Commit Graph

474 Commits

Author SHA1 Message Date
Aravind Gopalakrishnan
acfeffe274 feature: Append recorded commandlist into immediate (8/N)
Add primary dispatch capability for immediate command list

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-12-20 18:52:33 +01:00
Compute-Runtime-Validation
f35d620e06 Revert "feature: Append recorded commandlist into immediate (8/N)"
This reverts commit d8d7419aee.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2024-12-20 03:35:27 +01:00
Aravind Gopalakrishnan
d8d7419aee feature: Append recorded commandlist into immediate (8/N)
Add primary dispatch capability for immediate command list

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-12-19 19:02:14 +01:00
Bartosz Dunajski
e8cfb38db4 performance: improve relaxed ordering task count tracking
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-12-18 11:36:22 +01:00
Maciej Plewka
8151224501 fix: add microsecond resolution for timeout
Related-To: NEO-13445
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2024-12-13 09:32:18 +01:00
Zbigniew Zdanowicz
75139d2322 fix: zero sync and region barrier buffers before use on regular command lists
Related-To: NEO-13350

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-12-06 15:54:50 +01:00
Mateusz Jablonski
fa58073095 refactor: remove not used usings/typedefs/variables
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-11-28 16:19:39 +01:00
Aravind Gopalakrishnan
c617048f1a fix: Enqueue blocking support for L0
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-10-19 10:28:48 +02:00
Artur Harasimiuk
00aedcaed4 refactor: add NOLINT for pending problems
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2024-10-10 11:46:35 +02:00
Wojciech Konior
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
Mateusz Jablonski
552930a75f fix: don't setup preemption surface when debugger is active
Related-To: NEO-12878
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-10-08 13:58:11 +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
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
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
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
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
Mateusz Jablonski
14fd9f3f24 fix: correct using L0 loader functions
use zelLoaderTranslateHandle for translating handle to internal handle
get pointer to zelSetDriverTeardown during global ctor
don't load loader library by name
get loader function pointers directly from current process

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-09-04 17:30:25 +02:00
Tomasz Biernacik
c5e174da00 refactor: remove queue extended methods and files
Related-To: NEO-12103

Signed-off-by: Tomasz Biernacik <tomasz.biernacik@intel.com>
2024-09-04 11:11:33 +02:00
Aravind Gopalakrishnan
20aa853369 feature: Append recorded commandlist into immediate (5/N)
- add support for heapless mode

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-08-30 09:23:59 +02:00
Mateusz Jablonski
dec502e11b fix: add magic identifier to L0 command queue object
add tests for toInternalType function

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2024-08-29 16:39:29 +02:00
Aravind Gopalakrishnan
a9cb7876a5 feature: Append recorded commandlist into immediate (4/N)
- add changes for copy queue support for immediate cmdlist submit

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-08-29 09:35:31 +02:00
Aravind Gopalakrishnan
cb8063f71d feature: Append recorded command list into immediate (3/N)
- Use correct stream for dispatch
- Add capability to append signal event
- Check available space globally in immediate append call

Related-To: NEO-10356

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-08-16 17:40:28 +02:00
Compute-Runtime-Validation
1cca5e24c1 Revert "performance: disable dispatch task count update when direct submissio...
This reverts commit 6d486459fe.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2024-08-13 16:37:31 +02:00
Zbigniew Zdanowicz
6d486459fe performance: disable dispatch task count update when direct submission active
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-08-13 13:19:26 +02:00
Bartosz Dunajski
d76ac1d1de fix: scratch controller residency
Related-To: HSD-18039519400

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-08-09 14:47:56 +02:00
Bartosz Dunajski
24cfd203ab fix: dont download tbx allocations on heapless first device submission
Related-To: HSD-18039476929

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-08-06 14:03:42 +02:00
Fabian Zwoliński
674c4a15ad fix: use correct gpu address when bindless heaps helper is enabled
Related-To: NEO-7063
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
2024-08-05 15:09:57 +02:00
Bartosz Dunajski
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
Zbigniew Zdanowicz
7ca0210ef2 fix: patch compute walker scratch address when scratch controller is changed
- scenario when command list is changed from normal to low priority queue
- save only scratch patch address, when changed, then enable patching
- kernels will re-use scratch patch address after update of compute walker

