Media
/
compute-runtime
mirror of https://github.com/intel/compute-runtime.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
11,768 Commits 35 Branches 603 Tags 163 MiB
Commit Graph

58 Commits

Author SHA1 Message Date
Szymon Morek 3281dea1fe Allow debug allocs to use copyMemoryToAllocation 
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
 2022-11-14 17:50:32 +01:00
Neil R Spruit ada9b5d4a9 Handle if L0 Event Memory is Shareable 
- Properly check for IPC event handle flag to determine if the event
pool memory is sharable between processes.
- Given Host Visible Event Pool, a check is done to determine if the
Host memory can be shared between the processes.
- Enabled handling if Event Host Memory is shareable for DRM
- If Event Pool Memory is Not shareable, then retrieving the IPC Event
Pool Handle returns unsupported.

Signed-off-by: Neil R Spruit <neil.r.spruit@intel.com>
 2022-08-05 00:11:05 +02:00
Kamil Kopryk d4d54f5093 Cleanup includes 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2022-07-25 09:58:38 +02:00
Krzysztof Gibala 77dde01503 Pass canonized gpuAddress in setCpuPtrAndGpuAddress 
Related-To: NEO-6523
Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
 2022-06-07 10:05:18 +02:00
Krzysztof Gibala 81899c4477 Add canonized gpuAddress to GraphicsAllocation constructor 
Related-To: NEO-6523
Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
 2022-06-06 18:17:36 +02:00
Krzysztof Gibala dc1fe7d59a Change MemoryPool to enum class 
Use enum class for MemoryPool in GraphicsAllocation
This change will ensure that GA is constructed in the proper way

- Rename namespace for isSystemMemoryPool method
- Add method getMemoryPoolString for logging actual pool which is in used
- Remove wrong pattern in GraphicsAllocation constructor

Related-To: NEO-6523
Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
 2022-06-02 12:46:15 +02:00
Jaime Arteaga 325db6a99c Fix P2P support for implicit scaling 
when using implicit scaling, 2 dma-buf handles, one per tile, are
needed to support dma access from peer.

Related-To: LOCI-3122

Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
 2022-06-01 20:10:32 +02:00
Krzysztof Gibala ae56d50b4f Pass canonized gpuAddress to GraphicsAllocation 
Related-To: NEO-6523

Signed-off-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
 2022-05-30 16:54:38 +02:00
Mateusz Jablonski d935815d74 Move residency data from WddmAllocation to GraphicsAllocation 
Related-To: NEO-6848

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2022-05-10 18:16:42 +02:00
Jaime Arteaga 3f26f45c10 Add support for IPC handles with implicit scaling 
When using implicit scaling, device allocations may have
more than one internal allocation created internally. In that case,
a separate dma-buf handle per internal allocation needs to be
exported.

So introduced two driver experimental extensions to export and
import more than one IPC handle:

- zexMemGetIpcHandles
- zexMemOpenIpcHandles

Related-To: LOCI-2919

Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
 2022-05-09 00:38:17 +02:00
Maciej Plewka 0a16dc6c47 Fix multi thread usage of external host alloc 
This is fixed reupload of this commit after auto revert
With this commit OpenCL will track if external host memory is used from
few threads and will secure to update task count in all threads before
destroing allocation.

Resolves: NEO-6807

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-05-05 13:32:15 +02:00
Compute-Runtime-Validation 00a1a14652 Revert "Fix multi thread usage of external host alloc" 
This reverts commit 54eee2a88b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2022-04-28 17:42:07 +02:00
Maciej Plewka 54eee2a88b Fix multi thread usage of external host alloc 
With this commit OpenCL will track if external host memory is used from
few threads and will secure to update task count in all threads before
destroing allocation.

Resolves: NEO-6807

Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2022-04-26 15:31:24 +02:00
Mateusz Hoppe c9d61840a2 Allocate SBA buffers per HW context 
- different physical storage for every HW context
- adds support for debugging with implicit scaling on
- reorganize tests

Relates-To: NEO-6883

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2022-04-15 10:01:28 +02:00
Bartosz Dunajski 4b0d986876 Move AllocationType enum out of GraphicsAllocation class 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2022-02-04 17:49:09 +01:00
Katarzyna Cencelewska 45d23868de Remove device enqueue part 15 
- remove DEVICE_QUEUE_BUFFER

Related-To: NEO-6559
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2022-02-03 16:19:07 +01:00
Milczarek, Slawomir 2be98a1e62 Create kmd migrated allocation with initial placement 
Implements ZE_HOST_MEM_ALLOC_FLAG_BIAS_INITIAL_PLACEMENT
for zeMemAllocShared with KMD migrated allocation.

