intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-22 10:17:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
18,882 Commits 42 Branches 655 Tags
35eae3f977caeef7baac48ced02e3b7a89251382
Commit Graph

443 Commits

Author SHA1 Message Date
Lukasz Jobczyk
35eae3f977 performance: Improve ULLS light residency management 
-skip bo::wait if completion fence not needed
-do not restart exec on evict

Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-03-24 17:48:55 +01:00
Szymon Morek
bb10290828 fix: make misaligned user memory 2-Way coherent 
Related-To: NEO-9004

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2025-03-21 17:56:37 +01:00
Lukasz Jobczyk
6cb52f71b4 fix: Avoid mutex deadlock when switch ulls light ring buffer 
Related-To: NEO-14406

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-03-19 11:47:40 +01:00
John Falkowski
4d281cf51d feature: Implement appendMemoryPrefetch for Shared System USM allocations 
Related-To: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2025-03-13 06:26:38 +01:00
Compute-Runtime-Validation
fa2e3adad3 Revert "feature: Implement appendMemoryPrefetch for Shared System USM Allocat... 
This reverts commit 97799b3faf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-03-12 05:55:32 +01:00
Compute-Runtime-Validation
0d5baa2c30 Revert "performance: Cache timestamps on CPU" 
This reverts commit 83637404bf.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-03-12 04:41:46 +01:00
Lukasz Jobczyk
83637404bf performance: Cache timestamps on CPU 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-03-11 13:40:18 +01:00
John Falkowski
97799b3faf feature: Implement appendMemoryPrefetch for Shared System USM Allocations 
Related-To: NEO-12989

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2025-03-11 09:12:48 +01:00
Fabian Zwoliński
f5e37e725c Revert "fix: configure ISA Pool params based on productHelper" 
This reverts commit bf20ae7ae8.

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2025-03-10 22:41:13 +01:00
Tomasz Biernacik
1aa418ec15 performance: override cacheable value passed to gmm on linux 
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
 2025-03-06 21:45:01 +01:00
Tomasz Biernacik
92512fdc64 fix: preserve allocation type for memory object 
Related-To: NEO-9421

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
 2025-03-05 14:48:57 +01:00
Fabian Zwoliński
bf20ae7ae8 fix: configure ISA Pool params based on productHelper 
When is2MBLocalMemAlignmentEnabled returns true,
increase pool size for builtins from 64k to 2MB.

Additionally, set appropriate alignment for kernel ISA heap allocations.
Additionally, configure isaAllocationPageSize based on productHelper

Related-To: NEO-12287
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2025-02-20 08:42:35 +01:00
Lukasz Jobczyk
051f7928f1 performance: tiny improvements for ULLS light 
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-02-17 23:52:33 +01:00
Lukasz Jobczyk
7cb7229c1c performance: Disable force pin for ULLS light 
Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-02-14 15:31:50 +01:00
Lukasz Jobczyk
9085f6aeca fix: drain gem close worker on csr destroy 
Resolves: HSD-18041493278

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-02-13 20:34:13 +01:00
Lukasz Jobczyk
bc2b49b958 feature: Introduce ULLS light 
Add core implementation of ULLS without VM_BIND interface aka ULLS
light.

Related-To: NEO-13922

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2025-02-12 17:52:02 +01:00
Chandio, Bibrak Qamar
7149743162 fix: Set vmbind user fence when makeMemoryResident 
Related-To: NEO-11977, GSD-10293

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
 2025-02-10 14:20:09 +01:00
Maciej Bielski
971b7c27a2 fix: enable usm compression on linux 
Related-To: NEO-12056
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-02-04 13:09:04 +01:00
Bellekallu Rajkiran
3bef9f886a fix: Crash on over memory allocation 
- Add defer backing flag to gem create ioctl
- Make memory resident before lock

Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
 2025-02-03 14:29:42 +01:00
Fabian Zwoliński
7e9c358a73 fix: apply 2MB alignment to large local memory image allocations 
In this patch, we align up the allocation size to 2MB for all
image allocations >= 2MB located in local memory.
2MB alignment support is defined by function:
`is2MBLocalMemAlignmentEnabled`

Related-To: NEO-12287

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2025-01-31 14:58:24 +01:00
Compute-Runtime-Validation
d23249b061 Revert "fix: Set vmbind user fence when makeMemoryResident" 
This reverts commit 80dc4fb43a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-31 11:36:29 +01:00
Fabian Zwoliński
7918b44a94 fix: apply 2MB alignment to large local memory allocations 
In this patch, we align up the allocation size to 2MB for all
allocations >= 2MB located in local memory.
2MB alignment support is defined by function:
`is2MBLocalMemAlignmentEnabled`

Related-To: NEO-12287

Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2025-01-30 22:09:39 +01:00
Chandio, Bibrak Qamar
80dc4fb43a fix: Set vmbind user fence when makeMemoryResident 
Related-To: NEO-11977, GSD-10293

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
 2025-01-28 22:04:37 +01:00
Compute-Runtime-Validation
83af0b77ff Revert "fix: Crash on over memory allocation" 
This reverts commit 212ccb8bd4.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-24 21:35:59 +01:00
Bellekallu Rajkiran
212ccb8bd4 fix: Crash on over memory allocation 
- Add defer backing flag to gem create ioctl
- Make memory resident before lock

Related-To: NEO-13403

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
 2025-01-24 14:01:37 +01:00
Maciej Bielski
e95c7aac92 fix: set memoryBanks correctly for single memory bank 
Resolves: HSD-18040585222

