Age | Commit message (Collapse) | Author |
|
If an exception was thrown in the main thread, the child threads
were not being synchronised, leading to undefined behaviour (and
probably the program crashing instead of correctly propagating the
exception).
Add support to the build system for enabling ThreadSanitizer.
This needs a build system option rather than simply passing
extra_cxx/link_flags because the sanitizer options are
incompatible with -Wl,-undefined,error.
Add a unit test for throwing an exception within a CPPScheduler
workload.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I7638272a5d43a24a861f3e6d63f3ee7b099483b5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/538048
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9957
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Previously, building the `arm_compute-static` archive would fail the linking stage due to the Compute Kernel Writer (CKW) symbols not being correctly included. We fix this issue by collecting the built CKW objects and packing them into the Compute Library archive during SCons build time.
Compiling the shared library remains unchanged, and still statically links against CKW.
Resolves: COMPMID-6342
Change-Id: I841ed7379652fbede6afe9e90a98202656683086
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9873
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Partially resolves: COMPMID-6283
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I7596e3dc357d6f0b9cbe66534523943a73c26d81
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9864
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
* Partially port ElementwiseBinary component to ckw (broadcast not
supported yet)
* Port Store component to ckw
* Move KernelArgumentsHelpers to ckw_driver/ as it's only used by the
driver
ckw_driver is a middle layer between dynamic fusion and Compute Kernel
Writer (CKW). It consumes the fused kernel component stream produced by
Dynamic Fusion and uses CKW to write the kernel code complete with all
meta info needed by the runtime to enqueue the kernel.
It consists of two parts:
* Kernel writing: This resides in dynamic_fusion/sketch
* Runtime utilities: This resides in dynamic_fusion/runtime
The integration (separation between DF and CKW) occurs in two places:
* Inside GpuCKWDriver
global driver that coordinates how the
final fused kernel code is assembled together alongwith other meta
info needed by runtime.
* Inside each instantiated IGpuCKWComponentDriver
component driver that drives CKW to write component-specific code
or do component-specific configurations
Partially resolves: COMPMID-5792 COMPMID-6282 COMPMID-6260 COMPMID-6266
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ib57a080a65fe8cfee1a8df1529fe572005a6d2f2
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9847
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
* Always link Compute Kernel Writer statically to Compute Library
* Move CMake logic to be set on libckw target
* Build CKW in parallel from SCons
Resolves: COMPMID-6297
Change-Id: I247a1f6ddf84a58032358a196574866b857d9bdc
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9834
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
* Define ckw::TensorStorage. The tensor storage represents the type of tensor memory object.
* Add helper functions for setting the CKW TensorComponent and TensorStorage as OpenCL kernel arguments.
* Refactor CL Image2D method for simpler image object creation.
Resolves: COMPMID-5784
Change-Id: I2d37d06783c1dc55f3b5692b44eb49b151f2401c
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9807
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-6299
Change-Id: I3b9c464e8cdc6c081472ec0aa6b738c7ccb18b49
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9759
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Add a 'CKW' option to Compute Library's Sconscript that invokes the Compute Kernel Writer subproject's CMake build and links CKW to the main library.
Resolves: COMPMID-6297
Change-Id: I8d45c8a950da5c13a15d39064636bb25ba7a2913
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9748
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Ramy Elgammal <ramy.elgammal@arm.com>
Dynamic-Fusion: Ramy Elgammal <ramy.elgammal@arm.com>
|
|
This change adds support for multi isa build with armv8-a as the
base micro architecture. To enable this, use 'arch=armv8a' and 'multi_isa=1'
build flags during scons build. This build option doesn't include
fp16 vector arithmetic. To include fp16 vector arithmetic, use 'arch=armv8.2-a'
and 'multi_isa=1' build option.
Signed-off-by: Sunita Nadampalli <nadampal@amazon.com>
Change-Id: Ib5ca61dc65603382baee53b3ec30b2b817beda3c
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9474
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Renames `experimental_fixed_format_kernels` build option to
`fixed_format_kernels`.
Adds documentation for the flag covering basics:
- What fixed-format kernels are
- Why they're needed
- Which backend they're for (i.e. CPU)
- Some pointers on how to use them.
Resolves: ONCPUML-1253
Change-Id: I428c98614c309c9ffc32d0f32daa24740f7cb967
Signed-off-by: Nathan John Sircombe <nathan.sircombe@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9523
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* Add an option in scons script to export compile_commands.json
file to support development using language server.
* Add .cache directory to the git ignore list. It is normally
used by clangd as the local cache.
