Commit Graph

3694 Commits

Author SHA1 Message Date
Zhang, Winston
2a41ace67e feature: Add hang detection support for zeDeviceGetStatus
Added hang detection for zeDeviceGetStatus API.
Added ULT for hang detection for zeDeviceGetStatus API.

Related-To: LOCI-1558

Signed-off-by: Zhang, Winston <winston.zhang@intel.com>
2023-07-20 15:09:10 +02:00
Compute-Runtime-Validation
8c155a2e89 Revert "performance: Memory handling improvements"
This reverts commit 5b80bd4d7c.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-07-20 11:37:09 +02:00
Artur Harasimiuk
1434872427 refactor: remove unused code
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2023-07-20 11:09:55 +02:00
Mayank Raghuwanshi
af6798f257 feature: Add support for 64 bit memory counters for zesInit
Related-To: LOCI-4613, LOCI-4612

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
2023-07-20 11:04:24 +02:00
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
Compute-Runtime-Validation
5c60b4d973 Revert "feature: Add support for Media frequncy Domain on linux"
This reverts commit 085293b230.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-07-20 03:04:52 +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
Filip Hazubski
5b80bd4d7c performance: Memory handling improvements
By default prefer allocating memory first by KMD, instead of malloc first.

By default prefer not caching allocations on MTL devices. This results
in allocations being handled with non-coherent pat index.

For integrated devices when caching is not preferred do not allow
direct memory access in CPU domain. For map/unmap operations create
a dedicated memory allocation for CPU access, instead of accessing it
directly, reusing the same logic as when mapping/unmapping local memory.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2023-07-19 19:21:44 +02:00
Mayank Raghuwanshi
085293b230 feature: Add support for Media frequncy Domain on linux
Related-To: LOCI-4552

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
2023-07-19 16:43:27 +02:00
Artur Harasimiuk
c8d26bec02 test: handle SEGV and ABRT in L0 ults
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2023-07-19 15:46:34 +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
Artur Harasimiuk
9524b65b51 refactor: remove unused code
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2023-07-19 12:00:40 +02:00
Bari, Pratik
16b56b9a6f feature(sysman): New shared directory in the sysman code.
The files containing the new 'SysmanKmdInterface' has been moved into
the new 'shared' directory in the existing sysman directory. More files
are to be added in this directory which will be used by all the sysman
modules in the sysman and tools directories.

Related-To: LOCI-4649

Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
2023-07-18 16:06:31 +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
Artur Harasimiuk
faa8907344 refactor: remove unused code
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
2023-07-18 14:52:43 +02:00
Mateusz Hoppe
8e07dd30cb performance(debugger): optimize ATT handling - minimize mem allocs
- do not allocate state save area every time attention event
is handled
- keep allocated memory for subsequent events
- remove not needed DBEUG_BREAK

Related-To: NEO-8183

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-18 08:37:04 +02:00
Zbigniew Zdanowicz
6d458cd002 fix: modify tests for primary batch buffer in command lists
Related-To: NEO-7807

Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2023-07-18 08:36:47 +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
Bellekallu Rajkiran
461ecc9b3b fix(sysman): Align board number string sequence
Related-To: LOCI-4631

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2023-07-17 16:07:43 +02:00
Mateusz Hoppe
3070fed574 test: run zello_bindless_kernel with external SSH allocator
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-17 15:13:55 +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
Mateusz Hoppe
9a53f20e6c performance(debugger): optimize ATT event handling
- check threads with attention state before reading SR_IDENT
- memory read is costly, for threads already in stopped state
there is no need to read sr_ident and check thread state again
- single stepping one thread performance is substantially improved,
by the factor of 6x

Related-To: NEO-8183

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-17 10:42:34 +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
Kulkarni, Ashwin Kumar
ed972bb21c feature(sysman): supports pci module for zesInit windows
Related-To: LOCI-4204

Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
2023-07-14 02:28:32 +02:00
Puneeth Kumar Reddy, Devarinti
6f29e3b100 feature(sysman): add debug logs to power module for zesInit
Related-To: LOCI-3879

