aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-06-28Fix compute kernel writer build warningsViet-Hoa Do
Partially resolves: COMPMID-6283 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I40cdbfd30abca2016f4caaa41a24350d1ff35c4c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9830 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-06-27Compute kernel writer API and prototypeViet-Hoa Do
* Add the public API for compute kernel writer. * Use the prototype as the implementation of the public API. Resolves: COMPMID-5790 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I9d80e15325e1d953feb87c1f2eb61a587bb9ab5e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9814 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-26Add helpers to set CKW tensor components as OpenCL kernel argumentsJakub Sujak
* 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>
2023-06-26Remove dependency on fp16 definitions from some core include filesMatthew Bentham
This significantly improves the compilation times for parts of the core library that just need a definition of float16_t rather than access to all of the fp16 intrinsics. Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I5da1c6b0df0dd87d1d17948cd2e9b7375874f455 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/529385 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9781 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>
2023-06-26Use MatMul in fully connected layer with dynamic weights when supportedMohammed Suhail Munshi
- Use MatMul kernels in FC layer when using dynamic weights without broadcasting or bias. - Fix minor typo in IClMatMulNativeKernelConfig.h Partially Resolves : [COMPMID-6193] Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Change-Id: Id494062b5b4f4e75ff9714c202dde941955afa52 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9797 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-23Implement FP32/FP16 MatMul NT/T kernel using the MMUL extensionRamy Elgammal
Resolves COMPMID-6195 Signed-off-by: ramy.elgammal@arm.com <ramy.elgammal@arm.com> Change-Id: I8e85fe73308ed84ebb142d6d6d1562b62dddfaa5 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9819 Reviewed-by: SiCong Li <sicong.li@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-06-23Address the issues with the ACL coverage pipeline failures related to matmul.Renato Arantes
Signed-off-by: Renato Arantes <renato.arantes@arm.com> Change-Id: I98de659d1289c930e366727d4799f0dacc8121ab Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9782 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-06-23Fix doxygen warningsramy.elgammal@arm.com
Resolves: COMPMID-6312 Signed-off-by: ramy.elgammal@arm.com <ramy.elgammal@arm.com> Change-Id: I9f68ccd2edb8c4d03fec19e6b9c29609d4833342 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9806 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>
2023-06-22Bazel and CMake optional fp16 supportDavid Svantesson
Resolves ONCPUML-1274 Signed-off-by: David Svantesson <david.svantesson@arm.com> Change-Id: I1d189596cfce5be87a18c8065d683700b3c9960f Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9745 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>
2023-06-21Include CKW sources in Android.bpJakub Sujak
Resolves: COMPMID-6318 Change-Id: I447cd46a7e86da5858d264fc10c72d194d728085 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9804 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
2023-06-21Fix CPU depthwise convolution in case of large paddingViet-Hoa Do
* Avoid the assembly kernels to be used when the padding is greater than the kernel shape. Resolves: COMPMID-6280 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: Ibe0820018c97f4481bf318397b797ec7b351a1d5 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9802 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>
2023-06-21Enable vmfa in arm7va/aarch32 when presentPablo Marquez Tello
* vfma is an extension on armv7a and it can be enabled with -mfpu=neon-vfpv4 * Resolves MLCE-1079 Change-Id: Id455c39ee4feb8d3cdc4515c8307eb8a5d6e093b Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9795 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>
2023-06-20Implement CLConstantTileGian Marco Iodice
- Create tile object to store constant variables - Add unit tests for the CLConstantTile - Extend unit test for CLTile Resolves COMPMID-5786 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: I351d8b88327e071791b781a04a6ab4990c89c04d Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9794 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
2023-06-20Deprecate legacy libarm_compute_coreJakub Sujak
This library is an artifact of Compute Library's legacy library architecture and no longer serves any purpose. Users must no longer link their applications to this library and instead link only to the main `libarm_compute` library to maintain full functionality. Resolves: COMPMID-6300 Change-Id: I7c222f511174ce9b0cfde94cf8f90da4a89f2a8b Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9760 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-19Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extensionSiCong Li
Resolves COMPMID-6194 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ie45e2aa9533948b2e5235563cef1d3834494eccf Signed-off-by: SiCong Li <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9739 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>
2023-06-16Add Fused Activation to OpenCL MatMulMohammed Suhail Munshi
- Added fused activation to MatMul function interface - Added fused activation to CL backend - Includes tests for supported Activation Functions in MatMul Resolves: [COMPMID-6192] Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Change-Id: Ie103212b600b60699eaf6a6394d609e6e1f5aba6 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/522465 Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9714 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-16Escape double qoutes in embedded version stringMatthew Bentham
