ComputeLibrary.git -

Age	Commit message (Expand)	Author
2021-01-21	Check for FP16 CPU support in optimized pooling kernels	Michele Di Giorgio
2021-01-21	Fix softmax SVE compiling failure without SVE2 support	Sheri Zhang
2021-01-21	Make Sub kernel and operator stateless	Sheri Zhang
2021-01-20	Integrate improved pooling layer on NEON	Michele Di Giorgio
2021-01-20	Make all CL Concatenate kernels and functions state-less	Michele Di Giorgio
2021-01-20	Update documentation for SVE/SVE2 support	Sheri Zhang
2021-01-20	Direct convolution fix for quantized data type	Gian Marco Iodice
2021-01-19	Fix doxygen references to new kernels	Michele Di Giorgio
2021-01-19	Make memset/copy functions state-less	Georgios Pinitas
2021-01-19	Remove padding from direct convolution - OpenCL	Gian Marco Iodice
2021-01-19	Make Add kernel and operator stateless	Sheri Zhang
2021-01-19	LOGICAL_NOT fail	Teresa Charlin
2021-01-18	Make Concatenate kernels and operator stateless	Georgios Pinitas
2021-01-18	Add SVE for Softmax	Michalis Spyrou
2021-01-18	Decouple data types of elementwise kernels	Sang-Hoon Park
2021-01-18	Cycle estimate-based kernel selection for dot product quantized s8/u8 kernels	Georgios Pinitas
2021-01-18	Add explicit cast to fix gcc10 build error	Sang-Hoon Park
2021-01-17	Add missing std headers	Sang-Hoon Park
2021-01-15	Introduce threshold for NEON floating-point SOFT_RELU activation	Michele Di Giorgio
2021-01-15	Release winograd transformed weights if not needed on NEON	Georgios Pinitas
2021-01-15	Fix build error for gcc 10.2+	Sang-Hoon Park
2021-01-15	[Nightly Failure] Fix DeconvolutionLayer OpenCL kernel compilation	Giorgio Arena
2021-01-15	Add support for Armv8-R AArch64 build	Sang-Hoon Park
2021-01-14	Remove OpenCL padding CLTransposeKernel	Manuel Bottini
2021-01-14	Add missing INTEGER type in nn driver	Michalis Spyrou
2021-01-13	Add support for macOS	Georgios Pinitas
2021-01-13	Fix wrong file inclusion in QLSTMLayerNormalization reference	Georgios Pinitas
2021-01-13	Add tolerance for quantized activations computed in float	Michele Di Giorgio
2021-01-13	Alter tolerance in QuantizationLayer to use int8_t for asymmetric signed	Georgios Pinitas
2021-01-13	Remove padding for CLArgMinMaxLayerKernel and fix CLRange mismatches	Giorgio Arena
2021-01-13	Add SVE2 kernels for quantized elementwise operations	Sang-Hoon Park
2021-01-13	[Nightly Failure] Fix CLDepthwiseConvolutionLayer 3x3 QASYMM8 on Midgard	Giorgio Arena
2021-01-13	Remove OpenCL padding CLFloorKernel	Manuel Bottini
2021-01-12	Add SVE support for non-quantized elementwise operations	Sang-Hoon Park
2021-01-12	Add SVE support and decouple data type for NEScaleKernel	Sheri Zhang
2021-01-12	Add meta-data to express dynamic shapes in ITensorInfo	Georgios Pinitas
2021-01-11	Make CpuActivation stateless	Georgios Pinitas
2021-01-11	Remove OpenCL padding: CLROIAlignLayerKernel	Manuel Bottini
2021-01-08	[Nightly Failure] Fix NEIm2Col argument validation errors	Giorgio Arena
2021-01-08	Make CpuFloorKernel kernel stateless	Georgios Pinitas
2021-01-08	[Nightly Failure] Fix OpenCL kernel compilation for CLRange	Giorgio Arena
2021-01-08	Resolve merge conflicts between new fills and new fp16 generator	Giorgio Arena
2021-01-08	Generalization of CLTuner	Manuel Bottini
2021-01-08	Add an SVE implementation of the Leaky ReLU activation function for qasymm8 a...	arngra01
2021-01-07	Fix fill() for FP data type in fixtures - Part 2	Giorgio Arena
2021-01-07	[Nightly Failure] Fix ColorConvert empty coordinates error	Giorgio Arena
2021-01-07	Add SVE support to elementwise unary kernels	Sang-Hoon Park
2021-01-07	Review all shapes in datasets to account for padding removal Part 3	SiCong Li
2021-01-07	Generalize custom uniform generator for floating point data types with 16 bits	Giorgio Arena
2021-01-07	Clean up macro definitions in arm_compute headers	Giorgio Arena