diff options
| -rw-r--r-- | docs/00_introduction.dox | 43 |
1 files changed, 42 insertions, 1 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index e85d2b2efb..57f59632a5 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -1,5 +1,5 @@ /// -/// Copyright (c) 2017-2019 ARM Limited. +/// Copyright (c) 2017-2020 ARM Limited. /// /// SPDX-License-Identifier: MIT /// @@ -246,6 +246,47 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog +v20.02 Public major release + - Various bug fixes. + - Various optimisations. + - Update recommended android toolchain to 17c. + - Added new data type QASYMM8_SIGNED support for: + - CLDepthwiseConvolutionLayer + - CLDepthwiseConvolutionLayer3x3 + - CLElementWiseOperations + - CLGEMMConvolutionLayer + - CLGEMMLowpMatrixMultiplyCore + - CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel + - CLGEMMLowpOutputStage + - NEActivationLayer + - NEComparisonOperationKernel + - NEConvolutionLayer. + - NEDepthwiseConvolutionLayer + - NEDepthwiseConvolutionLayer3x3Kernel + - NEDirectConvolutionLayerOutputStageKernel + - NEElementwiseMax + - NEElementwiseMin + - NEElementwiseSquareDiff + - NEFullyConnectedLayer + - NEGEMMLowpOutputStage + - NEGEMMMatrixVectorMultiplyKernel + - NEPixelwiseMultiplication. + - NEPoolingLayer + - NEPReluLayer + - Added support for QUANT8_PER_CHANNEL_SYMM in: + - @ref NEDepthwiseConvolution 3x3 + - Added support for split sizes in: + - @ref CLSplit + - @ref NESplit + - New OpenCL functions: + - @ref CLFill + - New NEON functions: + - @ref NEFill + - Added support for quantization with multiplier greater than 1 on NEON and CL. + - Added the ability to build bootcode for bare metal. + - Added support for generating synthetic QASYMM8 graphs. + - Added support for F16 datatype in VGG16. + v19.11.1 Public maintenance release - Fix offset calculation in NEReductionOperationKernel. - Fix data layout in NEScaleKernel for nhwc. |