Resolves: COMPMID-5940
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I8c2a1ac85942d34ada22adea3e7de2baf2189eb2
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9258
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* Do not link dl when os=windows
* Partially resolves MLCE-996
Change-Id: Ibc036cc69aa9b146f263eb69d64fcb89ace2c97c
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9040
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
* Removed BF16 validation tests for DepthConvert
* Revert back to using inline assembly to convert to/from BF16
* Resolves COMPMID-5800
Change-Id: I803b2ad19ead297417f780c97c5b724cca6b394c
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8929
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
* bfloat16 cause build errors when building arch=armv8a multi_isa=1
* Resolves COMPMID-5793
Change-Id: I92114f1134c8d7bebeec556c42cfde778f9ba5bd
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8871
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* Add SME/SME2 detection.
* Integrate SME2 implementation for:
- Normal convolution
- Winograd
- Depthwise convolution
- Pooling
Resolves: COMPMID-5700
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I2f1ca1d05f8cfeee9309ed1c0a36096a4a6aad5c
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8692
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* Resolves MLCE-942
Change-Id: I4e61e3712c7bc7e711b1fa280d7c3e73d08a57e3
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8407
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
* Resolves ARMCL-588
Change-Id: I0ae29e001fecbcf31b40fc51f8b25107456626de
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8337
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
|
|
Since Androidâ„¢ 13, the underlying NDK has deprecated system assembler
and favors integrated assembler instead
Please also see https://github.com/android/ndk/wiki/Changelog-r23
Resolves COMPMID-5410
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ib9fa8a22f6cdb5cb4f0095e15bf332484f709630
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7956
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-by: Ramy Elgammal <ramy.elgammal@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* scons arch=armv8.6-a translates to -march=armv8.6-a
* scons arch=armv8.6-a-sve translates to -march=armv8.6-a+sve
* scons arch=armv8.6-a-sve2 translates to -march=armv8.6-a+sve2
* Resolves COMPMID-5408
Change-Id: I0901e1de864d00109759509af7cc2b5c9ae1cd75
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7943
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
Partially resolves MLCE-739
Change-Id: Ice06a96d6a8a26b31e334ba4e697cd41d352b026
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7364
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-5381
Change-Id: I556e2269ff6350f58509624a3d3d94cb0853cb8d
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7882
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
* When build=native toolchain_prefix and compiler_prefix must be
set to "" instead of auto
* Resolves COMPMID-5395
Change-Id: I481ee4596e16d55d2a696af9124a0d06c916cef7
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7855
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
|
|
* Only print a warning for this build
* Fix the wording in documentation to avoid misunderstanding. User can
still run armv7a on Android, but we stop testing it and this build is
discouraged
Resolves COMPMID-5379
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I3d00baa2479671bcef8882db0e3d3cc3043d5811
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7838
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-5379
Change-Id: Ie2564b8ef029241e34b964de524c4a4c288a7846
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7735
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Currently it is counterintuitive to disable toolchain prefixes: we need
to pass an empty space to it; passing an empty string would not disable
prefixes but instead instruct the build script to use a set of default
prefixes.
With this patch we restore the intuitive approach of passing an empty
string "" to disable the prefix.
Resolves COMPMID-5353, COMPMID-5380
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I2fe84689df9093cf6baf507dde44ca5ebf61023b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7686
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
This is a No Functional Change Intended (NFCI) patch. It imports the
kernel in the code, but the interface to select them and expose the
format of the weight tensors to the user will be provided in a
subsequent patch.
Kernels and kernel selection code in arm_gemm has been provided
by David.Mansell <David.Mansell@arm.com>.
The kernels are not compiled in the library by default, but need to be
selected via the `scons` option `experimental_fixed_format_kernels=1`.
Resolves: ONCPUML-829
Signed-off-by: Francesco.Petrogalli@arm.com <francesco.petrogalli@arm.com>
Change-Id: If00ccb2b9b7221e01b214cf9783111226ccc8bf4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7380
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Related to: COMPMID-4985
Signed-off-by: SiCongLi <sicong.li@arm.com>
Change-Id: I5f2bd81abd6c90e6bf53068e21f751cdcc5732af
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7346
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Android NDKs >= r21 need the '-static-openmp' flag enabled when using openmp.
The check on the NDK version is performed by querying the compiler binary's clang version.
NDK versions <= r20 use clang 8 and below. Versions >= r21 use clang 9 and above
Resolves: COMPMID-5052
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I910f8d7a0a59866c06b16c1a856ea877bcbd7ad6
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7344
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
(cherry picked from commit 444b43a55bab37fa6dc8628c6283e54e422db3ad)
|
|
Resolves MLCE-739
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
Change-Id: I30a11393e928061c82a5c93d8ec195c04a0e838b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7279
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-5151
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: Ic4024d5cd4819fe917a1d49621f1866ae2e90a37
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7260
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves COMPMID-5133
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: Ice2ed60aa91042e1dc78a3548f8b960f185cb6e5
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7120
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves COMPMID-5127
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I2b1eefdf5d9a58a13295b27f2d66e461d9b9289c
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7086
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
|
|
* Add kernel selection at build time
* Modify filelist.json to allow files separation
as part of our kernel decoupling process.
