aboutsummaryrefslogtreecommitdiff
path: root/src/core
AgeCommit message (Expand)Author
2021-08-13Avoid releasing weights if they are used by multiple functionsGeorgios Pinitas
2021-08-04Fix depthwise convolution assembly kernelsFreddie Liardet
2021-08-04Avoid over-allocation of temporary buffers within CpuWinogradConv2dGeorgios Pinitas
2021-08-02Add missing limits includeFreddie Liardet
2021-08-02Benchmark and set default LWS for GEMM, Direct convolution and WinogradGiorgio Arena
2021-07-30Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1Gian Marco Iodice
2021-07-29Fix A55 performance constant for fp16 hybrid gemm kernelGeorgios Pinitas
2021-07-29Port NEConvolutionLayerMichalis Spyrou
2021-07-28Create custom flags for enabling fp16 supportGeorgios Pinitas
2021-07-28Reduce binary footprint of CpuConvertFullyConnectedWeightsKernelMichele Di Giorgio
2021-07-28Fix bare metal build issuesFreddie Liardet
2021-07-28Fix cpu GEMM fp16 issueFreddie Liardet
2021-07-28Reorganize the kernels into nhwc, nchw and common foldersAdnan AlSinan
2021-07-28Remove generated kernels that overlap hand-written onesGeorgios Pinitas
2021-07-27Port CLGEMMConvolutionLayerManuel Bottini
2021-07-27Update GEMM assembly performance parametersGeorgios Pinitas
2021-07-26Add missing limits includeFreddie Liardet
2021-07-25Reorganize the kernels into nhwc, nchw and common foldersAdnan AlSinan
2021-07-23Fix vector_length identification mechanism for SVEGeorgios Pinitas
2021-07-23Port NEFullyConnectedLayer to memory injecting interfaceMichele Di Giorgio
2021-07-23Fix bare metal build errorFreddie Liardet
2021-07-22Fix oclgrind int overflow warningFreddie Liardet
2021-07-22Update GEMM assembly kernelsGeorgios Pinitas
2021-07-16Include limits header to fix errors reported by GCC11Michele Di Giorgio
2021-07-16Avoid multiple Rhs matrix transformation on ClGemmGeorgios Pinitas
2021-07-16Port CLIm2ColKernel to ClIm2ColKernelManuel Bottini
2021-07-15Port NEGEMMConvolutionLayerManuel Bottini
2021-07-15Improve filelist for GPUGeorgios Pinitas
2021-07-15Port CLCol2ImKernel to ClCol2ImKernelManuel Bottini
2021-07-14Fix CL kernel compilation failureMichalis Spyrou
2021-07-13Add in-place calculation support for CL elementwise arithmetic kernelsSheri Zhang
2021-07-13Port NEWinogradConvolutionLayerMichalis Spyrou
2021-07-09Limit the LOOP_UNROLLING on the kernel heightGian Marco Iodice
2021-07-09Port NECol2ImKernelManuel Bottini
2021-07-08Remove redundant implementations of Add/Sub operatorsGeorgios Pinitas
2021-07-08Port NEGEMMLowp Part 2Manuel Bottini
2021-07-07Validate unsupported data types with runtime informationGeorgios Pinitas
2021-07-06Fix manual LOOP_UNROLLINGGian Marco Iodice
2021-07-06Port NEIm2ColKernelManuel Bottini
2021-07-05Improve implementation selection speed of CpuElementwiseUnaryGeorgios Pinitas
2021-07-02Rework OpenCL Depthwise ConvolutionGian Marco Iodice
2021-07-02Align kernel/operator header layoutGeorgios Pinitas
2021-07-02Implement FP GPU depthwise convolution 1x1 kernel for in-place computationSiCongLi
2021-07-01Add quantization helper functions for OpenCLGeorgios Pinitas
2021-07-01Reduce binary size footprint of CpuGemmInterleave4x4KernelMichele Di Giorgio
2021-07-01Adjust minimum DDK version for manual unrollGiorgio Arena
2021-06-30Revert "Rework OpenCL Depthwise Convolution"Gian Marco Iodice
2021-06-29Port the ClGemmLowp kernels to the new APIGeorgios Pinitas
2021-06-29Port NEGEMM to memory injecting interface (Part 2)Michele Di Giorgio
2021-06-29Enable global pooling optimization on OpenCLGian Marco Iodice
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-12 20:26:03 +0000