aboutsummaryrefslogtreecommitdiff
path: root/src/runtime/CL/functions
AgeCommit message (Expand)Author
2021-07-27Fix memory lifetime issueGeorgios Pinitas
2021-07-27Port CLGEMMConvolutionLayerManuel Bottini
2021-07-27Dispatch Conv2d using the Direct method when necessaryGeorgios Pinitas
2021-07-22Port ClGemmLowp to new APIGeorgios Pinitas
2021-07-22Update GEMM assembly kernelsGeorgios Pinitas
2021-07-16Avoid multiple Rhs matrix transformation on ClGemmGeorgios Pinitas
2021-07-16Port CLIm2ColKernel to ClIm2ColKernelManuel Bottini
2021-07-15Port CLCol2ImKernel to ClCol2ImKernelManuel Bottini
2021-07-08Change CLConvolution selection to run Direct approach on large kernelsGeorgios Pinitas
2021-07-02Rework OpenCL Depthwise ConvolutionGian Marco Iodice
2021-07-02Implement FP GPU depthwise convolution 1x1 kernel for in-place computationSiCongLi
2021-06-30Port ClGemmLowpOutputStage operator to new interfaceGeorgios Pinitas
2021-06-30Revert "Rework OpenCL Depthwise Convolution"Gian Marco Iodice
2021-06-29Port the ClGemmLowp kernels to the new APIGeorgios Pinitas
2021-06-25Port NEGEMMConv2d to memory injecting interfaceMichele Di Giorgio
2021-06-24Rework OpenCL Depthwise ConvolutionGian Marco Iodice
2021-06-22Fix Winograd heuristic in CLConvolutionLayerGian Marco Iodice
2021-06-22Add FP16 support to CLRemapFreddie Liardet
2021-06-21Rework the CLConvolutionLayer heuristicGian Marco Iodice
2021-06-18Integrate improved CPU depthwise convolution kernelsMichele Di Giorgio
2021-06-15Port CLWinogradConvolutionLayer with ClWinogradConv2dManuel Bottini
2021-06-15Fix incorrect memory handling in ported functionsManuel Bottini
2021-06-15Add NHWC support to CLRemapFrederick Liardet
2021-06-11Fix errata in documentationJakub Sujak
2021-06-07Fix WeightRetention tests on multiple calls of FullyConnectedGeorgios Pinitas
2021-06-01Rename ported functionsManuel Bottini
2021-05-20Add support for dynamic weights in CL FullyConnected layerGiorgio Arena
2021-05-19Port DepthConvert to new ApiGeorgios Pinitas
2021-05-18Port CLGEMM to memory injecting interfaceGeorgios Pinitas
2021-05-18Port CLFlattenLayer to a memory injecting interfaceGeorgios Pinitas
2021-05-17Fix oclgrind error on CLGEMMLowp reshaped only RHS quantized per channelGiorgio Arena
2021-05-14Fix the OpenCL convolution layer heuristic for int8Gian Marco Iodice
2021-05-07Update heuristic for CLConvolutionLayerGian Marco Iodice
2021-05-05Rename Quantization/Dequantization kernels/operators to imperative moodGeorgios Pinitas
2021-05-04Rename PixelwiseMultiplications to Mul for simplicityGeorgios Pinitas
2021-04-29Remove OpenCL padding: CLReductionOperationKernelGiorgio Arena
2021-04-28Fix for performance regression on G71 (mate9) for direct convolutionAleksandr Nikolaev
2021-04-28Add per-channel quantization support for CLDeconvolutionLayerFreddie Liardet
2021-04-27Fixed CTS failures CLInstanceNormPablo Tello
2021-04-20CLDepthwiseConvolutionLayer rework - Part 1Giorgio Arena
2021-04-20Remove OpenCL padding: CLPixelWiseMultiplicationKernelGiorgio Arena
2021-04-19CLInstanceNormalizationLayer NHWC optimisationPablo Marquez Tello
2021-04-19Port DepthwiseConvolution to new APIMichalis Spyrou
2021-04-14Remove OpenCL padding: CLNormalizationLayerKernelManuel Bottini
2021-04-13Port CLConvertFullyConnectedWeights to new APITeresa Charlin
2021-04-12Fix CLDepthwiseConvolutionLayer QSYMM8_PER_CHANNEL mismatchesGiorgio Arena
2021-04-12Add support for cl_image in CLDirectConvolutionLayerGian Marco Iodice
2021-04-08Substitute CLFullyConnectedLayerReshapeWeights by CLTransposeTeresa Charlin
2021-04-06Mixed data-layout testing on high priority operatorsManuel Bottini
2021-04-01Added Qasymm8 datatype support to CLROIPoolingLayer with TestsSuhail Munshi
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-11 04:44:21 +0000