From bf193548b3afdee7db154c2fa5625e2194e51de2 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Thu, 22 Aug 2019 10:10:52 +0100 Subject: COMPMID-2555: Release notes 19.08 Change-Id: I3ff6b7580c7cb7a9df9056d17e41ff553479dd53 Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/1787 Reviewed-by: Michalis Spyrou Comments-Addressed: Arm Jenkins Tested-by: Arm Jenkins --- docs/00_introduction.dox | 46 +++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 41 insertions(+), 5 deletions(-) diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 09a847286a..9c8eaf2733 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -239,11 +239,47 @@ If there is more than one release in a month then an extra sequential number is v19.08 Public major release - Various bug fixes. - Various optimisations. - - Deprecated functions/interfaces - - Altered @ref QuantizationInfo interface to support per-channel quantization. - - The @ref NEDepthwiseConvolutionLayer3x3 will be replaced by @ref NEDepthwiseConvolutionLayerOptimized to accommodate for future optimizations. - - Removed inner_border_right and inner_border_top parameters from @ref CLDeconvolutionLayer interface - - Removed inner_border_right and inner_border_top parameters from @ref NEDeconvolutionLayer interface + - Deprecated NEON functions + - NEDepthConcatenateLayer + - NEWidthConcatenateLayer + - Deprecated OpenCL kernels / functions + - CLDepthConcatenateLayer + - CLGEMMInterleave4x4Kernel / CLGEMMInterleave4x4 + - CLGEMMTranspose1xWKernel / CLGEMMTranspose1xW + - CLWidthConcatenateLayer + - New NEON kernels / functions: + - @ref NECast + - @ref NELSTMLayerQuantized + - @ref NEPReluLayer + - @ref NEBatchConcatenateLayerKernel + - @ref NEDepthToSpaceLayerKernel / @ref NEDepthToSpaceLayer + - @ref NEDepthwiseConvolutionLayerNativeKernel + - @ref NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel + - @ref NEMeanStdDevNormalizationKernel / @ref NEMeanStdDevNormalizationLayer + - @ref NESpaceToDepthLayerKernel / @ref NESpaceToDepthLayer + - New OpenCL kernels / functions: + - @ref CLLSTMLayerQuantized + - @ref CLPReluLayer + - @ref CLBatchConcatenateLayerKernel + - @ref CLDepthToSpaceLayerKernel / @ref CLDepthToSpaceLayer + - @ref CLGEMMLowpMatrixMultiplyNativeKernel + - @ref CLGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel + - @ref CLGEMMMatrixMultiplyNativeKernel + - @ref CLMeanStdDevNormalizationKernel / @ref CLMeanStdDevNormalizationLayer + - @ref CLSpaceToDepthLayerKernel / @ref CLSpaceToDepthLayer + - New examples: + - neon_opticalflow + - cl_cache + - neon_permute + - Enable the fusion of batch normalization with convolution and depthwise convolution layer for FP32 in the graph API (OpenCL only) + - Added support for fusing activation function and broadcast addition with the matrix multiplication for FP32 (OpenCL only) + - Re-factored the depthwise convolution layer kernel on NEON for generic cases + - Added an optimized depthwise convolution layer kernel for 5x5 filters (NEON only) + - Added support to enable OpenCL kernel cache. Added example showing how to load the prebuilt OpenCL kernels from a binary cache file + - Altered @ref QuantizationInfo interface to support per-channel quantization. + - The @ref NEDepthwiseConvolutionLayer3x3 will be replaced by @ref NEDepthwiseConvolutionLayerOptimized to accommodate for future optimizations. + - Removed inner_border_right and inner_border_top parameters from @ref CLDeconvolutionLayer interface + - Removed inner_border_right and inner_border_top parameters from @ref NEDeconvolutionLayer interface v19.05 Public major release - Various bug fixes. -- cgit v1.2.1