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
 2022-02-01 15:42:10 +01:00
Bartosz Dunajski dfdd3c597a Remove redundant BUFFER_COMPRESSED allocation type 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-12-07 13:35:49 +01:00
Bartosz Dunajski 55959d4d1d Helper method to check if allocation is compressed 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-12-02 16:13:53 +01:00
Artur Harasimiuk d2a29ce458 DrmBO: canonize GPU addresses 
Related-To: NEO-6364
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2021-10-21 18:25:48 +02:00
Kamil Diedrich 465bec3d76 Add NTHandle sharing 
Signed-off-by: Kamil Diedrich <kamil.diedrich@intel.com>
 2021-10-19 14:17:25 +02:00
Mateusz Jablonski 0d74ab8ae8 Correct allocating event pool in device memory 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-10-13 17:36:46 +02:00
Lukasz Jobczyk 7392b5fb8d Add new colouring policy 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2021-10-07 23:33:26 +02:00
Jaime Arteaga 5c236a62fd Changes to SW tags 
Add SW tags to synchronization points
Add ID sequence numbers
Add new allocation type

Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
 2021-08-18 01:51:37 +02:00
Bartosz Dunajski c7a936d1f4 Add memory banks to Simulated CSR 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-07-05 12:19:58 +02:00
Bartosz Dunajski 96d14967ac Partial support for XE_HP_SDV 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2021-06-24 18:35:54 +02:00
Mateusz Jablonski b50a6bec82 Correct isBlitCopyRequiredForLocalMemory 
detect not lockable allocation based on gmm flag
Related-To: NEO-5733

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-20 13:17:49 +02:00
lgotszal 3bd4bca911 Copyright header update 
Dates corrected in copyright headers to reflect original publication date
(2018 for OpenCL, 2020 for Level Zero).

Signed-off-by: lgotszal <lukasz.gotszald@intel.com>
 2021-05-17 20:38:19 +02:00
Mateusz Jablonski fcbf1dcf32 Mark SVM_GPU allocation as not lockable 
require blitter usage if allocation is not lockable and in local memory

Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 17:47:15 +02:00
Mateusz Jablonski a552d1fd65 Revert "Mark SVM_GPU allocation as not lockable" 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 12:24:02 +02:00
Mateusz Jablonski a79f7b678b Mark SVM_GPU allocation as not lockable 
require blitter usage if allocation is not lockable and in local memory

Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-05-12 09:49:35 +02:00
Konstanty Misiak c4502ccf66 Fix OCL MOCS index with UNCACHED flag 
Related-To: NEO-5742

Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
 2021-05-04 10:01:44 +02:00
Compute-Runtime-Validation c453e7fe8b Revert "Mark SVM_GPU allocation as not lockable" 
This reverts commit 5341d0663c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-04-29 18:06:38 +02:00
Mateusz Jablonski 5341d0663c Mark SVM_GPU allocation as not lockable 
use blitter if available and allocation is not lockable

Related-To: NEO-5733

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-29 15:55:13 +02:00
Mateusz Jablonski de116aac5c Make buffer allocations not lockable 
Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-29 11:27:44 +02:00
Mateusz Jablonski 2b956651a7 Mark Shared resource copy allocations as lockable 
Related-To: NEO-5733
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-19 11:16:34 +02:00
Mateusz Jablonski 9026362b76 Add GraphicsAllocation::isLockable method 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-15 12:14:03 +02:00
Compute-Runtime-Validation c9b5de0f1d Revert "Add GraphicsAllocation::isLockable method" 
This reverts commit 48d40ad850.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2021-04-15 07:58:35 +02:00
Mateusz Jablonski 48d40ad850 Add GraphicsAllocation::isLockable method 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2021-04-14 16:12:51 +02:00
Jaime Arteaga ddca333045 Improve support for L0 uncached device allocations 
Make sure UNCACHED flags are translated into setting the MOCS index
for uncaching L3.

Related-To: NEO-5500

Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
 2021-04-08 13:00:03 +02:00
Mateusz Hoppe 86a234ead6 Allocate debug area together with isa 
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2021-03-26 09:31:44 +01:00
Slawomir Milczarek 693f2ff384 Ensure shared handle be closed once on Linux 
Related-To: NEO-5644

Signed-off-by: Slawomir Milczarek <slawomir.milczarek@intel.com>
 2021-03-18 18:38:01 +01:00
Zbigniew Zdanowicz 24b928303b Rename fields in AllocationProperties 
Related-To: NEO-5498

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-03-02 18:32:37 +01:00
Zbigniew Zdanowicz 3e4be8d78e Add new allocation type 
Related-To: NEO-5244

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2021-02-26 12:57:12 +01:00
Maciej Dziuban f7d105f2e2 Create work partition allocation 
Related-To: NEO-5546
Resolves: NEO-5561
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
 2021-02-17 15:28:42 +01:00
Mateusz Hoppe 0f42ef1ed7 Differentiate between users ISA and internal ISA allocation 
Related-To: NEO-5240

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-11-16 13:16:30 +01:00
Lukasz Jobczyk 045632f355 Add new unified shared memory model 
Related-To: NEO-3312

Change-Id: I640fb8d120729fa8bb2a23ff65c74c41ef27260d
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2020-11-02 19:23:40 +01:00
Mateusz Hoppe 4623cb3f85 Create module debug area allocation 
Related-To: NEO-4550

Change-Id: I1aa151134cb51a7d4f578de3b08cdd51aefc58f2
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-10-16 11:21:39 +02:00
Mateusz Jablonski 6870104a1a Pass maxOsContextCount to GraphicsAllocation 
Change-Id: I4f327866433fe9b0cc0a6191336b54a9d2282702
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2020-08-26 09:57:15 +02:00
Bartosz Dunajski 1544453f24 Fix dumping allocations when BCS copy is allowed 
Change-Id: I0d56e0d2e8007e7dc1686fab0e40502b658c254e
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2020-07-10 16:53:47 +02:00