ComputeLibrary.git -

Age	Commit message (Expand)	Author
2023-03-13	arm_gemm: Add SME2 FP16 kernels.	David Mansell
2023-03-13	[ONCPUML-1174] Allow src/weights mismatch for fixed format	Jonathan Deakin
2023-03-08	Add support for arbitrary parameters for CPU Gather	Viet-Hoa Do
2023-03-07	Add sigmoid and tanh for dynamic fusion	Viet-Hoa Do
2023-03-07	Add exporting compile_commands.json file	Viet-Hoa Do
2023-03-07	GEMM: SME: Allow threading for quantized GEMMs.	David Mansell
2023-03-07	Resolve the presence of variables that are unused in release mode in Dynamic ...	Omar Al Khatib
2023-03-06	Fix LWS search space used by CLTuner	SiCong Li
2023-03-03	Add weights_info as optional input for NEDeconvolutionLayer	Annop Wongwathanarat
2023-03-03	NEGEMMLowpMatrixMultiplyCore should be configured for optimized int8 kernel.	Ethan Doe
2023-03-02	Fix direct conv2d in dynamic fusion	Viet-Hoa Do
2023-03-01	Add support for kernel indices in Maxpool	Adnan AlSinan
2023-02-28	Add an option to use lowest for max-pooling	Adnan AlSinan
2023-02-28	Add MatMulInfo Information class to ComputeLibrary	Mohammed Suhail Munshi
2023-02-27	Add build option to disable threads hint	Viet-Hoa Do
2023-02-24	Fixes for CMake and Bazel builds, tests failing in scons	David Svantesson
2023-02-22	Fix configuration files required for Bazel and CMake builds	Gunes Bayir
2023-02-21	Add Microsoft Windows® trademarks	Jakub Sujak
2023-02-15	Fix Intermittent Neon™ ReduceMean QASYMM8 Mismatch	Mohammed Suhail Munshi
2023-02-15	Fix clang-tidy error	Jakub Sujak
2023-02-14	Add absolute tolerance to f16 CLConv3D validation tests	SiCong Li
2023-02-14	Extend skip upsampling for deconvolution for non-1x1 kernels	Annop Wongwathanarat
2023-02-14	Fix convolution layer fixture	Viet-Hoa Do
2023-02-14	Add missing cpu feature printouts during tests	Gunes Bayir
2023-02-10	Update release version and change log documentation	Jakub Sujak
2023-02-10	Fix DeconvolutionLayer tolerance issues in FP16 tests	Gunes Bayir
2023-02-10	Update release version and change log documentation	Jakub Sujak
2023-02-10	Remove legacy dynamic fusion example from documentation	Jakub Sujak
2023-02-10	Update README	Jakub Sujak
2023-02-10	Update SONAME_VERSION in SConscript	Jakub Sujak
2023-02-09	Fix performance regression in Transposed Convolution	Gunes Bayir
2023-02-08	Update CPU kernels to remove x19 and w19	Michael Tyler
2023-02-08	Add support for dilation > 1 in assembly DepthwiseConvolution	Pablo Marquez Tello
2023-02-03	Fix armv7a failing GEMMConvolutionLayer tests	Mohammed Suhail Munshi
2023-02-03	Disable AddMulAdd armv7a tests	Gunes Bayir
2023-02-02	Update recommended NDK to r20b in the documentation	SiCong Li
2023-02-01	Fix GEMMLowp/Batched MatMul mismatches on CPU	Mohammed Suhail Munshi
2023-02-01	Add new operator AddMulAdd for Neon™ backend for Float/Quantized types	Gunes Bayir
2023-02-01	Add Subtraction operator to Dynamic Fusion interface	Ramy Elgammal
2023-02-01	Remove fixed format strides hack	Jonathan Deakin
2023-01-31	Fixed clang-cl linker errors	Pablo Tello
2023-01-31	Add Multiplication operator (FP only) to Dynamic Fusion Interface	Jakub Sujak
2023-01-31	Bazel and CMake builds	David Svantesson
2023-01-31	Sync tolerance number of dynamic fusion direct conv2d with the current library	SiCong Li
2023-01-30	Skip upsampling for deconvolution when not needed	Annop Wongwathanarat
2023-01-30	Fixed build error for Windows.	Pablo Tello
2023-01-26	Fix num_threads_hint() on macos.	Pablo Marquez Tello
2023-01-25	Implement dynamic fusion softmax operator	Ramy Elgammal
2023-01-24	Change dynamic fusion API to return destination tensor info	Gunes Bayir
2023-01-23	Fix performance regression when stride equal to kernel size	Gunes Bayir