intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-30 01:35:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
17,385 Commits 42 Branches 655 Tags
2b48599c38dccbfe405e86f13ca23d6a4bd36daa
Commit Graph

2839 Commits

Author SHA1 Message Date
Bartosz Dunajski
2b48599c38 feature: enable standalone profiling allocation for CB events 2 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-30 14:57:44 +02:00
Bartosz Dunajski
f02b518674 fix: improve CB event completion writes 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-30 13:12:58 +02:00
Compute-Runtime-Validation
a58e42ef8c Revert "feature: enable standalone profiling allocation for CB events" 
This reverts commit f3b266f7b8.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-09-28 07:51:22 +02:00
Bartosz Dunajski
a7ff04e28f performance: dont pull host allocation each time in the loop 2 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-27 14:39:12 +02:00
Bartosz Dunajski
f3b266f7b8 feature: enable standalone profiling allocation for CB events 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-27 12:59:09 +02:00
Mateusz Jablonski
340a4906a1 fix: fix compilation issues with clang18 
- pass aligned memory to std::map::find and std::map::erase functions
- use EXPECT_EQ_VAL when comparing potentially misaligned memory

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-09-27 09:54:54 +02:00
Bartosz Dunajski
17c27c94e4 performance: dont pull host allocation each time in the loop 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-26 20:04:11 +02:00
Bartosz Dunajski
17a2b36a87 fix: allocation information from standalone profiling CB event 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-26 18:35:06 +02:00
John Falkowski
1d51f4b91c feature: Add driver-experimental API for retrieval of kernel binary program data 
Related-To: NEO-11651

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2024-09-25 20:38:17 +02:00
Damian Tomczak
98b1f8b1fa feature: stateless appendPageFaultCopy 
Related-to: NEO-11859

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
 2024-09-25 11:13:16 +02:00
Damian Tomczak
4d68f1de43 refactor: stateless unification for l0 
Related-to: NEO-11859

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
 2024-09-25 10:01:50 +02:00
Compute-Runtime-Validation
5dddd4a67f Revert "feature: Add experimental API for retrieval of kernel binary program ... 
This reverts commit 24682e702b.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-09-25 10:01:36 +02:00
Bartosz Dunajski
2618f586fa fix: copy offload mmio programming 
Related-To: NEO-12771

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-24 19:37:58 +02:00
Compute-Runtime-Validation
abcb462ac3 Revert "performance: optimize memory used for scratch programming" 
This reverts commit 9b2696a942.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-09-24 06:52:19 +02:00
John Falkowski
24682e702b feature: Add experimental API for retrieval of kernel binary program data 
Related-To: NEO-11651

Signed-off-by: John Falkowski <john.falkowski@intel.com>
 2024-09-24 02:48:29 +02:00
Bartosz Dunajski
65cc393638 feature: allow for dispatching work without event pool allocation 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-23 16:34:03 +02:00
Bartosz Dunajski
5a72d93c31 fix: skip not initialized csr when downloading for tbx 
Related-To: HSD-18040094854

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-23 16:23:11 +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
Mateusz Hoppe
9b2696a942 performance: optimize memory used for scratch programming 
- reserve exact number of slots for scratch surface states in surface
state heaps
- do not use offsets for contexts depending on engine type executing
cmdlists

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-09-23 14:15:47 +02:00
Jitendra Sharma
ac52a2ff5b feature: Before resuming the thread unlock them 
Related-To: NEO-7988
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
 2024-09-21 09:25:12 +02:00
Bartosz Dunajski
d7ce841081 fix: InOrderExecInfo upload to tbx 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-20 16:03:09 +02:00
Bartosz Dunajski
08f57c0fd4 refactor: get correct profiling allocation from event 
Related-To: NEO-11925

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-20 15:07:58 +02:00
Maciej Bielski
1ccc208bc3 fix: avoid null pointer dereference 
Related-To: NEO-12651

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2024-09-20 12:38:31 +02:00
Mateusz Hoppe
4a068c8eab fix: correclty program StateBaseAddress in global bindless mode 
- prepare bindful ssh when kernel requires ssh heap and
SurfaceStateBaseAddress
- remove lastAppendedKernelBindlesMode - local ssh heap may be needed
for bindless kernels with scratch or misaligned buffer args
- use ssh heap gpu address to program SurfaceStateBaseAddress, global base is
used for BindlessSurfaceState and DynamicState

