3f646839ca
fix: usm reuse cleaning unused allocations
...
mechanism for freeing allocations saved for reuse that have not been
used in a given time
Related-To: NEO-13425
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2025-01-21 14:23:19 +01:00
3d3c5ddf9f
feature: Submission for GlobalTimestamp as default
...
Related-To: NEO-11908
Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2025-01-18 01:27:24 +01:00
3d247d75ec
feature: disable page fault handler on migration
...
Disabled RegisterPageFaultHandlerOnMigration by default
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2025-01-16 23:42:09 +01:00
2dd9940f60
Revert "fix: count active modules for enabling per-dispatch private memory"
...
This reverts commit a483b361f9
2025-01-15 15:03:37 +01:00
ca72dff1ab
feature: Add missing pipelined EU thread arbitration on Xe3
...
Related-To: NEO-13682
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2025-01-15 08:24:43 +01:00
a483b361f9
fix: count active modules for enabling per-dispatch private memory
...
Related-To: NEO-13086
Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2025-01-10 15:03:34 +01:00
7f9fadc314
fix: regression caused by tbx fault mngr
...
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.
Recursive locking of mutex caused deadlock.
To fix, separate tbx fault data from base
cpu fault data, allowing separate mutexes
for each, eliminating recursive locks on
the same mutex.
By separating, we also help ensure that tbx-related
changes don't affect the original cpu fault manager code
paths.
As an added safe guard preventing critical regressions
and avoiding another auto-revert, the tbx fault manager
is hidden behind a new debug flag which is disabled by default.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
2025-01-09 07:48:53 +01:00
bb1a125f0c
feature: add support for Panther Lake platform
...
Related-To: NEO-12803
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2025-01-07 11:39:56 +01:00
b83db7ee32
Revert "feature: disable page fault handler on migration"
...
This reverts commit a258c9b010
2024-12-31 03:57:02 +01:00
a258c9b010
feature: disable page fault handler on migration
...
Disabled RegisterPageFaultHandlerOnMigration by default
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-12-30 09:42:52 +01:00
83ebbb01d3
performance: Add flag to mitigate host visible signal in CB events
...
Related-To: NEO-13441
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-12-24 12:35:55 +01:00
593a6c54ea
feature: add debug flag to ignore product specific ioctl helper creation
...
Related-To: NEO-13527
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-12-18 13:52:30 +01:00
ae394d815c
refactor: fix typo
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-12-18 10:21:48 +01:00
105a586615
feature: Enable Tile64 Optimization Flag
...
Related-To: NEO-12134
Signed-off-by: Andrzej Koska <andrzej.koska@intel.com>
2024-12-16 11:09:26 +01:00
c19df80bd8
feature: add key to force GPU status check in event synchronization
...
Related-To: GSD-10187
Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2024-12-12 22:24:36 +01:00
8cf4804fcd
fix: Overhead in zeDeviceGetGlobalTimestamps
...
Related-To: NEO-11908
There is overhead when submission method is used for
zeDeviceGetGlobalTimestamps. This fixes it.
Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2024-12-12 08:54:19 +01:00
f2725f217e
refactor: Introduce debug flags to manipulate event's signal visibility
...
-Add AbortHostSyncOnNonHostVisibleEvent which abort when waiting for non
host visible event from host
-Add ForceHostSignalScope which forces add or clear of host scope to
event's signal scope
Related-To: NEO-13441
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-12-11 14:07:43 +01:00
eca3d5a677
feature: debug flag to clear timestamp before submission
...
Related-To: HSD-18040896547
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-12-11 13:56:49 +01:00
37e81d2a11
feature: new heuristic to enable relaxed ordering 2
...
Related-To: NEO-13431
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2024-12-09 11:58:42 +01:00
0b7367ed5f
refactor: Update STATE_BASE_ADDRESS
...
Refactors the STATE_BASE_ADDRESS to align with the latest specification.
Removes redundant functionality for multiple GPU partial writes and
atomics.
Related-To: NEO-13147
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
2024-12-09 08:50:59 +01:00
af8ad3aa7a
Revert "feature: new heuristic to enable relaxed ordering"
...
This reverts commit 526f9c5e81
2024-12-08 16:01:32 +01:00
526f9c5e81
feature: new heuristic to enable relaxed ordering
...
