From ff850937ddfd3095b3cbe32e5c255817e5ccfeda Mon Sep 17 00:00:00 2001 From: Gian Marco Date: Mon, 11 Dec 2017 12:37:17 +0000 Subject: COMPMID-741 - Changelog for major release 17.12 Change-Id: If71190e398217ca6ca44df822554998d047b79db Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/112716 Reviewed-by: Anthony Barbier Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com --- docs/00_introduction.dox | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ docs/Doxyfile | 3 ++- 2 files changed, 57 insertions(+), 1 deletion(-) (limited to 'docs') diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index bf43b3abb3..4d6fafa980 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -155,6 +155,61 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog +v17.12 Public major release + - Most machine learning functions on OpenCL support the new data type QASYMM8 + - Introduced logging interface + - Introduced opencl timer + - Reworked GEMMLowp interface + - Added new NEON assembly kernels for GEMMLowp, SGEMM and HGEMM + - Added validation method for most Machine Learning kernels / functions + - Added new graph examples such as googlenet, mobilenet, squeezenet, vgg16 and vgg19 + - Added sgemm example for OpenCL + - Added absolute difference example for GLES compute + - Added new tests and benchmarks in validation and benchmark frameworks + - Added new kernels / functions for GLES compute + + - New OpenGL ES kernels / functions + - @ref arm_compute::GCAbsoluteDifferenceKernel / @ref arm_compute::GCAbsoluteDifference + - @ref arm_compute::GCActivationLayerKernel / @ref arm_compute::GCActivationLayer + - @ref arm_compute::GCBatchNormalizationLayerKernel / @ref arm_compute::GCBatchNormalizationLayer + - @ref arm_compute::GCCol2ImKernel + - @ref arm_compute::GCDepthConcatenateLayerKernel / @ref arm_compute::GCDepthConcatenateLayer + - @ref arm_compute::GCDirectConvolutionLayerKernel / @ref arm_compute::GCDirectConvolutionLayer + - @ref arm_compute::GCDropoutLayerKernel / @ref arm_compute::GCDropoutLayer + - @ref arm_compute::GCFillBorderKernel / @ref arm_compute::GCFillBorder + - @ref arm_compute::GCGEMMInterleave4x4Kernel / @ref arm_compute::GCGEMMInterleave4x4 + - @ref arm_compute::GCGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::GCGEMMMatrixAdditionKernel / @ref arm_compute::GCGEMMMatrixMultiplyKernel / @ref arm_compute::GCGEMM + - @ref arm_compute::GCGEMMTranspose1xWKernel / @ref arm_compute::GCGEMMTranspose1xW + - @ref arm_compute::GCIm2ColKernel + - @ref arm_compute::GCNormalizationLayerKernel / @ref arm_compute::GCNormalizationLayer + - @ref arm_compute::GCPixelWiseMultiplicationKernel / @ref arm_compute::GCPixelWiseMultiplication + - @ref arm_compute::GCPoolingLayerKernel / @ref arm_compute::GCPoolingLayer + - @ref arm_compute::GCLogits1DMaxKernel / @ref arm_compute::GCLogits1DShiftExpSumKernel / @ref arm_compute::GCLogits1DNormKernel / @ref arm_compute::GCSoftmaxLayer + - @ref arm_compute::GCTransposeKernel / @ref arm_compute::GCTranspose + + - New NEON kernels / functions + - @ref arm_compute::NEGEMMLowpAArch64A53Kernel / @ref arm_compute::NEGEMMLowpAArch64Kernel / @ref arm_compute::NEGEMMLowpAArch64V8P4Kernel / arm_compute::NEGEMMInterleavedBlockedKernel / @ref arm_compute::NEGEMMLowpAssemblyMatrixMultiplyCore + - @ref arm_compute::NEHGEMMAArch64FP16Kernel + - @ref arm_compute::NEDepthwiseConvolutionLayer3x3Kernel / @ref arm_compute::NEDepthwiseIm2ColKernel / @ref arm_compute::NEGEMMMatrixVectorMultiplyKernel / @ref arm_compute::NEDepthwiseVectorToTensorKernel / @ref arm_compute::NEDepthwiseConvolutionLayer + - @ref arm_compute::NEGEMMLowpOffsetContributionKernel / @ref arm_compute::NEGEMMLowpMatrixAReductionKernel / @ref arm_compute::NEGEMMLowpMatrixBReductionKernel / @ref arm_compute::NEGEMMLowpMatrixMultiplyCore + - @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint + - @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8Scale + - @ref arm_compute::NEWinogradLayerKernel / @ref arm_compute::NEWinogradLayer + + - New OpenCL kernels / functions + - @ref arm_compute::CLGEMMLowpOffsetContributionKernel / @ref arm_compute::CLGEMMLowpMatrixAReductionKernel / @ref arm_compute::CLGEMMLowpMatrixBReductionKernel / @ref arm_compute::CLGEMMLowpMatrixMultiplyCore + - @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint + - @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel / @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8Scale + + - New graph nodes for NEON and OpenCL + - @ref arm_compute::graph::BranchLayer + - @ref arm_compute::graph::DepthConvertLayer + - @ref arm_compute::graph::DepthwiseConvolutionLayer + - @ref arm_compute::graph::DequantizationLayer + - @ref arm_compute::graph::FlattenLayer + - @ref arm_compute::graph::QuantizationLayer + - @ref arm_compute::graph::ReshapeLayer + v17.10 Public maintenance release - Bug fixes: - Check the maximum local workgroup size supported by OpenCL devices diff --git a/docs/Doxyfile b/docs/Doxyfile index a3e4f5c908..de0320f38b 100644 --- a/docs/Doxyfile +++ b/docs/Doxyfile @@ -2076,7 +2076,8 @@ PREDEFINED = DOXYGEN_SKIP_THIS \ LOCATE_MAX \ HAS_BIAS \ POOL_AVG \ - ARM_COMPUTE_AARCH64_V8_2 + ARM_COMPUTE_AARCH64_V8_2 \ + ARM_COMPUTE_AARCH64_V8A # If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this -- cgit v1.2.1