Allows for double quotes to be used in build options without breaking compilation of Version.cpp Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: If503111d46419022d9a3255ab6c9774b75c35b90 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/528085 Reviewed-by: Matthew Bentham <matthew.bentham@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Release-Notes: Jakub Sujak <jakub.sujak@arm.com> Release-Notes: Gunes Bayir <gunes.bayir@arm.com> Release-Notes: Ramy Elgammal <ramy.elgammal@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9780 Benchmark: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-06-16Fix potential infinite recursion in bfloat16 printerMatthew Bentham
Change-Id: I5f186749caf6e534d71b41666a276b47f4d7c454 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/528134 Reviewed-by: Matthew Bentham <matthew.bentham@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9783 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>
2023-06-15Break up Utils.h a bit to reduce unused code being included everywhereMatthew Bentham
Move some maths-related things from Utils.h to new Math.h header in utils/math. Move some routines used for Tensor shape validation to Validate.h Change-Id: I8ce89fe03ec3ae1b61d1a80c282b8b91eea0cfb3 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/524783 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9743 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>
2023-06-15Break up arm_compute/core/Types.h a bitMatthew Bentham
Split some of the larger types with inlined code into their own header files, so that the implementation of them needn't be included everywhere. Change-Id: Id3ec2d42efbd33cedb55705a5a24e1b90c8b7a01 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/524782 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9757 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-14Add a Getting Started guide to CKW READMEJakub Sujak
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>
2023-06-12Add multi-sketch support for dynamic fusionViet-Hoa Do
* Tensors are owned by workload context instead of workload sketch so that they can be used by multiple sketches. * Add an integration test for multi-sketch case. Resolves: COMPMID-6148 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I37d0de5ac103fb2a85020aa1c26e49eb304f47b7 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9706 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-12Refactor activation LUT computationPablo Marquez Tello
* Moving the code out of Types.h will help with the compilation time. * Added LUT support for all other activation functions. * Resolves COMPMID-6292 Change-Id: I1b5f0b21f03237447163276b8796b2aeb3fdd45c Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9749 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-12Enable building Compute Kernel Writer from SconsJakub Sujak
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>
2023-06-09Enable conversion of F32 NumPy files to F16Gian Marco Iodice
Resolves COMPMID-6277 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: Ibbe5eb0869f701d4329782101ee7336948350269 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9747 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>
2023-06-09Reorder destructor in srcDavid Svantesson
Signed-off-by: David Svantesson <david.svantesson@arm.com> Change-Id: Iaed0933d665bd98829be49b9df11653d4d74081c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9746 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-06-09Added int8 support in LeakyRelu/LUT kernel.Pablo Marquez Tello
* Resolves COMPMID-6292 Change-Id: I15a0ad1c298ff53dd111fda76ef70872aaadac3b Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9740 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-07Fix build error for armv7aPablo Marquez Tello
* Removed the BF16 code related to the linker error for armv7a * Resolves COMPMID-6288 Change-Id: I2dcedf5c0ba684f8e31865985899bf00b9390c9e Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9736 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: <michael.tyler@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-06-07Fix guards for FP16 depthwise kernelsMichael Tyler
Resolves COMPMID-6291 Change-Id: Ibe5da8cfcf6d7fd994ddf7759efd0e773accdeb2 Signed-off-by: Michael Tyler <michael.tyler@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9731 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-06-06Fix ScaleKernel validate method.Pablo Marquez Tello
* Validate returns an error if the number of channels of the input tensor is not 1. With this change we generate an error if scale is called with any of these formats: Format::UV88, Format::RGB888, Format::RGBA8888,Format::YUV444, Format::YUYV422, Format::NV12, Format::NV21,Format::IYUV, Format::UYVY422 * Resolves ARMCL-631 Change-Id: If9d8b9d95332994920def55d8faae9dbf4213f79 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9579 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-06-05Update CPU kernel implementations and guard directivesMichael Tyler
Resolves COMPMID-6023 Change-Id: I868975d14c4f98af6716726feda22405a6a4c891 Signed-off-by: Michael Tyler <michael.tyler@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9686 Tested-by: Arm Jenkins <bsgcomp@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>
2023-06-01Add CMakeLists to Compute Kernel WriterJakub Sujak
Resolves: COMPMID-6276 Change-Id: Id6d6d8c1a92cf2b11c1240e044d31f386fbda61e Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9700 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-05-31Fix number of dimensions changed after transposeViet-Hoa Do
Partially resolves: IVGCVSW-7759 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I08a3e34db2c3980709718c5a8fc8783dd467d0fe Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9705 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-24Prepare the basic types for the compute kernel writer (CKW)Gian Marco Iodice
