intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-03 06:49:52 +08:00
Code Issues Packages Projects Releases Wiki Activity
14,466 Commits 43 Branches 655 Tags
c9d661523121bbf25f0cc80bc33f5e073666fa2a
Commit Graph

2254 Commits

Author SHA1 Message Date
Dunajski, Bartosz
c3ca3ff119 refactor: use qword memcpy for Events with qword packet size 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-20 07:29:45 +02:00
Neil R Spruit
8efd8853fb feature: L0 Device Hierarchy support for Composite & Flat modes 
Related-To: LOCI-4615

- Added Support for users to set ZE_FLAT_DEVICE_HIERARCHY to either FLAT
or COMPOSITE to change how devices are returned in zeDeviceGet and
clGetDeviceIDs.
- COMPOSITE is default behavior that exists today.
- FLAT returns all sub devices which have no sub devices and all root
devices that have no sub devices in zeDeviceGet ie with all devices
flattened out in order.
- Added zeDeviceGetRootDevice for one to retrieve the Root Device for
any SubDevice.

Signed-off-by: Neil R Spruit <neil.r.spruit@intel.com>
 2023-07-20 01:00:54 +02:00
Zbigniew Zdanowicz
0374a66d97 performance: enable command list primary batch buffer on gen platforms 
Related-To: NEO-7807

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-19 14:25:18 +02:00
Dominik Dabek
622a3ed89c performance(ocl): flag to not dcFlush on no event 
If waitForBarrier is not passed outEvent then do
dcFlush on the next synchronize call.

Related-To: NEO-8147

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-07-18 15:38:54 +02:00
Lukasz Jobczyk
2407658376 performance: Flush constant cache only if any ULLS enabled 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-17 16:13:55 +02:00
Dunajski, Bartosz
ec9afc5450 feature: ZE_COMMAND_QUEUE_FLAG_IN_ORDER flag support 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-17 12:02:56 +02:00
Zbigniew Zdanowicz
ceed88d39e performance: add debug support to immediate flush task 
Related-To: NEO-7808

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-14 16:10:50 +02:00
Luzynski, Sebastian Jozef
c141fbaf74 fix: Adjust zeVirtualMem functions to store size provided by user 
Related-To: LOCI-3397

Signed-off-by: Luzynski, Sebastian Jozef <sebastian.jozef.luzynski@intel.com>
 2023-07-13 14:17:21 +02:00
Mateusz Hoppe
9fd7f9cf05 fix: set ImplicitArgs size to size of defined fields 
Resolves: NEO-8169

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-07-12 21:30:32 +02:00
Kacper Nowak
04291be379 refactor: Enhance L0 builtins ULTs 
- Removed redundant code
- Corrected naming
- Improved code coverage

Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
 2023-07-12 16:52:19 +02:00
Lukasz Jobczyk
83bd33befc refactor: Add flag to control BCS split for pageable memory 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-07-11 15:12:40 +02:00
Dunajski, Bartosz
37fdb5998e feature: appendMemoryFill support for in-order cmd lists 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-11 13:05:27 +02:00
Dunajski, Bartosz
241d9d447a feature: optimize programming wait events from the same in-order cmdlist 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-11 12:59:34 +02:00
Zbigniew Zdanowicz
3f7269d401 fix: make sip state programing once for all level zero command queues 
Related-To: NEO-7828

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-11 11:34:21 +02:00
Cencelewska, Katarzyna
aa0beb8191 fix: Unify logic calculating threads per work group part 4 
- also use helper when checking that is simd1 to have same flow

Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-07-07 15:34:59 +02:00
Mateusz Hoppe
4aba0f0340 feature: global bindless surface state base support 
- program global bindless ssba when external allocator used (
UseExternalAllocatorForSshAndDsh)

Related-To: NEO-7063

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-07-06 18:31:49 +02:00
Spruit, Neil R
11c96559a9 fix: Use Symbols map to report exported symbols vs external functions 
Related-To: LOCI-4578

- Report all symbols in the Symbols Map for a Module as the Exported
symbols instead of using the External Functions Program Info.
- Resolves the issue of reporting symbols for platforms that don't have
ZEBIN binaries by default.

Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
 2023-07-06 17:41:45 +02:00
Dunajski, Bartosz
9adfa4b355 feature: improve in-order Events chaining 
- Clear TS event before chaining
- Dont chain non-TS events

Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-05 14:21:36 +02:00
Mateusz Jablonski
66c733eac7 fix: add missing zero-initialization of variable 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-07-05 10:39:48 +02:00
Zbigniew Zdanowicz
866e3c37ba performance: add implementation of cmdlist immediate flush task 
Related-To: NEO-7808

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-07-05 10:23:16 +02:00
Dunajski, Bartosz
c18198ebd8 feature: change in-order allocation type to uint32_t 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-05 09:56:32 +02:00
Dunajski, Bartosz
5b9d45f3bc feature: handle in-order allocation overflow 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-07-04 15:58:11 +02:00
Cencelewska, Katarzyna
61f701aba5 fix: Unify logic calculating threads per work group part 3 
Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-07-04 15:27:44 +02:00
Cencelewska, Katarzyna
2e17c21728 fix: Unify logic calculating threads per work group part 2 
- use calculateNumThreadsPerThreadGroup instead of getThreadsPerWG to
have same flow and proper values of threads per work groups

Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-07-04 10:34:02 +02:00
Compute-Runtime-Validation
39740da9d1 Revert "fix: Unify logic calculating threads per work group part 2" 
This reverts commit 1e8a53bd53.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-07-02 07:09:14 +02:00
Dunajski, Bartosz
f9a58b5544 feature: program in-order barrier as non stalling instruction 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-30 17:17:53 +02:00
Young Jin Yoon
c5d675570a feature: support for zeDriverGetLastErrorDescription 
Added setErrorDescription() and getErrorDescription() in DriverHandle
to record and retrieve the custom string for errors.

