Commit Graph

1640 Commits

Author SHA1 Message Date
Fabian Zwolinski
7953d15826 Print warning when kernel uses too much SLM
Instead of just returning proper error code in case of exceeding
available Shared Local Memory size we also want to print error message
to make debugging easier.

Related-To: NEO-7280
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2022-10-07 19:06:19 +02:00
Lukasz Jobczyk
f91047f2ee Wait on timestamps in Event::wait
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-10-07 12:04:45 +02:00
Fabian Zwolinski
1142404c0c Add error handling when kernel uses too much SLM
API Functions reporting error:
- clCreateKernel
- clEnqueueNDRangeKernel
- zeKernelCreate
- zeCommandListAppendLaunchKernel
- zeKernelSuggestGroupSize

Related-To: NEO-7280
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2022-10-06 16:45:42 +02:00
Dunajski, Bartosz
9100610b5d Remove test API to disable overdispatch
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-10-06 10:12:47 +02:00
Compute-Runtime-Validation
f226718fef Revert "Remove test API to disable overdispatch"
This reverts commit 3b92cef7a1.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-10-05 23:51:17 +02:00
Dunajski, Bartosz
ad2d3d0289 Remove not used method
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-10-05 17:10:51 +02:00
Mateusz Hoppe
2f24ef6855 Error from clEnqueueNDRangeKernel() for too big group counts
Resolves: NEO-6976

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2022-10-05 12:35:16 +02:00
Dunajski, Bartosz
52b63be026 Remove isCleanLeftoverMemoryRequired() + refactor sampler support path
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-10-04 16:24:03 +02:00
Kacper Nowak
65f7ff2027 Ocloc: Add -s to options string for non-spirv input with -g option passed
Automatically add "-s" (source path) option if -g flag is present.
This applies only to non-spirv input.
- Due to conflict, do not automatically append source path when
CMC compiler is used.
- Minor code refactor: use defined compiler options instead of local
strings; wrap filename in quotes (in case of space-separated filename
string).

Related-To: NEO-7285
Signed-off-by: Kacper Nowak kacper.nowak@intel.com
2022-10-04 14:49:53 +02:00
Baj, Tomasz
625f88d64d Move API specific logic directly to getDefaultCompilerCacheConfig function
Signed-off-by: Baj, Tomasz <tomasz.baj@intel.com>
2022-10-04 10:25:08 +02:00
Dunajski, Bartosz
3b92cef7a1 Remove test API to disable overdispatch
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-10-04 09:54:05 +02:00
Compute-Runtime-Validation
36e17cebef Revert "Include dynamic SLM in clGetKernelWorkGroupInfo"
This reverts commit ccdb5aaa2a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-10-03 19:27:21 +02:00
Mateusz Jablonski
23eff82d0a OCL: optimize creating printf buffer
Dont create printf buffer when kernel doesnt require it

Related-To: HSD-18023825570
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-09-30 12:25:57 +02:00
Fabian Zwolinski
ccdb5aaa2a Include dynamic SLM in clGetKernelWorkGroupInfo
Current implementation only takes static slmInlineSize into account.
With this change we also include dynamic SLM passed as a kernel arguments.

Related-To: NEO-5761
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
2022-09-29 17:38:44 +02:00
Dunajski, Bartosz
f2ce393fc2 Capability to set overdispatch param for Kernel
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-09-27 18:29:04 +02:00
Dominik Dabek
d8b7d56160 Copy host ptr on cpu if possible in clCreateBuffer
use cpu copy with locked pointer if possible
because this is faster than copy on gpu
limit to buffers of size at most 64kb

Related-To: NEO-7332

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2022-09-27 17:54:06 +02:00
Kamil Diedrich
842003f827 Add support for Y210 format in cl_va sharing
Related-To: NEO-7245

Signed-off-by: Kamil Diedrich <kamil.diedrich@intel.com>
2022-09-26 10:34:16 +02:00
Patryk Wrobel
46e0317548 Remove possibility of accessing directly USM device memory in debug logs
clEnqueueSVMMemFill() is utilized by clEnqueueMemFillINTEL().
The latter may receive USM device pointers. If anyone passed
such pointer then SEGMENTATION_FAULT would occur.

Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
2022-09-23 17:14:05 +02:00
Dunajski, Bartosz
b2001bf265 L0: GRF mode debug flags support
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-09-22 15:27:31 +02:00
Patryk Wrobel
f6bcdfafaa Fix types passed to sizeof operator in clGetProgramInfo()
CL_PROGRAM_BINARY_SIZES parameter uses size_t according to
the specification. Replaced usage of cl_device_id with size_t.

Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
2022-09-22 12:26:15 +02:00
Krystian Chmielewski
311b0b0020 Create input for linker during zebin decoding
Remove code duplication. Parsing zebin elf for relocations and symbols
is moved to decodeSingleDeviceBinary.

