aboutsummaryrefslogtreecommitdiff
path: root/src/core
AgeCommit message (Expand)Author
2021-12-14Update A510 arm_gemm cpu Kernelsramelg01
2021-12-13Remove padding from ClDirectConv2dKernelAdnan AlSinan
2021-12-10Fix 300% Regression CPU - Change default mws value in Kernel filesMohammed Suhail Munshi
2021-12-10Use #if directive instead of regular condition in CLDirectConv2DGiorgio Arena
2021-12-01Improve start-up direct convolution on OpenCLGian Marco Iodice
2021-11-29Use loop unrolling only when the kernel height is less than 5Gian Marco Iodice
2021-11-28Decouple CpuAddKernelDana Zlotnik
2021-11-26Rework gemm_reshape_rhs_(nt,t) with new macrosGian Marco Iodice
2021-11-23Decouple data type for NERangeKernelYair Schwarzbaum
2021-11-20Improve start-up timer for GeMM (floating-point):ramelg01
2021-11-17Improve start-up timer for ClIm2ColGiorgio Arena
2021-11-17Improve start-up time for depthwise convolutionSheri Zhang
2021-11-16Implement 1D Adaptive Workload Splitting in CPPSchedulerDana Zlotnik
2021-11-12Fix PostOp dependencySiCongLi
2021-11-09Improve start-up time for ClScaleAdnan AlSinan
2021-11-05Update GeMM heuristic on CPUGian Marco Iodice
2021-11-04Add validate tests for CLConvolutionLayer and CLGEMMConvolutionLayer with pos...SiCongLi
2021-11-04Add PRelu to supported PostOps in:ramelg01
2021-11-03Fix out-of-bound reads in cl gemm kernelsSiCongLi
2021-11-02Add post ops to ClGemmMatrixMultiplyReshapedOnlyRHSKernel and ClGemmMatrixMul...SiCongLi
2021-11-01Remove padding in FP Cl Gemm kernelsSiCongLi
2021-11-01Fix dst "widening" validationSiCongLi
2021-10-28Add experimental PostOp interface to ClGemmMatrixMultiplyReshapedKernel Part 1SiCongLi
2021-10-27Improve conv3d validationFreddie Liardet
2021-10-20Implement CLDirectConv3DKernel - uint8/int8Giorgio Arena
2021-10-18DirectConv3d support refineSheri Zhang
2021-10-18Remove legacy GeMM kernels on OpenCLGian Marco Iodice
2021-10-18Fix precision issue in ChannelShuffleKernelPablo Marquez Tello
2021-10-18Add user provided JSON operator list buildFreddie Liardet
2021-10-18Implement Minimum Workload Size (MWS) in all CPPKernels used by small networksDana Zlotnik
2021-10-15Fix CLConv3D filelist and commentsGiorgio Arena
2021-10-14Implement CLDirectConv3D f32/f16Giorgio Arena
2021-10-13Improve performance of Softmax uint8 on GPUAdnan AlSinan
2021-10-11Fix precision issue in ChannelShuffleKernelPablo Tello
2021-10-07Add support for 5D data layout indexingGiorgio Arena
2021-10-07Per-operator build dependenciesGeorgios Pinitas
2021-10-06Fix the multipliers calculationPablo Marquez Tello
2021-10-05Fixed the compiler warning -Werror=type-limitsPablo Marquez Tello
2021-09-29Add support for non-constant weights and biases in CpuFullyConnectedGiorgio Arena
2021-09-23Fix inefficient store in gemmlowp_mm_reshaped_only_rhs_tGian Marco Iodice
2021-09-22Update OpenCL header file to version 2020.12.18Sheri Zhang
2021-09-16Revert "Add support for non-constant weights and biases in CpuFullyConnected"Pablo Marquez Tello
2021-09-15Adds Conv3d reference implementation support.Adnan AlSinan
2021-09-15Update cpu heuristics for GEMMGunes Bayir
2021-09-14Optimize ClScaleKernel on NHWC (f32/f16/int8)Gian Marco Iodice
2021-09-09Remove padding from ClGemmMatrixMultiplyReshapedOnlyRhsKernelGiorgio Arena
2021-09-08Fix vload_partial macros on OpenCLGiorgio Arena
2021-09-07Remove padding from ClGemmMatrixMultiplyReshapedKernelGiorgio Arena
2021-09-07Add support for non-constant weights and biases in CpuFullyConnectedMichele Di Giorgio
2021-09-07Update cpu depthwise kernelsFreddie Liardet
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-26 03:50:20 +0000