Related-To: GSD-10308
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-12-06 17:04:39 +01:00
ab2e831a4a
fix: zeDeviceGetGlobalTimestamp to use submisison
...
Related-To: GSD-10253, GSD-9467, GSD-9381, NEO-11908
When EnableGlobalTimestampViaSubmission is set then
zeDeviceGetGlobalTimestamp uses immediate cmd submission
method to get GPU time.
Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
2024-12-04 19:10:07 +01:00
99a353a15a
feature: flags for logging indirect detection
...
Add flag to log information for indirect detection debugging.
Add flag to disable indirect detection by kernel name.
Add flag to force indirect detection enable/disable for CM kernels.
Related-To: NEO-13372
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-11-29 16:37:47 +01:00
4ad8c17db9
feature: add debug flags for timestamps
...
PrintCalculatedTimestamps - print ts in level zero paths
PrintTimestampPacketContents - add logging also to level zero paths
ForceUseOnlyGlobalTimestamps - force using a global ts
Related-To: HSD-14023527252
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-11-21 11:28:08 +01:00
ed20069d47
feature: debug flag to override region count
...
Related-To: HSD-18040537404
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-11-19 16:46:43 +01:00
608c1d30c5
feature: add support for release helper 30.0/30.1
...
Related-To: NEO-12803
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-11-13 10:51:39 +01:00
d294d71f95
feature: make programmable metrics enabled by default
...
Related-To: NEO-13011
Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
2024-11-13 09:42:23 +01:00
0a12817664
performance: flag, force zero copy for host ptr
...
When debug flag ForceZeroCopyForUseHostPtr is set, add
CL_MEM_FORCE_HOST_MEMORY_INTEL flag to buffers created with
CL_MEM_USE_HOST_PTR.
This makes the buffers use zero copy.
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-11-12 15:43:17 +01:00
c65b45471b
feature: support binary compatibility across multiple HW targets
...
- EnableCompatibilityMode flag added
- validateTergetDevice func modified to take into account the flag
Related-To: NEO-11568
Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
2024-11-04 16:53:57 +01:00
1f6eaf2525
refactor: Add debug flags to set PATs for dc flush mitigation
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-10-29 21:12:59 +01:00
1c46ed9b40
feature: enable reservation from SVM range by default
...
Related-To: NEO-11981
Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2024-10-24 20:01:18 +02:00
b51be4e2dd
refactor: fix description of debug variables
...
Fix description of debug variable DebugUmdInterruptTimeout
and DebugUmdMaxReadWriteRetry.
Related-To: NEO-13046
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-10-24 09:35:57 +02:00
c9e48d0d2b
refactor: support oa programmable metric group
...
Related-To: NEO-12184
Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
2024-10-24 08:35:12 +02:00
5f908ce092
feature: adding support for custom compiler backends
...
This adds abbility to load different versions of the backend
compiler based on underlying device.
Related-To: NEO-12747
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2024-10-23 19:55:36 +02:00
9d76158c1f
feature: debug flag to change ULLS BCS timeout
...
Related-To: HSD-18040119232
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-10-23 18:18:42 +02:00
e687e11ab1
performance: Add CCS Optimization
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-10-23 11:35:57 +02:00
171f1e27a3
fix: Add debug variables for configurable timeouts in debugger
...
Related-To: NEO-13046
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-10-23 10:30:03 +02:00
a8a40d2afd
feature: support SVM heap in reserveVirtualMem
...
Related-To: NEO-11981
Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
2024-10-22 16:47:14 +02:00
01a0b8e7f7
performance: improve ULLS controller timeout detection
...
Related-To: NEO-12991
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-10-22 13:53:25 +02:00
e10998db45
Revert "performance: Add CCS Optimization"
...
This reverts commit e7b3a40aa7
2024-10-22 05:52:14 +02:00
18d828421d
performance: add debug flag to control huge chunk size on wddm.
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-10-21 16:51:03 +02:00
a5a11f4a0e
feature: add debug key to set MaxSubSlicesSupported
...
Related-To: HSD-16025421624
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
2024-10-21 13:34:43 +02:00
e7b3a40aa7
performance: Add CCS Optimization
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-10-21 09:59:14 +02:00
26709ba124
fix: Implement polling of SW FIFO
...
