intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2025-12-26 15:03:02 +08:00
Code Issues Packages Projects Releases Wiki Activity
15,653 Commits 42 Branches 655 Tags
34a80e915cc1133799345e991098eccd3644aa92
Commit Graph

145 Commits

Author SHA1 Message Date
Katarzyna Cencelewska
da7b03dd15 fix: to always use grfs count in calculateNumThreadsPerThreadGroup 
grf size != grf count

Related-To: GSD-8437
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2024-03-22 11:03:18 +01:00
Katarzyna Cencelewska
dd1d52259e refactor: add param rootDeviceEnvironment to calculateNumThreadsPerThreadGroup 
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
 2024-03-21 22:25:14 +01:00
Mrozek, Michal
f71f6d2b72 refactor: remove not needed code 
Signed-off-by: Mrozek, Michal <michal.mrozek@intel.com>
 2024-03-08 18:18:55 +01:00
Kacper Nowak
999ec9b2ca refactor: Unify logic for getting atomic FP caps 1/n 
- Separate logic for fp16/32/46 caps.
- Add aggregated constexprs for local & global caps of given type
- Pass arguments by reference
- Add hwInfo as argument for future refactors
- Add static_asserts in L0 to ensure there is no mismatch between
internal/external caps
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
 2024-02-07 11:39:36 +01:00
Mateusz Jablonski
a697a3f718 refactor: create new members for storing spill and private memory in scratch 
rename private scratch space into scratch space slot 1 as it can be generic

Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-01-23 12:42:25 +01:00
Compute-Runtime-Validation
f9f9035b95 Revert "refactor: create new members for storing spill and private memory in ... 
This reverts commit 87eb5f554a.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2024-01-23 09:13:00 +01:00
Mateusz Jablonski
87eb5f554a refactor: create new members for storing spill and private memory in scratch 
rename private scratch space into scratch space slot 1 as it can be generic

Related-To: NEO-9944
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2024-01-22 19:48:48 +01:00
Fabian Zwolinski
903e581b5f fix: add support for bindless implicit args 
Support for:
global_base and const_base in bindless addressing mode.

Related-To: NEO-9855
Signed-off-by: Fabian Zwolinski <fabian.zwolinski@intel.com>
 2024-01-12 01:27:17 +01:00
Dunajski, Bartosz
f7eb961435 refactor: validate template type in isUndefinedOffset helper 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-12-21 10:29:04 +01:00
Mateusz Jablonski
138fb65401 refactor: correct naming of enum class constants 11/n 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-19 14:52:57 +01:00
Dunajski, Bartosz
c612a86d28 feature: initial support for new zeinfo args 
Related-To: NEO-8070

Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-12-19 10:04:14 +01:00
Mateusz Jablonski
dd1b9d6abc refactor: correct naming of enum class constants 8/n 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-19 08:18:18 +01:00
Dunajski, Bartosz
d99104d5bf refactor: improve ImplicitArg struct handling 
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
 2023-12-18 15:19:00 +01:00
Mateusz Jablonski
895519db38 refactor: correct naming of NEOImageType enum values 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-12 11:15:28 +01:00
Mateusz Jablonski
83006521bc refactor: correct naming of internal fp atomic ext flags 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-04 19:02:53 +01:00
Mateusz Jablonski
c3d3a4db1f refactor: correct variable naming 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-04 13:45:53 +01:00
Mateusz Jablonski
c3ac7b78bd refactor: correct variable naming 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-12-01 02:18:46 +01:00
Mateusz Jablonski
c9664e6bad refactor: rename global debug manager to debugManager 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-11-30 13:00:59 +01:00
Kamil Kopryk
ae607502a0 feature: Add indirect data and scratch pointer to zeinfo 
Related-To: NEO-7621
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
 2023-11-03 12:01:58 +01:00
Mateusz Jablonski
fd7c750cf7 fix: ensure local variable address is not exposed outside of function 
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-10-06 15:59:16 +02:00
Mateusz Jablonski
9337911742 fix: add self-assign check in operator= 
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-10-03 08:09:16 +02:00
Mateusz Jablonski
2a78a00855 fix: correct passing string in populateArgMetadata 
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-09-27 18:00:33 +02:00
Maciej Bielski
97e7cda912 feature: Optimize intra-module kernel ISA allocations 
So far, there is a separate page allocated for each kernel's ISA within
`KernelImmutableData::initialize()`. Apparently the ISA blocks are often
much smaller than a 64k page, which leads to poor memory utilization and
was even observed to cause the device OOM error if a single module has
several keys.

Improve the situation by reusing the parent allocation (owned by the
module instance) for modules, which kernel ISAs can fit together within
a single 64k page. This improves the memory utilization on a single
module level.

Related-To: NEO-7788
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2023-09-21 13:55:45 +02:00
Compute-Runtime-Validation
913a926fd4 Revert "feature: Optimize intra-module kernel ISA allocations" 
This reverts commit c348831470.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-09-19 14:16:05 +02:00
Maciej Bielski
c348831470 feature: Optimize intra-module kernel ISA allocations 
So far, there is a separate page allocated for each kernel's ISA within
`KernelImmutableData::initialize()`. Apparently the ISA blocks are often
much smaller than a 64k page, which leads to poor memory utilization and
was even observed to cause the device OOM error if a single module has
several keys.

Improve the situation by reusing the parent allocation (owned by the
module instance) for modules, which kernel ISAs can fit together within
a single 64k page. This improves the memory utilization on a single
module level.