Issues to address after this change will be merged:
(1) Remove SVE/SVE2 defines from already decoupled kernels
(2) Adapt the new file list structure (filelist.json)
resolves COMPMID-4996 and COMPMID-5048
Change-Id: I8c17a9d6b150bbc7d8c1f2ed38060be82b6aa904
Signed-off-by: Motti Gondabi <motti.gondabi@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7006
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
This reverts commit 10e88a7351 "Rework gemm_mm_reshaped_only_rhs_ kernels with new macros"
Resolves: COMPMID-5095
Signed-off-by: Ramy Elgammal<ramy.elgammal@arm.com>
Change-Id: I46e167882f072e7508b6101d295accb6e089e740
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7045
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Kevin Lo <kevlo@kevlo.org>
Change-Id: I6f29bdb55caeec8893f128fdd50bdcc3d058cb3c
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6905
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Comments-Addressed: Pablo Marquez Tello <pablo.tello@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-5012
Signed-off-by: SiCongLi <sicong.li@arm.com>
Change-Id: I7df7098b464f564cf7f3d83e10fe57e2788531a0
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6839
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
When building for Multi ISA the link command throws:
'argument list too long' error since the list string being
pass to the linker exceeds the ARG_MAX value. The solution is to
split the object list into two distinct static libraries and have them
link back together.
Prohibit unknown variable use.
The script now checks for unknown parameters.
Resolves: COMPMID-4921
Change-Id: I97a27e86f90a7cc680a3c487da1c468cd3e1084e
Signed-off-by: Motti Gondabi <motti.gondabi@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6847
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
- Enhance the SCons build system to support V8
SVE/SVE2 achitecture in a single binary
- Add additional filedefs.json to include build definitions
Resolves: COMPMID-4921
Signed-off-by: Motti Gondabi <motti.gondabi@arm.com>
Change-Id: Ie3c0ef444303270ba560ca3f43c6e22d50b86679
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6689
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Allow ACL to be built via a user provided JSON file containing operators, data types and data layouts.
Modify TFLite file to JSON file script to output data layouts.
Fix build issue with "fat_binary" and "high_priority" options.
Resolves: COMPMID-4697, COMPMID-4837
Signed-off-by: Freddie Liardet <frederick.liardet@arm.com>
Change-Id: I08d494151c98f804325707ffd922ffe216813023
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6427
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
|
|
Creates a list of operators their respective dependencies.
Alters the build system to walk-through them resolve the dependencies
and build Compute Library.
Removes the following unused kernels/functions:
-[NE|CL]MinMaxLayerKernel
-CLFillBorder
Resolves: COMPMID-4695,COMPMID-4696
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I35ebeef38dac25ec5459cfe9c5f7c9a708621124
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/357914
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Signed-off-by: Freddie Liardet <frederick.liardet@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6295
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Partially Resolves: COMPMID-4818
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: I47f2f109e1f2442607bb70a36656c69e853d330e
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6309
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-4655
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I1c1398b39da6da089b288d032074b270d87510c4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6010
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
- Introduce Fp32 kernels with internal calculations in Bfloat16 when
fast_mode is enabled
- Improve kernel selection heuristics
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Now core and runtime files are build in the same library,
libarm_compute.so and libarm_compute-static.a. Create a dummy
core library for not breaking backwards compatibility.
Update documentation on fat binaries and new high priority
library.
Fixed issue on scons when using the install_dir feature.
Change-Id: I5a8a6bbe2808243eba07fd135496995259d8702f
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5845
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
A smaller core library is created using a subset of the operators.
Changed the structure of filelist.json in order to include more
information about the kernels and make the selection easier.
Resolves: COMPMID-4514
Change-Id: I079ca7d8e64346174eebdd13b834e1dd4dc36ca2
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5786
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Changes our build system to allow building both Neon(TM) and SVE
kernels and package them in the same binary. This will allow
runtime selection of the underlying architecture.
Adds new build option, fat_binary, for enabling this feature.
Change-Id: I8e8386149773ce28e071a2fb7ddd8c8ae0f28a4a
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5704
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
* This commit removes the tracing code which has not been maintained for a few releases.
* Resolves MLCE-445
Change-Id: I14793c82fe58ffef0cf936edf4af077b5dde85f8
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5455
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolve COMPMID-4377, COMPMID-4379
Change-Id: I302f08b5bf0afb5295d31843fea20181d9283658
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5435
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I9286dd199670e6311aee3c040d7b02a401522dd4
Signed-off-by: Slava Barinov <v.barinov@samsung.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5369
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Resolves: COMPMID-4299
Change-Id: Ie6a52c1371b9a2a7b5bb4f019ecd5e70a2008567
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5338
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|