Related-To: NEO-12955
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-10-21 07:19:42 +02:00
5463ddea06
feature: New forward-compatibility model for zeinfo
...
Up till now, NEO ignored uknown attributes in zeinfo
which could lead to undefined behavior. With this change
NEO will emit an error whenever an unknown attribute is
encountered.
Note : old behavior can be restored using new
IgnoreZebinUnknownAttributes debug environment variable
Resolves: NEO-11762
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2024-10-17 14:03:01 +02:00
2098e64dc1
Revert "feature: adding support for custom compiler backends"
...
This reverts commit 8098bcc48d
2024-10-16 02:07:25 +02:00
8098bcc48d
feature: adding support for custom compiler backends
...
This adds abbility to load different versions of the backend
compiler based on underlying device.
Related-To: NEO-12747
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2024-10-14 18:23:11 +02:00
7f2b806413
fix: Override timestamp width from KMD
...
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-10-14 13:38:33 +02:00
6b40f9bc5a
refactor: engineInstancedType removed
...
Related-To: NEO-12594
Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
2024-10-09 16:30:48 +02:00
6ddb550e05
feature: improve metrics debug messages
...
Resolves: NEO-12640
Signed-off-by: Matias Cabral <matias.a.cabral@intel.com>
2024-10-07 17:58:41 +02:00
cb3463db05
fix: update description of debug env
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-10-03 10:10:33 +02:00
0564a41919
feature: debug flag to control direct submission semaphore mode
...
Related-To: HSD-18039521047
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-10-02 21:06:53 +02:00
72cf384c7d
refactor: Fix typo
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-10-01 09:31:02 +02:00
4f96b6132f
Revert "feature: capture multiple cpu pagefault handler"
...
This reverts commit 4b3a6e9cfe
2024-09-28 07:53:30 +02:00
4b3a6e9cfe
feature: capture multiple cpu pagefault handler
...
Recorded multiple page fault handlers by using vector in
cpu_page_fault_manager_linux.
Added a static handlerIndex in order to track the depth of
handler logic to call appropriate previous handlers.
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-09-27 00:34:45 +02:00
29bd2763f1
refactor: Move debug key to correct category
...
Related-To: NEO-11817
Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
2024-09-12 12:49:40 +02:00
487b02a2ac
feature: debug flag to disable walker split during copy operations
...
Related-To: NEO-12607
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-09-11 16:44:16 +02:00
9bdd7b784a
fix: remove not needed cooperative kernel checks
...
Related-To: HSD-18039871488
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-09-10 18:32:20 +02:00
b2fc7345cf
performance: redesign usm alloc reuse mechanism
...
Dedicated pools for different allocations size ranges.
Additional reused allocations will create their own pools.
Do not reuse allocations >256MB.
Related-To: NEO-6893, NEO-12299, NEO-12349
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-09-10 18:12:14 +02:00
5569ebbe1f
Revert "feature: capture multiple cpu pagefault handler"
...
This reverts commit 44f2912195
2024-09-03 05:18:26 +02:00
44f2912195
feature: capture multiple cpu pagefault handler
...
Recorded multiple page fault handlers by using vector in
cpu_page_fault_manager_linux.
Added a static handlerIndex in order to track the depth of
handler logic to call appropriate previous handlers.
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2024-09-02 16:46:35 +02:00
ce3cb71773
performance: add debug flag to control timestamp caching
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-08-30 16:32:06 +02:00
656788e6c1
fix: Remove UC PAT override for shared images on LNL
...
Resolves: NEO-12326
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-08-26 10:24:10 +02:00
ef2ae9e1b7
Revert "feature: New forward-compatibility model for zeinfo"
...
This reverts commit f1815f941d
2024-08-21 00:27:42 +02:00
f1815f941d
feature: New forward-compatibility model for zeinfo
...
Up till now, NEO ignored uknown attributes in zeinfo
which could lead to undefined behavior. With this change
NEO will emit an error whenever an unknown attribute is
encountered.