Related-To: NEO-7063

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-09-20 11:57:05 +02:00
Bartosz Dunajski
2cb057a610 fix: download tbx allocations from all csrs 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-19 17:01:55 +02:00
Damian Tomczak
5c9fc079b0 fix: use stateless kernel when append memory fill on XeHpc and later 
Related-to: NEO-6075

Signed-off-by: Damian Tomczak <damian.tomczak@intel.com>
 2024-09-19 17:01:40 +02:00
Zbigniew Zdanowicz
672d8414f5 fix: remove not needed macro 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-09-19 17:01:17 +02:00
Maciej Bielski
cb62e31828 fix: avoid null pointer dereference 
Related-To: NEO-12651

Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2024-09-19 14:23:57 +02:00
Joshua Santosh Ranjan
6d86d562b5 refactor: move metric driver experimental apis to shared location 
modify driver experimental extensions according to guideline

Related-To: NEO-12530

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
 2024-09-18 20:46:33 +02:00
Bartosz Dunajski
7a56424c2c fix: program partition offset for secondary csr 
Related-To: HSD-18039998563

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-18 17:04:57 +02:00
Filip Hazubski
ebc19b4a70 feature: Add logic to disable bindless addressing via AIL 
Add mockable Device functions to get ReleaseHelper and AILConfiguration.

Resolves: NEO-12699

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2024-09-18 13:49:51 +02:00
Fabian Zwoliński
a6ddb61a5f fix: consider only misaligned buffers in getSurfaceStateHeapDataSize 
Adding checking for the presence of implicit args
was only a workaround for the time of implementing
support for bindless `const_base`, `global_base` in IGC.

Related-To: NEO-9855, NEO-7063
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
 2024-09-18 13:13:02 +02:00
Bartosz Dunajski
b8fb16c603 fix: initialize kernel members at the beginning 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-18 11:13:35 +02:00
Dominik Dabek
731cebd721 fix: trim device usm pools when alloc fails 
When normal allocation fails trim pools before deferred frees.

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2024-09-17 10:30:18 +02:00
Artur Harasimiuk
20a028f64b refactor: remove legacy code 
Related-To: NEO-6683
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2024-09-17 09:32:57 +02:00
Artur Harasimiuk
73382b9b6c refactor: remove legacy code 
Related-To: NEO-6683
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2024-09-16 19:04:13 +02:00
Mateusz Jablonski
d5812f49d7 refactor: remove not needed vme builtin related code 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-09-16 15:27:49 +02:00
Zbigniew Zdanowicz
7e00590994 performance: get work group count per tile value when setting new group size 
- change interface to function to accept external group size

Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-09-16 10:45:01 +02:00
Zbigniew Zdanowicz
fd4a744650 refactor: add command list engine group type and local dispatch getters 
Related-To: NEO-12639

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2024-09-16 10:08:16 +02:00
Aravind Gopalakrishnan
f5b88f085a feature: Update L0 Core release version to v1.6 
Related-To: NEO-12628

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
 2024-09-13 19:09:26 +02:00
Mateusz Hoppe
7cd9a2aa60 refactor: change name of variable 
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2024-09-13 03:06:44 +02:00
Compute-Runtime-Validation
e6079cdf24 Revert "feature: Update L0 Core release version to v1.6" 
This reverts commit 4eefd9eef7.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-09-13 02:33:53 +02:00
Aravind Gopalakrishnan
4eefd9eef7 feature: Update L0 Core release version to v1.6 
Related-To: NEO-12628

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
 2024-09-12 18:58:22 +02:00
Bartosz Dunajski
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
Aravind Gopalakrishnan
2a6faa64de feature: Append recorded commandlist into immediate (6/N) 
- fix premature call to make non resident

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
 2024-09-11 07:41:15 +02:00
Bartosz Dunajski
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
Dominik Dabek
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
Bartosz Dunajski
4f1262645b refactor: pass extra walker params 
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
 2024-09-10 15:30:03 +02:00
Filip Hazubski
beaddb55e0 fix: Minor code changes 
Remove needless checks for module and cmdList.
Add explicit check for surfaceState in setArgImageWithMipLevel.
Explicitly initialize WddmResidencyController::csr.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2024-09-10 13:31:15 +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