From 407c102b62632185e06b5e75553f7b0cdbc46cdb Mon Sep 17 00:00:00 2001 From: SiCong Li Date: Mon, 25 Nov 2019 19:15:56 +0000 Subject: COMPMID-2911 Update README and Doxygen for 19.11 Change-Id: Ibf0a0b5dc30471efb9089a7154f0204f6568f531 Signed-off-by: SiCong Li Reviewed-on: https://review.mlplatform.org/c/2369 Reviewed-by: Georgios Pinitas Tested-by: Georgios Pinitas --- README.md | 7 +++--- docs/00_introduction.dox | 57 ++++++++++++++++++++++++++++++++++++++++++++-- docs/06_functions_list.dox | 13 +++++++++-- 3 files changed, 69 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 2aeac7f8ba..ea1dd87803 100644 --- a/README.md +++ b/README.md @@ -25,12 +25,9 @@ Tutorials: - [Tutorial: Cartoonifying Images on Raspberry Pi with the Compute Library](https://community.arm.com/graphics/b/blog/posts/cartoonifying-images-on-raspberry-pi-with-the-compute-library) - [Tutorial: Running AlexNet on Raspberry Pi with Compute Library](https://community.arm.com/processors/b/blog/posts/running-alexnet-on-raspberry-pi-with-compute-library) -Blogs: - -- [Happy Birthday ACL!](https://community.arm.com/developer/tools-software/graphics/b/blog/posts/arm-compute-library-19-05-is-coming) - Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: +- [v19.11](https://arm-software.github.io/ComputeLibrary/v19.11/) - [v19.08](https://arm-software.github.io/ComputeLibrary/v19.08/) - [v19.05](https://arm-software.github.io/ComputeLibrary/v19.05/) - [v19.02](https://arm-software.github.io/ComputeLibrary/v19.02/) @@ -50,6 +47,8 @@ Documentation (API, changelogs, build guide, contribution guide, errata, etc.) a Binaries available here: +- [v19.11-linux](https://github.com/ARM-software/ComputeLibrary/releases/download/v19.11/arm_compute-v19.11-bin-linux.tar.gz) +- [v19.11-android](https://github.com/ARM-software/ComputeLibrary/releases/download/v19.11/arm_compute-v19.11-bin-android.tar.gz) - [v19.08-linux](https://github.com/ARM-software/ComputeLibrary/releases/download/v19.08/arm_compute-v19.08-bin-linux.tar.gz) - [v19.08-android](https://github.com/ARM-software/ComputeLibrary/releases/download/v19.08/arm_compute-v19.08-bin-android.tar.gz) - [v19.05-linux](https://github.com/ARM-software/ComputeLibrary/releases/download/v19.05/arm_compute-v19.05-bin-linux.tar.gz) diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 7f44fb7479..24e119c277 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -237,16 +237,69 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog v19.11 Public major release - - Deprecated OpenCL kernels / functions + - Various bug fixes. + - Various optimisations. + - Deprecated OpenCL kernels / functions: - CLDepthwiseConvolutionLayerReshapeWeightsGenericKernel - CLDepthwiseIm2ColKernel + - CLDepthwiseSeparableConvolutionLayer - CLDepthwiseVectorToTensorKernel - CLDirectConvolutionLayerOutputStageKernel - - Deprecated NEON kernels / functions + - Deprecated NEON kernels / functions: - NEDepthwiseWeightsReshapeKernel - NEDepthwiseIm2ColKernel + - NEDepthwiseSeparableConvolutionLayer - NEDepthwiseVectorToTensorKernel - NEDepthwiseConvolutionLayer3x3 + - New OpenCL kernels / functions: + - @ref CLInstanceNormalizationLayerKernel / @ref CLInstanceNormalizationLayer + - @ref CLDepthwiseConvolutionLayerNativeKernel to replace the old generic depthwise convolution (see Deprecated + OpenCL kernels / functions) + - @ref CLLogSoftmaxLayer + - New NEON kernels / functions: + - @ref NEBoundingBoxTransformKernel / @ref NEBoundingBoxTransform + - @ref NEComputeAllAnchorsKernel / @ref NEComputeAllAnchors + - @ref NEDetectionPostProcessLayer + - @ref NEGenerateProposalsLayer + - @ref NEInstanceNormalizationLayerKernel / @ref NEInstanceNormalizationLayer + - @ref NELogSoftmaxLayer + - @ref NEROIAlignLayerKernel / @ref NEROIAlignLayer + - Added QASYMM8 support for: + - @ref CLGenerateProposalsLayer + - @ref CLROIAlignLayer + - @ref