aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGiuseppe Rossini <giuseppe.rossini@arm.com>2020-02-17 15:57:15 +0000
committerGiuseppe Rossini <giuseppe.rossini@arm.com>2020-02-17 15:59:32 +0000
commitcc01dc3875dae30916fd18c6bb949426725ad612 (patch)
tree2a36623bd73cdbc4027a0b1f94da2991ce9a07ec
parent96b1b9723e7f2fda12244f3133661e687f58fef3 (diff)
downloadComputeLibrary-cc01dc3875dae30916fd18c6bb949426725ad612.tar.gz
Add Release notes to the documentation
Change-Id: I570d02b76439d054bf5aa807d78b808e03d71df3 Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
-rw-r--r--docs/00_introduction.dox43
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.