
fix: cl_intel_subgroup_split_matrix_multiply_accumulate support on PVC
...
Related-To: GSD-7696
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-18 19:40:59 +01:00
b533024b70
fix: Ensure correct evaluation order in gfx_partition.cpp
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-01-18 19:12:33 +01:00
f56eeb0eb7
fix: Use debug SIP when debugging is enabled
...
Disable wMTP when debug is enabled
Related-to: NEO-10085
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-18 18:58:16 +01:00
7fbf724c72
refactor: update Implicit Scaling interface
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-18 16:52:48 +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
af5977766d
performance: Push cmd buffer alloc to the front of reusable list
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-18 12:28:22 +01:00
c238f731af
fix: Skip mapping copy engines for unsupported ones
...
Based on the info retrieved from product helper, skip mapping returned
copy engines from KMD to disabled ones.
- Unify logic for EngineInfo ctors (remove redundant code).
Related-To: NEO-8356
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2024-01-18 09:49:14 +01:00
976d112188
performance: optimize copy in allocateDebugMetadata
...
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-18 08:07:02 +01:00
696be48cd4
refactor: add preemption xe only file to xehpg and xehpc sources
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-17 18:32:37 +01:00
d2eb29660d
performance: Refactor cmd buffer reuse for cmd lists
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-17 17:28:17 +01:00
ec40fdc382
fix: PVC dpas caps
...
Related-To: NEO-10083
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-17 16:28:57 +01:00
97ecf58577
refactor: reduce batch buffer struct size
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-17 14:04:00 +01:00
aa191b6f88
feature: Set runalone mode for contexts with online debugging
...
Related-To: NEO-9139
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-01-17 09:01:30 +01:00
f7dc17e6a2
fix: set mmapPtr in every allocation in multiGraphicAllocation
...
Related-To: GSD-7360
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
2024-01-16 15:18:44 +01:00
a28a2d305e
fix: align NEO code to new uAPI header
...
PMU is removed from XeKMD as it is likely to change in the future.
Related-To: NEO-8324
Co-authored-by: Francois Dugast <francois.dugast@intel.com>
Co-authored-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2024-01-16 13:36:32 +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
556645e0c5
fix: add unrecoverable to avoid OOB access
...
Related-To: NEO-9860
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-16 00:12:11 +01:00
9215f3acb5
performance: Remove tlb flush on DG2 Linux
...
Resolves: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-15 23:20:16 +01:00
10ef2a28ff
fix: correct for default hierachry
...
Resolves: NEO-10006
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2024-01-15 22:15:49 +01:00
7b40b01f54
feature: add debug key for toggling bit in 57bit GPU VA for specific allocations
...
Related-To: NEO-9419
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-01-15 19:37:00 +01:00
dfc69c746a
feature: create InOrderExecInfo for standalone CB Event
...
Related-To: NEO-8145
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-15 16:56:52 +01:00
cc1e3965ce
refactor: Improve builtins compilation
...
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-15 14:56:52 +01:00
b348eaf29f
fix: use required walk order
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-10014
2024-01-15 13:44:56 +01:00
997bdfa010
performance: add windows thread priority debug key
...
Set windows thread priority to "above normal" on wddm init if flag is
set.
Related-To: NEO-8215
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-01-15 08:14:46 +01:00
9b0c64abef
Revert "performance: Enable ULLS on WSL"
...
This reverts commit 42c2b6b0e2
2024-01-15 06:08:44 +01:00
37bfde9e4d
Revert "refactor: Improve builtins compilation"
...
This reverts commit 21bc398340
2024-01-13 05:10:20 +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
a972cdaa6b
fix: initialize device caps before creating engines
...
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-01-12 14:09:30 +01:00
a3bd629aff
fix: store image implicit args in bindless slot 1
...
bindless slot 0: image
bindless slot 1: image implicit args
bindless slot 2: redescribed image
Redescribed image moved one slot higher.
Separate allocation is created for new bindless slot.
Related-To: NEO-9740
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-01-12 13:09:06 +01:00
42c2b6b0e2
performance: Enable ULLS on WSL
...
Related-To: NEO-10037
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-12 12:03:53 +01:00
903e581b5f
fix: add support for bindless implicit args
...
Support for:
global_base and const_base in bindless addressing mode.
Related-To: NEO-9855
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2024-01-12 01:27:17 +01:00
2bda9f0b58
fix: Release usage when put cmd buffer to reusable list
...
Resolves: NEO-10004
Related-To: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-11 18:40:38 +01:00
21bc398340
refactor: Improve builtins compilation
...
Related-To: NEO-7621
- simplify logic
- correct names
- remove inconsistent foreach
foreach(GENERATED_BUILTINS_IMAGES ${GENERATED_BUILTINS_IMAGES})
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-11 15:20:01 +01:00
8dda7e3936
feature: adding device ids of 4 more DG2 variants
...
Related-To: NEO-9775
Signed-off-by: Dongwon Kim <dongwon.kim@intel.com>
2024-01-11 09:56:16 +01:00
ba0db2488a
refactor: Implement Xe Resoure Registration (2/x)
...
Refactor drm_debug.cpp into IoctlHelper
Related-to: NEO-9161
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-11 08:26:29 +01:00
d3baab00db
feature: Register resources for Xe at vm creation (1/x)
...