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-01-14 20:38:10 +01:00
Compute-Runtime-Validation
dc49d09e64 Revert "fix: set memoryBanks correctly for single memory bank" 
This reverts commit ec5477e3ee.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-11 01:56:37 +01:00
Maciej Bielski
ec5477e3ee fix: set memoryBanks correctly for single memory bank 
Resolves: HSD-18040585222

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2025-01-10 10:01:33 +01:00
Compute-Runtime-Validation
58707e0cf7 Revert "refactor: migration to std::make_unique C++17" 
This reverts commit 4cf685cb7d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2025-01-09 01:41:36 +01:00
Semenov Herman (Семенов Герман)
4cf685cb7d refactor: migration to std::make_unique C++17 
Signed-off-by: Semenov Herman (Семенов Герман) <GermanAizek@yandex.ru>
 2025-01-08 17:20:00 +01:00
Mateusz Hoppe
1110410caf fix: change emplace() on map to insert() 
- fixes problem with some compilers

Related-To: GSD-10365, GSD-10367, GSD-10441

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-12-18 17:51:22 +01:00
Slawomir Milczarek
3a6ce6dca9 feature: Improve ioctl helper function to synchronize userptr allocation 
Related-To: NEO-11817

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-12-18 17:40:27 +01:00
Filip Hazubski
a0cc124b2e performance: Pass RootDeviceIndicesContainer by reference 
Additionally pass std::map by reference in UsmMemAllocPoolsManager c-tor.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2024-12-17 14:18:30 +01:00
Mateusz Jablonski
49c028858a fix: optimize bind info in ioctl helper xe 
bind info container is needed to distinguish between userptr and handles
with this change it stores only userptrs and their corresponding gpu va

Related-To: NEO-13501
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-12-13 16:07:30 +01:00
Mateusz Hoppe
0589a70dc7 feature(sysman): reinitialize gfxPartition on reset 
Related-To: NEO-13203

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-12-12 16:27:25 +01:00
Slawomir Milczarek
edaac6ce43 feature: Add ioctl helper function to synchronize userptr allocations 
Related-To: NEO-12846

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-11-22 17:58:25 +01:00
Wenbin Lu
2ba80ce114 feature: support physical host memory 
Related-To: NEO-11981

Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
 2024-11-20 08:19:52 +01:00
Slawomir Milczarek
f005574f3e feature: ioctl helper for allocUserPtr in createAllocWithAlignmentFromUserptr 
Related-To: NEO-12846

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-11-19 18:13:46 +01:00
Slawomir Milczarek
8b7aa340ad feature: Add ioctl helper function to allocate user ptr 
Related-To: NEO-12846

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-11-15 22:10:29 +01:00
Slawomir Milczarek
d745f41a76 feature: Ioctl helper mmap/acquireGpuRange functions in creating usm allocation 
Related-To: NEO-12846

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-11-13 16:56:13 +01:00
Slawomir Milczarek
a331ffcb55 feature: Add ioctl helper functions to mmap/unmap and acquire/releaseGpuRange 
Related-To: NEO-11817

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2024-11-08 15:22:44 +01:00
Alicja Lukaszewicz
654fdc1345 feature: add query for additional device properties 
Related-To: NEO-12590

Signed-off-by: Alicja Lukaszewicz <alicja.lukaszewicz@intel.com>
 2024-10-29 20:40:27 +01:00
Wenbin Lu
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
Bartosz Dunajski
f430279d62 fix: change doorbell type 
Related-To: NEO-12870

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-10-14 14:58:11 +02:00
Compute-Runtime-Validation
41df1a6f47 Revert "feature: support SVM heap in reserveVirtualMem" 
This reverts commit bfaeeb01d6.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-10-03 14:53:50 +02:00
Dominik Dabek
ac8dcdb298 fix: do not unregister shared allocation 
Allocations imported from shared handle are not using registerAlloc in drm
manager but on free, unregister was called.

This could lead to problems with allocation size tracking.

This change will skip the unregisterAllocation call if allocation is
imported from shared handle.

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-10-02 16:32:24 +02:00
Maciej Plewka
80f75ceace fix: submit dummy exec to pin memory during zeContextMakeMemoryResident call 
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2024-09-23 14:43:59 +02:00
Chandio, Bibrak Qamar
27c7fbc611 feature: set error description in os_interface/linux 
Added setErrorDescription for drm_buffer_object, drm_memory_manager,
and ioctl_helper_prelim

Related-To: NEO-12456

Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
 2024-09-12 18:48:41 +02:00
Young Jin Yoon
675ec13439 fix: add rootDeviceIndex for BufferObjectHandleWrapper 
Modified sharedBoHandles to use the (boHandle, rootDeviceIndex) pair
as a key instead of boHandle, and added rootDeviceIndex variable in
the BufferObjectHandleWrapper class of drm_buffer_object.h.

Previously sharedBoHandles uses boHandle as a key. However, this will
not work with the system using multiple devices, because each devices
can return the same handle to refer different memory region.

Related-To: GSD-9024
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
 2024-09-10 19:27:19 +02:00
Wenbin Lu
bfaeeb01d6 feature: support SVM heap in reserveVirtualMem 
Related-To: NEO-11981

Signed-off-by: Wenbin Lu <wenbin.lu@intel.com>
 2024-09-09 23:22:04 +02:00