Signed-off-by: Puneeth Kumar Reddy, Devarinti <puneeth.kumar.reddy.devarinti@intel.com>
2023-07-13 17:46:30 +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
Lu, Wenbin
4de792cee0 fix: support alignments in host and shared UnifiedMemoryAllocation
Related-To: LOCI-4334

Signed-off-by: Lu, Wenbin <wenbin.lu@intel.com>
2023-07-13 08:48:41 +02:00
Bari, Pratik
b9837ef068 feature(sysman): Added changes for Porting Frequency API
The new classes SysmanKmdInterface, SysmanKmdInterfaceI915 and
SysmanKmdInterfaceXe have been introduced.
A map is maintained in the SysmanKmdInterfaceI915 and
SysmanKmdInterfaceXe class for the sysfs file names.
The access specifier of the function getDrmVersion has been changed from
protected to public so as to use it in the sysman code. This is required
for the SysmanKmdInterface pointer to point to the
SysmanKmdInterfaceI915 and SysmanKmdInterfaceXe accordingly.
The ULTs have been added for the new sysfs file path corresponding to
the i915 and the Xe driver.

Related-To: LOCI-4399

Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
2023-07-13 08:41:05 +02:00
Puneeth Kumar Reddy, Devarinti
d61961227c feature: add debug logs for fabricport for new sysman implementation
Related-To: LOCI-3882

Signed-off-by: Puneeth Kumar Reddy, Devarinti <puneeth.kumar.reddy.devarinti@intel.com>
2023-07-13 08:00:43 +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
Kacper Nowak
b908203001 fix: Compile built-ins per release
- Preserve releases on CMake level.
- Instead of generating builtins per platform, generate them per-release
(+ correct naming accordingly).
- Stop using revisions in builtin compilation logic path, as they are
already embedded in release (device ip).
- Remove platform names & revisions from names for generated files
(related to builtins).
- Remove unnecessary code, refactor ULT logic.

Related-To: NEO-7783
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2023-07-11 16:02:36 +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
Young Jin Yoon
81822e3716 refactor: rename pageSize2Mb to pageSize2M
The previous name "pageSize2Mb" defined in
shared/source/helpers/constant.h is inconsistent to other variable,
i.e. pageSize64k.

Furthermore, it's a bit misleading because the page size is defined in
Megabytes (MB), not in Megabits (Mb).

Related-to: NEO-7695
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
2023-07-10 20:12:09 +02:00
Mateusz Hoppe
9f466a9967 test: fix DebugSession ULT
- use size of state save area header when comparing contents

Related-To: NEO-7630

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-10 11:11:04 +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
Mateusz Hoppe
6205cca038 fix(debugger): require immediate binding for Module's allocations
- all bos from Module must have requireImmediateBinding
flag set
- this change fixes hang in debugger - where MODULE LOAD event
was not sent

Resolves: NEO-8121

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-06 17:34:22 +02:00
Puneeth Kumar Reddy, Devarinti
c6e0e397c6 feature: add debug logs for ecc module for new sysman implementation
Related-To: LOCI-3878

Signed-off-by: Puneeth Kumar Reddy, Devarinti <puneeth.kumar.reddy.devarinti@intel.com>
2023-07-06 15:39:28 +02:00
Mayank Raghuwanshi
ddd7e6087f fix: Add guid check while calculating sysman memory Bandwidth
Related-To: LOCI-4597

Signed-off-by: Mayank Raghuwanshi <mayank.raghuwanshi@intel.com>
2023-07-05 19:36:44 +02:00
Mateusz Hoppe
3242d3f8eb test: add bindful kernel to zello_bindless_kernel test
- bindful and bindless kernels should execute correctly

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2023-07-05 16:40:17 +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
Kulkarni, Ashwin Kumar
358a53c43b feature(sysman): enables ecc module for zesInit windows
Related-To: LOCI-4207

Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
2023-07-05 11:16:51 +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
Kulkarni, Ashwin Kumar
c1371eea9f feature(sysman): supports firmware and RAS modules for zesInit
Related-To: LOCI-4197

Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
2023-07-05 10:30:48 +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