Related-To: NEO-11972

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2024-08-01 13:28:53 +02:00
Kamil Kopryk
4008ccea05 fix: add scratch ptr in implicit args patching for L0 regular cmdlists
Related-To: NEO-11874
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2024-07-18 14:07:07 +02:00
Mateusz Hoppe
52f5a9d6f0 refactor: remove SourceLevelDebugger from test and function name
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-07-10 16:32:26 +02:00
Bartosz Dunajski
6ccd14838e feature: set CSR for interruptable Events during CmdList Execute
Related-To: NEO-8179

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-07-01 19:35:24 +02:00
Jitendra Sharma
51fc9059c2 feature: program debug surface address
Related-To: NEO-7986
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2024-07-01 16:30:14 +02:00
Lukasz Jobczyk
fed90f5c8e fix: Add infrastructure to force dc flush when mitigate dc
-force dc on next tag update after RT kernel
-force dc when release shared object

Related-To: NEO-10556

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2024-06-24 17:15:03 +02:00
Dominik Dabek
296d2bb148 performance: adjust ulls timeout on power saving
Use l0 power saving setting to also adjust ulls timeout.

Related-To: NEO-10800

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2024-06-17 16:51:55 +02:00
Bartosz Dunajski
54e07def28 refactor: add const suffix
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-12 15:45:23 +02:00
Bartosz Dunajski
2e9bb26708 feature: enable copy offload api
Related-To: NEO-11376

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-12 12:02:23 +02:00
Bartosz Dunajski
bb00193205 refactor: remove csr from cmd list class
Related-To: NEO-11376

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-11 15:43:13 +02:00
Bartosz Dunajski
703fabdffd refactor: improve extracting Queue properties
Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-07 13:13:53 +02:00
Bartosz Dunajski
da9c009b88 feature: assign unique interrupt to queue
Related-To: NEO-8179

Signed-off-by: Bartosz Dunajski <bartosz.dunajski@intel.com>
2024-06-07 10:06:31 +02:00
Aravind Gopalakrishnan
2406453440 feature: Append recorded command list into immediate (2/N)
Related-To: NEO-10356

- Fixes to move available space check to parent
- propogate result from wait on events call

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-05-31 11:04:28 +02:00
Aravind Gopalakrishnan
0eaed66334 feature: Append recorded command list into immediate (1/N)
Related-To: NEO-10356

- Refactoring wait on event to skip flush when needed
- Refactor execute call interface to accept linear stream
- Program wait on events in new interface

Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@intel.com>
2024-05-29 05:59:32 +02:00
Mateusz Hoppe
a2a154ba4a fix: initialize context with first submission in heapless execution
- early return from initializeDeviceWithFirstSubmission if flush was
already called

Related-To: NEO-11219

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-05-24 14:56:04 +02:00
Robert Krzemień
965060385c fix: metric query hangs gpu when direct submission is enabled
Related-To: NEO-11052
Signed-off-by: Robert Krzemień <robert.krzemien@intel.com>
2024-05-16 12:45:11 +02:00
Szymon Morek
e35b951a00 performance: Allow indirect allocs as pack on OpenCL
Related-To: NEO-11228

Signed-off-by: Szymon Morek <szymon.morek@intel.com>
2024-05-10 17:57:42 +02:00
Compute-Runtime-Validation
902b611179 Revert "fix: Fix front end programming for cooperative dispatch"
This reverts commit 36ddfaaf4d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2024-05-08 11:14:37 +02:00
Katarzyna Cencelewska
e9f7df6ae6 refactor: create helper for maxPtssIndex
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
2024-05-07 12:47:52 +02:00
Mateusz Hoppe
d35d8727e5 fix: use primaryCsr allocations when csr has primaryCsr set
- global fence allocation
- global stateless heap allocation
- preemption allocation
- debug surface allocation

all above are shared from primary csr

Related-To: NEO-7824


Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-05-07 02:41:24 +02:00
Mateusz Hoppe
0a59a26a2c fix: add missing residency management in heapless mode
Related-To: NEO-7824

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2024-05-06 11:27:38 +02:00