Note : old behavior can be restored using new
IgnoreZebinUnknownAttributes debug environment variable
Resolves: NEO-11762
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
2024-08-20 23:08:04 +02:00
85a42162f8
refactor: debug flag to print DirectSubmission semaphore usage
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-08-16 13:10:34 +02:00
d4c1631ac7
performance: don't wait for paging fence on user thread
...
Related-To: NEO-12197
Currently for new resources user thread must wait before submitting
actual workload. With this commit, instead of waiting on user thread,
request is sent to background ULLS controller thread and additional
semaphore is programmed. ULLS controller will perform actual wait
and signal semaphore when paging fence reaches required value.
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-08-07 08:30:51 +02:00
ec34656e0e
fix: debug flag to defer first device submission
...
Related-To: HSD-18039343751
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-08-02 09:31:25 +02:00
d2546d4062
refactor: add forceComputeWalkerPostSyncFlushWithWrite function
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-07-26 15:00:46 +02:00
3758e99cbf
feature: initial support for standalone CB Events Timestamps allocator
...
Related-To: NEO-11925
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-07-22 10:13:55 +02:00
153cda9a9f
feature: add debug flag to force gmm system memory resource type
...
Related-To: NEO-10157
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-07-18 14:05:16 +02:00
c0a92c87b7
fix: Override UC PAT to cacheable for shared images on LNL
...
Temporary WA for UC PAT index in GMM from shared image
Add flag to control WA
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-07-18 12:08:42 +02:00
61e08ef4ff
performance: add debug flag to allow non zero for compressed
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-07-16 12:46:10 +02:00
05eb4e7a0d
performance: add debug flag to disable l1 flush
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-07-11 10:09:46 +02:00
778645c11e
feature: add initial support for Xe2 platforms
...
Related-To: NEO-8188, NEO-10774
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-07-09 10:30:27 +02:00
a14d5c52cb
fix: Extend scope of OverrideSlmSize debug key - apply key during initialization
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-07-05 18:03:45 +02:00
4f4b8fed15
refactor: remove not needed code related to deprecated device ip version
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-07-05 09:54:48 +02:00
0db66bb708
feature: add new flag to StateComputeModeProperties
...
Related-To: NEO-8188, NEO-10774
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-07-03 14:05:02 +02:00
6992cb8aeb
fix: Add experimental debug toggle to force 2M local memory size alignment
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2024-06-27 15:21:35 +02:00
6d70304e7b
refactor: debug flag to override num HP contexts
...
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-25 16:46:16 +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
cd3219d092
feature: add debug key to set vmBind userFence wait timeout
...
- VmBindWaitUserFenceTimeout
Related-To: NEO-11219
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-06-19 15:01:30 +02:00
d97dccc409
refactor: rename MaximumNumberOfThreads debug key
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-19 13:06:42 +02:00
0e29ab8387
performance: add debug key to control cpu cacheablitiy
...
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
2024-06-19 12:34:06 +02:00
f05ff9b156
refactor: rename OverDispatchControl debug key
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-18 18:59:43 +02:00
c40f0f2421
refactor: rename ComputeOverdispatchDisable debug key
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-17 13:18:29 +02:00
3f45e40684
feature: add debug flag for forcing sip kernel class
...
Related-To: NEO-8188, NEO-10774
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-06-14 17:34:33 +02:00
0cb48901dc
refactor: add AUBDumpCaptureDirPath debug flag
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-06-13 14:17:50 +02:00
d79e3947d1
fix: fix debug variables descriptions
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2024-06-13 12:49:44 +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
844b29d17c
feature: debug flag to disable l0 debugger
...
Related-To: HSD-18037823909
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-06-03 16:12:01 +02:00
38d7e02c28
refactor: remove not needed code
...
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
2024-05-29 13:24:02 +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
8217b76cef
refactor: Add key to not register pagefault handler on migration
...
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-05-28 08:45:34 +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
913d5dc3b1
feature: create secondary contexts for different engine types
...
Related-To: NEO-7824
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-05-24 15:14:24 +02:00
294c3b77ba
refactor: add level zero console logging for kernel buffer arguments
...
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-05-23 11:01:38 +02:00
cb9977b8f4
feature: create copy offload queue under debug flag
...
Related-To: NEO-11376
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-05-17 11:04:35 +02:00
Dominik Dabek