Related-To: NEO-7788
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
 2023-09-19 12:05:09 +02:00
Mateusz Jablonski
00e24c0069 performance: leave StackVec::onStackMemRawBytes uninitialized 
this memory shouldn't be accessed before resize

Resolves: HSD-18032826534

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-08-25 11:40:38 +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
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
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
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 Hoppe
313fb84fda feature: bindless addressing mode support 
- allow bindless kernels to execute
- bindless addressing kernels are using private heaps mode
- do not differentiate bindful and bindless surface state base addresses

Related-To: NEO-7063

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-06-19 12:41:03 +02:00
Cencelewska, Katarzyna
7cb3278eb3 fix: add function to calculate number of threads per tg 
Signed-off-by: Cencelewska, Katarzyna <katarzyna.cencelewska@intel.com>
 2023-06-13 14:02:24 +02:00
Mateusz Hoppe
8bc1fb1251 refactor: add function checking bindless addressing 
- simplify logic to check addressing mode of a kernel

Related-To: NEO-7063

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-06-12 14:42:18 +02:00
Mateusz Hoppe
646c8985e8 refactor: store number of stateful args in KernelDescriptor 
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-06-12 14:15:43 +02:00
Kamil Kopryk
6a0f7afd64 feature: verify stateful information only when binary is generated by IGC 
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>

Related-To: NEO-6075

Ngen binaries contain stateful information, however they are
not used in isa on Pvc. Therefore, we can just ignore them.
 2023-06-12 11:45:41 +02:00
Mateusz Jablonski
31f32cc16e fix implicit args: generate local ids as for grf size 32 
Related-To: IGC-6936

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-04-07 11:37:07 +02:00
Mateusz Jablonski
dd39b822d3 feature implicit args: patch rt dispatch global array in implicit args buffer 
handle has_rtcalls in kernels and functions in zebin

Related-To: NEO-7818
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2023-03-28 12:31:38 +02:00
Mateusz Hoppe
0204761add feature: gpu assert implementation 
- allocate assert buffer when kernel has assert
- track assert kernels in cmdlists and cmdqueues
- check and print assert at sync calls: cmdqueue synchronize(), fence
synchronize(), event hostSynchronize(), synchronous imm cmdlists
append()

Related-To: NEO-5753

Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2023-03-15 19:22:09 +01:00
Dominik Dabek
69a16fd3ed feature: check indirect access for kernel 
Do not make indirect allocations resident if kernel does not use
indirect access.
For both level zero and opencl.
Currently disabled by default, enable with debug flag
DetectIndirectAccessInKernel

Related-To: NEO-7712

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-03-08 16:58:26 +01:00
Michal Mrozek
c77d954900 [perf] simplify setting constant buffer and improve performance 
- no need to count parameters
- remove unrecoverable which requires fetching additional fields.

Related-To: NEO-5170

Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
 2023-03-02 13:09:52 +01:00
Compute-Runtime-Validation
4a369ad88d Revert "feature: check indirect access for kernel" 
This reverts commit 075c96267d.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
 2023-02-24 03:48:22 +01:00
Dominik Dabek
075c96267d feature: check indirect access for kernel 
Do not make indirect allocations resident if kernel does not use
indirect access.
Enable for both level zero and opencl.

Related-To: NEO-7712

Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
 2023-02-23 12:38:53 +01:00
Warchulski, Jaroslaw
5ec9de90ee Cleanup includes 52 
Cleaned up files:
level_zero/core/source/driver/driver.h
level_zero/tools/source/sysman/fabric_port/windows/os_fabric_port_imp.h
level_zero/tools/source/sysman/pci/os_pci.h
shared/source/debug_settings/debug_settings_manager.h
shared/source/gmm_helper/page_table_mngr.h
shared/source/gmm_helper/windows/gmm_memory_base.h
shared/source/kernel/kernel_arg_metadata.h
shared/test/common/libult/linux/drm_mock.h
shared/test/unit_test/fixtures/command_container_fixture.h
shared/test/unit_test/fixtures/product_config_fixture.h
shared/test/unit_test/helpers/simd_helper_tests_pvc_and_later.inl
shared/test/unit_test/os_interface/hw_info_config_tests.h

Related-To: NEO-5548

Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2023-02-13 11:39:34 +01:00
Warchulski, Jaroslaw
fe8a6d98ad Cleanup includes 45 
Cleaned up files:
opencl/source/api/api.h
shared/source/command_stream/csr_deps.h
shared/source/helpers/engine_node_helper.h

Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2023-01-26 11:12:15 +01:00
Warchulski, Jaroslaw
8de3898abc Cleanup includes 31 
Cleaned up files:
shared/source/command_stream/experimental_command_buffer.h
shared/source/helpers/get_info.h
shared/source/helpers/local_id_gen.h
shared/source/memory_manager/gfx_partition.h
shared/source/memory_manager/host_ptr_manager.h
shared/source/memory_manager/prefetch_manager.h
shared/test/common/mocks/mock_memory_manager.h

Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2023-01-16 11:45:55 +01:00
Warchulski, Jaroslaw
3d59dce80c Cleanup includes 27 
Cleaned up files:
opencl/source/command_queue/command_queue.h
shared/source/built_ins/registry/built_ins_registry.h
shared/source/kernel/kernel_descriptor.h

Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2023-01-11 16:10:28 +01:00
Krystian Chmielewski
614928ed45 refactor(zebin): decouple zeInfo decoding 
Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
 2023-01-10 12:27:10 +01:00
Warchulski, Jaroslaw
7ae44268cb Cleanup includes 17 
Cleaned up files:
shared/source/built_ins/sip.h
shared/source/compiler_interface/compiler_cache.h
shared/source/compiler_interface/compiler_interface.h
shared/source/device_binary_format/device_binary_formats.h
shared/source/helpers/timestamp_packet.h
shared/source/kernel/debug_data.h
shared/source/utilities/tag_allocator.h
shared/test/common/mocks/mock_device.h

Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com>
 2023-01-02 10:59:08 +01:00