- Various optimisations.
- Upgrade C++ standard to C++14
- Add macOS support
+ - Add Armv8-R AArch64 architecture support
- Add SVE/SVE2 support for:
- @ref NEScaleKernel
- @ref NEActivationLayer
- @ref NEArithmeticAddition
- @ref NEBatchNormalizationLayerKernel
- - NELogits1DSoftmaxKernel
- - NELogits1DMaxKernel
- - NEElementwiseUnaryKernel
+ - @ref cpu::kernels::CpuLogits1DSoftmaxKernel
+ - @ref cpu::kernels::CpuLogits1DMaxKernel
+ - @ref cpu::kernels::CpuElementwiseUnaryKernel
- Remove padding from OpenCL kernels:
- @ref CLDirectConvolutionLayerKernel
- @ref CLArgMinMaxLayerKernel
- @ref CLScaleKernel
- @ref CLSelectKernel
- @ref CLBitwiseKernel
- - ClFloorKernel
+ - @ref opencl::kernels::ClFloorKernel
- @ref CLTransposeKernel
- Deprecate functions in CLTuner:
- add_lws_to_table