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
2022-09-22 11:12:39 +02:00
Lukasz Jobczyk
e00a5e0a1e Release main copy engine from device and sub device
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-20 17:12:34 +02:00
Krystian Chmielewski
6b3ac9f1e2 refactor ocl patchtokens tests
Related-To: NEO-7131

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
2022-09-19 17:46:02 +02:00
Milczarek, Slawomir
0192e8038f Check for GPU hang in path with wait for timestamps
Related-To: NEO-6868

Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
2022-09-19 15:01:46 +02:00
Patryk Wrobel
f6bf669ee9 Use forward declarations in compression_selector.h
Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
2022-09-14 11:54:24 +02:00
Kamil Kopryk
410fd7d909 Correct binding table prefetch
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
Related-To: NEO-6075

Binding table entry count was zeroed even when
ForceBtpPrefetchMode debug flag was enabled
2022-09-13 14:34:30 +02:00
Lukasz Jobczyk
3a7f266d66 Enable BCS split in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-08 15:56:30 +02:00
Kacper Nowak
710c8cf5ef Linker: add support for symbols with local binding
This commits add support for relocating
symbols with local binding and of functional type
(STB_LOCAL, STT_FUNC).

Related-To: NEO-7299
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2022-09-08 14:50:29 +02:00
Lukasz Jobczyk
f65d2aeb87 Split copy along single dimension
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-08 12:39:06 +02:00
Mateusz Hoppe
6ad16c9e72 Missing support for OCL debugging with L0
- make resident debugSurface
- allocate debugSurface with correct allocation type and size
- notify cmdQ create/destroy

Related-To: NEO-7075

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
2022-09-07 13:30:05 +02:00
Compute-Runtime-Validation
c0ce477f85 Revert "Enable BCS split WA in OCL"
This reverts commit abfcaf1265.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-09-06 20:42:57 +02:00
Patryk Wrobel
53c127e64c Remove superfluous const_casts
Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
2022-09-06 13:34:01 +02:00
Dunajski, Bartosz
16d9000429 Add option to change GRF mode
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2022-09-06 13:00:17 +02:00
Dominik Dabek
16798467ac Add api specific config for allocation cache
Currently disabled for both opencl and level zero

Related-To: NEO-6893

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2022-09-05 21:15:18 +02:00
Lukasz Jobczyk
abfcaf1265 Enable BCS split WA in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-05 13:34:11 +02:00
Lukasz Jobczyk
a9b3b8137f Release locks before wait on blocking BCS split calls
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-05 11:20:23 +02:00
Lukasz Jobczyk
0d6bef0753 Add BCS split to api specific config
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-05 11:13:10 +02:00
Compute-Runtime-Validation
20f49481f2 Revert "Enable BCS split WA in OCL"
This reverts commit d672920121.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-09-03 20:25:10 +02:00
Compute-Runtime-Validation
572fc24cf5 Revert "Wait on timestamps in Event::wait"
This reverts commit 5d4aca361f.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-09-02 02:43:20 +02:00
Lukasz Jobczyk
d672920121 Enable BCS split WA in OCL
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-09-01 16:26:00 +02:00
Zbigniew Zdanowicz
c3f7e40a8d Rename special pipeline select mode to systolic
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
2022-08-31 22:16:26 +02:00
Lukasz Jobczyk
399758ef17 Change default engines for BCS split
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-08-31 21:34:36 +02:00
Lukasz Jobczyk
a3dedcc7ee Add minimal transfer size for BCS split
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-08-31 21:28:40 +02:00
Filip Hazubski
74bf623ddb Correct arguments verification of clEnqueueReleaseDX9ObjectsINTEL call
When clEnqueueReleaseDX9ObjectsINTEL is called and
incorrect memory objects list is passed, ensure that
api returns gracefully and proper value is returned.

Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2022-08-31 21:02:10 +02:00
Dominik Dabek
8cc0177f1c Change DG2 l1 cache policy to WB
With compiler LSC WAs this gives better performance.

If debugger is active, policy will not be changed ie.
will be WBP.

Related-To: NEO-7003

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2022-08-31 14:31:23 +02:00
Lukasz Jobczyk
5d4aca361f Wait on timestamps in Event::wait
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
2022-08-31 12:57:27 +02:00
Compute-Runtime-Validation
2621460e80 Revert "Change DG2 l1 cache policy to WB"
This reverts commit a820e73dd7.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2022-08-27 08:04:19 +02:00
Dominik Dabek
a820e73dd7 Change DG2 l1 cache policy to WB
With compiler LSC WAs this gives better performance.

If debugger is active, policy will not be changed ie.
will be WBP.

Related-To: NEO-7003

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
2022-08-26 12:58:45 +02:00
Kamil Diedrich
2de3cdc90c Add packed formats to import va surface
This patch adds YUY2 and Y210 packed formats into cl/va sharing

Signed-off-by: Kamil Diedrich <kamil.diedrich@intel.com>
2022-08-25 18:18:52 +02:00
Mateusz Jablonski
ca0686b404 Unify include directories for i915 headers
include i915_drm_prelim.h using relative path

Related-To: NEO-6852
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2022-08-24 14:58:01 +02:00