- Add TensorInfo - Add TileInfo - Add CLTile - Add basic utility methods to get tensor components - Add unit tests Resolves COMPMID-5782, COMPMID-5785 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: I5e590bddd240d2f1fc876cac7129947558d7d53b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/486221 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9687 Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-05-18Printing out the rerun command of each failed testcaseRamy Elgammal
- After a testcase fail, print the arm_compute_validation command with filter specified and seed to rerun. Resolves: COMPMID-5916 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: I0c8214e7d3b61f01ce16f50499c29bfe08b6a885 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9673 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@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>
2023-05-17Move lut kernel to sve2 categorySiCong Li
This specific Lut kernel uses sve2 instructions Resolves: COMPMID-6268 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I44fa3812e96fa79b3d1e1e3a31d587581f59f0e1 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9675 Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-17Revert "Check for nullptr when failing to load OpenCL libraries"Omar Al Khatib
This reverts commit 9d254610ef3072263ac5c20eed906157e8869b3d. Reason for revert: Causing High Impact failure in Coverity Change-Id: I7a3b963cc13c0eea856a15451ffed8c4d4a62e75 Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9643 Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: SiCong Li <sicong.li@arm.com>
2023-05-16Raise an erratum about sporadic CLArgMinMax nightly failureSiCong Li
Resolves COMPMID-6248 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I2a7549c227b9a8e59e8fd85d88a18f631b1f6900 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9663 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-05-16Check for nullptr when failing to load OpenCL librariesJakub Sujak
Resolves: COMPMID-6272 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Change-Id: I4b4ff4eeb909ac95c63d1f2d2081f2be9ade2295 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9662 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>
2023-05-15Raise abs_tolerance number for CL/DirectConvolution3D fp16 testsRamy Elgammal
Resolves: COMPMID-6255 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: I602bcbf58f78e7384789cd077cfc3b549d53463e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9637 Benchmark: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-15Raise tolerance number for NEDeconvolutionLayer fp16 testsSiCong Li
Tolerance number was too strict for fp16 Resolves COMPMID-6254 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I42a5df21c2545c38ea7234497effd232b43aabf8 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9635 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Omar Al Khatib <omar.alkhatib@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-12Move matmul heuristics files from Gemm to MatMul in filelist.jsonRamy Elgammal
Resolves: COMPMID-6253 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: Id5497ff3ba1346511b8d4c4c839a7fec19438e1f Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9623 Reviewed-by: SiCong Li <sicong.li@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-05-12Update release notes for the 23.05 release.Omar Al Khatib
Partially resolves: [COMPMID-5888] Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Change-Id: I0313af488050d2babb47b3e164c111e11d84021f Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9605 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-05-12Fix performance regression in FP16 DeconvolutionJakub Sujak
The previous heuristic for selecting the Deconvolution method with FP32 input data introduced a performance regression for FP16. A simple fix ensures the previous heuristic applies to FP32 types only. Resolves: COMPMID-6027 Change-Id: I77ca6c9c72534057a3967db58924a972b0efb09f Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9616 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-05-12Update README to refer to the 23.05 releaseOmar Al Khatib
Partially resolves : [COMPMID-5888] Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Change-Id: Iff4611e7ac828d36bcb24c591b2cdc40fcfc1147 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9617 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>
2023-05-11Fix invalid vector length in CLViet-Hoa Do
Resolves: COMPMID-6252 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I97ddf8a6c83bc2621abc712094db6bc0fe3d97b1 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9620 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-11Remove check for bias in CPU Depthwise ConvolutionJakub Sujak
The Depthwise convolution operation is not required to have a bias, hence the check may fail unexpectedly. Resolves: COMPMID-6250 Change-Id: I2844ffde6139f79ade118d756c930318f16fbe50 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9615 Reviewed-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-by: Sang Won Ha Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-11Fix undefined ClMatMulNativeKernel::validate for high priority buildSiCong Li
Resolves COMPMID-6249 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I910ecec57279ecc20aeac2d24b0caa27f688f693 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9612 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-05-10Remove inclusion of NEReorderKernel header from NEReorderLayerRamy Elgammal
Resolves: COMPMID-6235 Change-Id: I7a094a23244286090415ee2788632cfa7bd6c037 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9608 Benchmark: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-05-10Update SONAME_VERSION in SConscriptOmar Al Khatib
Partially resolves: [COMPMID-5888] Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Change-Id: I8eb5a7a37cb39f4fd450fc4da4e15c4039aa5ac0 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9596 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>