diff options
| -rw-r--r-- | docs/00_introduction.dox | 53 |
1 files changed, 38 insertions, 15 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 11d6cbd98b..bb1dfec69e 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -255,18 +255,41 @@ v20.08 Public major release - @ref NEMaxUnpoolingLayerKernel - New graph example: - graph_yolov3_output_detector + - GEMMTuner improvements: + - Added fp16 support + - Output json files for easier integration + - Enabled tuning for export_to_cl_image_rhs option for RHS tensors + - More robust script for running benchmarks - Removed padding from: - @ref NEPixelWiseMultiplicationKernel + - @ref NEHeightConcatenateLayerKernel + - @ref NEThresholdKernel + - @ref NEBatchConcatenateLayerKernel + - @ref NETransposeKernel + - @ref NEBatchNormalizationLayerKernel + - @ref NEArithmeticSubtractionKernel + - @ref NEBoundingBoxTransformKernel + - @ref NELogits1DMaxKernel + - @ref NELogits1DSoftmaxKernel + - @ref NEROIPoolingLayerKernel + - @ref NEROIAlignLayerKernel + - @ref NEYOLOLayerKernel + - @ref NEUpsampleLayerKernel + - @ref NEFloorKernel + - @ref NEWidthConcatenateLayerKernel + - @ref NEDepthConcatenateLayerKernel + - @ref NENormalizationLayerKernel + - @ref NEL2NormalizeLayerKernel + - @ref NEFillArrayKernel + - @ref NEDepthConvertLayerKernel + - @ref NERangeKernel + - @ref NEPriorBoxLayer - Removedd OpenCL kernels / functions: - - CLGEMMLowpQuantizeDownInt32ToUint8Scale - - CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloat + - CLGEMMLowpQuantizeDownInt32ToUint8Scale + - CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloat - Removed NEON kernels / functions: - - NEGEMMLowpQuantizeDownInt32ToUint8Scale - - GEMMTuner improvements: - - Added fp16 support - - Output json files for easier integration - - Enabled tuning for export_to_cl_image_rhs option for RHS tensors - - More robust script for running benchmarks + - NEGEMMLowpQuantizeDownInt32ToUint8Scale + - NEGEMMMatrixAccumulateBiasesKernel - Deprecated functions / interfaces: - Non-descriptor based interfaces for @ref NEThreshold, @ref CLThreshold - Non-descriptor based interfaces for @ref NEScale, @ref CLScale and @ref GCScale @@ -274,16 +297,16 @@ v20.08 Public major release The default "axis" value for @ref CLSoftmaxLayer, @ref CLLogSoftmaxLayer and @ref GCSoftmaxLayer is changed from 1 to 0. Only axis 0 is supported. The default "axis" value for @ref NESoftmaxLayer, @ref NELogSoftmaxLayer is changed from 1 to 0. - Only axis 0 is supported. + Only axis 0 is supported. - The support for quantized data types has been removed from @ref CLLogSoftmaxLayer due to implementation complexity. - Removed padding requirement for the input (e.g. LHS of GEMM) and output in @ref CLGEMMMatrixMultiplyNativeKernel, @ref CLGEMMMatrixMultiplyReshapedKernel, @ref CLGEMMMatrixMultiplyReshapedOnlyRHSKernel and @ref CLIm2ColKernel (NHWC only) - - This change allows to use @ref CLGEMMConvolutionLayer without extra padding for the input and output. - - Only the weights/bias of @ref CLGEMMConvolutionLayer could require padding for the computation. - - Only on Arm Mali Midgard GPUs, @ref CLGEMMConvolutionLayer could require padding since @ref CLGEMMMatrixMultiplyKernel is called and currently requires padding. + - This change allows to use @ref CLGEMMConvolutionLayer without extra padding for the input and output. + - Only the weights/bias of @ref CLGEMMConvolutionLayer could require padding for the computation. + - Only on Arm Mali Midgard GPUs, @ref CLGEMMConvolutionLayer could require padding since @ref CLGEMMMatrixMultiplyKernel is called and currently requires padding. - Added support for exporting the OpenCL buffer object to the OpenCL image object in @ref CLGEMMMatrixMultiplyReshapedKernel and @ref CLGEMMMatrixMultiplyReshapedOnlyRHSKernel. - - This support allows to export the OpenCL buffer used for the reshaped RHS matrix to the OpenCL image object. - - The padding requirement for the OpenCL image object is considered into the @ref CLGEMMReshapeRHSMatrixKernel. - - The reshaped RHS matrix stores the weights when GEMM is used to accelerate @ref CLGEMMConvolutionLayer. + - This support allows to export the OpenCL buffer used for the reshaped RHS matrix to the OpenCL image object. + - The padding requirement for the OpenCL image object is considered into the @ref CLGEMMReshapeRHSMatrixKernel. + - The reshaped RHS matrix stores the weights when GEMM is used to accelerate @ref CLGEMMConvolutionLayer. v20.05 Public major release - Various bug fixes. |