CPPBoxWithNonMaximaSuppressionLimit + - Added QASYMM16 support for: + - @ref CLBoundingBoxTransform + - Added FP16 support for: + - @ref CLGEMMMatrixMultiplyReshapedKernel + - Added new data type QASYMM8_PER_CHANNEL support for: + - @ref CLDequantizationLayer + - @ref NEDequantizationLayer + - Added new data type QSYMM8_PER_CHANNEL support for: + - @ref CLConvolutionLayer + - @ref NEConvolutionLayer + - @ref CLDepthwiseConvolutionLayer + - @ref NEDepthwiseConvolutionLayer + - Added FP16 mixed-precision support for: + - @ref CLGEMMMatrixMultiplyReshapedKernel + - @ref CLPoolingLayerKernel + - Added FP32 and FP16 ELU activation for: + - @ref CLActivationLayer + - @ref NEActivationLayer + - Added asymmetric padding support for: + - @ref CLDirectDeconvolutionLayer + - @ref CLGEMMDeconvolutionLayer + - @ref NEDeconvolutionLayer + - Added SYMMETRIC and REFLECT modes for @ref CLPadLayerKernel / @ref CLPadLayer. + - Replaced the calls to @ref NECopyKernel and @ref NEMemsetKernel with @ref NEPadLayer in @ref NEGenerateProposals. + - Replaced the calls to @ref CLCopyKernel and @ref CLMemsetKernel with @ref CLPadLayer in @ref CLGenerateProposals. + - Improved performance for CL Inception V3 - FP16. + - Improved accuracy for CL Inception V3 - FP16 by enabling FP32 accumulator (mixed-precision). + - Improved NEON performance by enabling fusing batch normalization with convolution and depth-wise convolution layer. + - Improved NEON performance for MobileNet-SSD by improving the output detection performance. + - Optimized @ref CLPadLayer. + - Optimized CL generic depthwise convolution layer by introducing @ref CLDepthwiseConvolutionLayerNativeKernel. + - Reduced memory consumption by implementing weights sharing. v19.08 Public major release - Various bug fixes. diff --git a/docs/06_functions_list.dox b/docs/06_functions_list.dox index 48016ed375..0008087872 100644 --- a/docs/06_functions_list.dox +++ b/docs/06_functions_list.dox @@ -36,8 +36,11 @@ namespace arm_compute - @ref NEAbsoluteDifference - @ref NEArithmeticAddition - @ref NEArithmeticSubtraction + - @ref NEBoundingBoxTransform - @ref NEBox3x3 - @ref NECast + - @ref NEComplexPixelWiseMultiplication + - @ref NEComputeAllAnchors - @ref NEConvolution3x3 - @ref NEConvolutionRectangle - @ref NEDilate @@ -57,6 +60,8 @@ namespace arm_compute - @ref NEPixelWiseMultiplication - @ref NEPReluLayer - @ref NERemap + - @ref NEROIAlignLayer + - @ref NERoundLayer - @ref NERsqrtLayer - @ref NEScharr3x3 - @ref NESelect @@ -120,6 +125,7 @@ namespace arm_compute - @ref NEDepthwiseConvolutionLayerOptimized - @ref NEDequantizationLayer - @ref NEDerivative + - @ref NEDetectionPostProcessLayer - @ref NEDirectConvolutionLayer - @ref NEEqualizeHistogram - @ref NEFastCorners @@ -138,12 +144,14 @@ namespace arm_compute - @ref NEGEMMConvolutionLayer - @ref NEGEMMLowpAssemblyMatrixMultiplyCore - @ref NEGEMMLowpMatrixMultiplyCore + - @ref NEGenerateProposalsLayer - @ref NEHarrisCorners - @ref NEHistogram - @ref NEHOGDescriptor - @ref NEHOGGradient - @ref NEHOGMultiDetection - @ref NEIm2Col + - @ref NEInstanceNormalizationLayer - @ref NEL2NormalizeLayer - @ref NELaplacianPyramid - @ref NELaplacianReconstruct @@ -166,7 +174,7 @@ namespace arm_compute - @ref NESimpleAssemblyFunction - @ref NESobel5x5 - @ref NESobel7x7 - - @ref NESoftmaxLayer + - @ref NESoftmaxLayerGeneric <IS_LOG> - @ref NESpaceToBatchLayer - @ref NESpaceToDepthLayer - @ref NESplit @@ -236,7 +244,7 @@ namespace arm_compute - @ref CLRNNLayer - @ref CLSobel5x5 - @ref CLSobel7x7 - - @ref CLSoftmaxLayer + - @ref CLSoftmaxLayerGeneric <IS_LOG> - @ref CLSpaceToBatchLayer - @ref CLSpaceToDepthLayer - @ref CLSplit @@ -356,6 +364,7 @@ namespace arm_compute - @ref IFunction - @ref CPPDetectionOutputLayer + - @ref CPPDetectionPostProcessLayer - @ref ICPPSimpleFunction - @ref CPPBoxWithNonMaximaSuppressionLimit - @ref CPPPermute -- cgit v1.2.1