Related-To: LOCI-4619
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
 2023-06-30 17:12:32 +02:00
Cencelewska, Katarzyna
1e8a53bd53 fix: Unify logic calculating threads per work group part 2 
- use calculateNumThreadsPerThreadGroup instead of getThreadsPerWG to
have same flow and proper values of threads per work groups

Related-To: NEO-8087
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-06-30 14:16:08 +02:00
Michal Mrozek
5eadedc36e refactor: Remove not used logic. 
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2023-06-30 10:58:35 +02:00
Zbigniew Zdanowicz
21823af419 performance: add skeleton method to cmdlist immediate flush task 
Related-To: NEO-7808

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-06-30 10:46:20 +02:00
Dunajski, Bartosz
9a8c38fa94 feature: unregister csr client on cmd list host sync 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-29 13:52:08 +02:00
Artur Harasimiuk
cf73ab0df3 refactor: remove not used code 
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2023-06-29 13:04:23 +02:00
Cencelewska, Katarzyna
0d7aefe66b fix: Unify logic calculating threads per work group part 1 
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-06-29 10:43:22 +02:00
Jaroslaw Chodor
023fe38448 fix: Use correct dimensions for UV plane 
For image view mapped directly to UV plane,
the dimensions should 2 times smaller than
dimensions of the source image.
(1 raw UV pair maps to 2x2 block of original image)

Related-To: NEO-7936

Signed-off-by: Jaroslaw Chodor <jaroslaw.chodor@intel.com>
 2023-06-28 23:34:50 +02:00
Dunajski, Bartosz
ecb415bf62 feature: reenable RelaxedOrdering 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-28 12:20:17 +02:00
Dunajski, Bartosz
2383896dbb fix: stall RelaxedOrdering scheduler when programming Semaphores 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-28 11:46:04 +02:00
Zbigniew Zdanowicz
1067167637 test: adding testing debug flag overriding driver version 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-06-27 17:58:03 +02:00
Dunajski, Bartosz
7ac825e74b refactor: add debug flag to synchronize Event before reset 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-26 17:38:37 +02:00
Cencelewska, Katarzyna
68d81c82a7 fix: Use proper value about hw local id generations 
- remove useless flag ForceNumberOfThreadsInGpgpuThreadGroup
- add new flag "RemoveRestrictionsOnNumberOfThreadsInGpgpuThreadGroup"
to restore old path without restrictions about number of threads in
thread group
- fix forwarding information about hw local ids generations to
calculate numOfThreadsInThreadGroup correctly

Related-To: NEO-7952, NEO-7982
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-06-26 16:35:42 +02:00
Dunajski, Bartosz
aea5f435db feature: unregister CSR client on Event host synchronize 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-26 12:02:14 +02:00
Dunajski, Bartosz
61fb19caab feature: bring back counter based in-order tracking 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-26 10:01:18 +02:00
Lukasz Jobczyk
bc0a3a7eb5 fix: Consider slm size in suggest work group cache 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-06-26 09:12:54 +02:00
Joshua Santosh Ranjan
97b4d8bab5 feature: add initial support for host mapped timestamps 
Related-To: LOCI-4171

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
 2023-06-26 08:29:58 +02:00
Lukasz Jobczyk
0bc5eead84 fix: Remove not needed BCS split helper 
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-06-22 14:36:22 +02:00
Zbigniew Zdanowicz
ddffb8a67f fix: add missing unrecoverable macro 
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2023-06-22 10:47:18 +02:00
Dunajski, Bartosz
eda13e675a feature: enable dynamic post sync allocation layout 
Related-To: NEO-7966

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-22 08:37:40 +02:00
Lukasz Jobczyk
a61b39c47b fix: Invalidate constant cache when ULLS enabled 
Related-To: NEO-8067

Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2023-06-21 15:17:14 +02:00
Mateusz Hoppe
111b112729 feature: add assertBufferPtr to ImplicitArgs 
Related-To: NEO-5753, NEO-8078

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-06-20 20:43:57 +02:00
Mateusz Jablonski
1be48965ef fix: parse all extensions passed to zeMemAllocShared 
reuse common pNext parser

allow to create raytracing allocation with relaxed size

Related-To: NEO-8075
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-06-20 14:32:16 +02:00
Dunajski, Bartosz
46e8c3f5dd fix: reenable RelaxedOrdering for OCL 
Related-To: NEO-7458

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-06-20 13:05:25 +02:00