diff options
author | Giuseppe Rossini <giuseppe.rossini@arm.com> | 2020-02-17 17:22:49 +0000 |
---|---|---|
committer | Giuseppe Rossini <giuseppe.rossini@arm.com> | 2020-02-20 14:33:59 +0000 |
commit | 2209921c38e3509668a80313c04440a164910f89 (patch) | |
tree | 1367664b27904f5e667499afae8f0b1e3ae8740d /docs/00_introduction.dox | |
parent | 84886987b0c2067d9bb32d9b427dab4f834ed180 (diff) | |
download | ComputeLibrary-2209921c38e3509668a80313c04440a164910f89.tar.gz |
COMPMID-3192: Update release notes
Change-Id: Ia78cf1ec6cfcf047595ac6f9a866c36918ffe7be
Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2744
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'docs/00_introduction.dox')
-rw-r--r-- | docs/00_introduction.dox | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index d61eab834f..379b0aa105 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -255,9 +255,10 @@ v20.02 Public major release - @ref CLGEMMConvolutionLayer - @ref CLGEMMLowpMatrixMultiplyCore - @ref CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel + - @ref CLGEMMLowpMatrixMultiplyNativeKernel - @ref NEActivationLayer - @ref NEComparisonOperationKernel - - @ref NEConvolutionLayer. + - @ref NEConvolutionLayer - @ref NEDepthwiseConvolutionLayer - @ref NEDepthwiseConvolutionLayer3x3Kernel - @ref NEDirectConvolutionLayerOutputStageKernel @@ -270,18 +271,23 @@ v20.02 Public major release - @ref NEPixelWiseMultiplication - @ref NEPoolingLayer - @ref NEPReluLayer - - Added support for QUANT8_PER_CHANNEL_SYMM in: + - Added support for QSYMM8_PER_CHANNEL in: - @ref NEDepthwiseConvolutionLayer3x3Kernel - Added support for split sizes in: - @ref CLSplit - @ref NESplit - New OpenCL kernels / functions: - @ref CLFill - - @ref CLGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel / CLGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint + - @ref CLGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel / @ref CLGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint - New NEON kernels / functions: - @ref NEFill - - @ref NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel / NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint + - @ref NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel / @ref NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint + - Deprecated NEON functions / interfaces: + - @ref CLDepthwiseConvolutionLayer3x3 + - @ref NEDepthwiseConvolutionLayerOptimized + - @ref PoolingLayerInfo constructors without Data Layout. - Added support for quantization with multiplier greater than 1 on NEON and CL. + - Added support for quantized inputs of type QASYMM8_SIGNED and QASYMM8 to @ref CLQuantizationLayer. - Added the ability to build bootcode for bare metal. - Added support for generating synthetic QASYMM8 graphs. - Added support for F16 datatype in VGG16. |