Add interfaces to IoctlHelperXe for registering resources.
Introduce new debug key EnableXeResourceRegistration to attach
resources to vm_create ioctl.
Related-to: NEO-9161
Signed-off-by: Brandon Yatse <brandon.yates@intel.com>
2024-01-11 08:15:50 +01:00
0aee72f1fc
refactor: disable instantiation-after-specialization clang warning
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-01-10 13:50:25 +01:00
eec553ea6a
fix: set ulls ring start state according to returned value from kmd call
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-01-10 12:57:34 +01:00
31edeb0765
feature: set HP flag when creating HardwareContextController
...
- for highPriority context
Related-To: NEO-7824
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-01-10 12:46:29 +01:00
5d2d3ed899
refactor: modify sip kernel helpers
...
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-01-09 17:09:10 +01:00
8df4dab1a3
Revert "performance: Remove tlb flush on DG2 Linux"
...
This reverts commit 44a162053b
2024-01-09 16:53:00 +01:00
6eb152b24b
feature: improve post sync system memory fence programming
...
Related-To: NEO-8210
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-09 11:55:25 +01:00
46d860b2bf
Revert "feature: Register resources for Xe at vm creation (1/x)"
...
This reverts commit e1fefd1974
2024-01-09 11:36:00 +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
e1fefd1974
feature: Register resources for Xe at vm creation (1/x)
...
Add interfaces to IoctlHelperXe for registering resources.
Introduce new debug key EnableXeResourceRegistration to attach
resources to vm_create ioctl.
Related-to: NEO-9161
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2024-01-08 13:36:24 +01:00
44a162053b
performance: Remove tlb flush on DG2 Linux
...
Resolves: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-08 12:39:19 +01:00
7b8abd8fff
fix: pass GMM to Drm::getPatIndex
...
Related-To: NEO-9543
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-08 09:14:14 +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
add394722c
fix: Create GMM in DrmMemoryManager::createAllocWithAlignment
...
Resolves: NEO-9739
Related-To: NEO-9543
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-05 13:17:11 +01:00
4ccae1dbb4
feature: support memory policy for GEM_CREATE
...
Modified ioctl_helper_prelim to support the extension of gem_create_ext,
i.e. prelim_drm_i915_gem_create_ext_mempolicy.
Added two debug variables to be used for the mempolicy extension.
Modified functions in memory_info and drm_memory_manager to support extension
Added numaif.h from https://github.com/numactl/numactl/tree/master ,
v2.0.14
Related-To: NEO-8276
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-01-04 23:49:10 +01:00
57900c5455
refactor: improve single slice dispatch mode handling
...
Related-To: NEO-8210
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-04 15:24:09 +01:00
3970f1bc4c
fix: create hwQueue when reinitialize osContext
...
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-9877
2024-01-04 12:46:36 +01:00
d472cf0a5d
fix: Restore handle fence completion when reusing cmd buffer
...
Related-To: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-01-04 12:11:39 +01:00
342bfcd17c
feature: disable dpas on release 12.61
...
Related-To: NEO-9736
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-01-03 13:27:41 +01:00
c3b6ca8011
Revert "fix: Restore handle fence completion when reusing cmd buffer"
...
This reverts commit 5d90818cce
2023-12-30 10:39:16 +01:00
87857a6558
feature: add new PVC device id
...
Related-To: NEO-9736
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-29 19:06:33 +01:00
edd6fd5e6c
performance: Optimize ULLS start on submit path
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-12-29 15:21:49 +01:00
5d90818cce
fix: Restore handle fence completion when reusing cmd buffer
...
Related-To: NEO-7116
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-12-29 11:38:36 +01:00
d7b6f11ced
refactor: improve creating 48b resources
...
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2023-12-29 10:05:42 +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
d8f6551b6b
refactor: move i915 ioctl helper to dedicated file
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-28 12:01:18 +01:00
72a999599f
refactor: remove i915 dependency from xe ioctl helper
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-28 09:29:27 +01:00
1d02f7fdd9
Revert "performance: Optimize ULLS start on submit path"
...
This reverts commit ea78831e28
2023-12-28 01:54:18 +01:00
1d9c29f9a9
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>
2023-12-27 22:59:54 +01:00
138f22f684
fix: correct calculation for chunking size
...
Resolves: NEO-9562
Signed-off-by: John Falkowski <john.falkowski@intel.com>
2023-12-27 16:27:09 +01:00
368070069e
refactor: remove intel_hwconfig_types file from third party
...
remove not needed querying of vs/hs/ds/ps/gs threads
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-12-27 15:32:23 +01:00
ea78831e28
performance: Optimize ULLS start on submit path
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2023-12-27 13:55:30 +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
4fa6368c01
fix: cast param to proper datatype width
...
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2023-12-27 09:23:19 +01:00
341a13ce8e
Revert "performance: Limit tlb flush WA scope on DG2 Linux"
...
This reverts commit fa181937a4
2023-12-24 08:17:39 +01:00
f2c9d7172a
Revert "fix: store image implicit args in bindless slot 1"
...
This reverts commit b6d572ddb8
2023-12-23 12:01:42 +01:00
Michal Mrozek