aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
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
2021-11-03Add graph level convolution fusion with post operatorSheri Zhang
2021-11-02Fix GEMMMatrixMultiplyReshapedOnlyRHSKernel tests to use InitializerListDatasetSiCongLi
2021-11-02Fix clang issue when casting negative int32_t to int64_tGiorgio Arena
2021-11-02Add post ops to ClGemmMatrixMultiplyReshapedOnlyRHSKernel and ClGemmMatrixMul...SiCongLi
2021-11-01Add PostOp support to GEMM and CLGEMM operators and functions Part 2SiCongLi
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
2021-10-27Fixed issue where cppflags were being set incorrectlyPablo Marquez Tello
2021-10-27Improve conv3d validationFreddie Liardet
2021-10-22Add uint8/int8 support to cpu conv3dFreddie Liardet
2021-10-22Remove large conv3d testsFreddie Liardet
2021-10-21Reduce size of large conv3d nightly testsFreddie Liardet
2021-10-21Fix enforcing incorrect ISA feature for given CPU modelsGeorgios Pinitas
2021-10-21Enable CPP11 math on AndroidPablo Tello
2021-10-20Implement CLDirectConv3DKernel - uint8/int8Giorgio Arena
2021-10-19Fix arm8.6-a-sve2 build issuesFreddie Liardet
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
2021-10-18Fix unused variable issueSheri Zhang
2021-10-18Implement Minimum Workload Size (MWS) in all CPPKernels used by small networksDana Zlotnik
2021-10-15Conv3d supportSheri Zhang
2021-10-15Fix CLConv3D filelist and commentsGiorgio Arena
2021-10-14Implement CLDirectConv3D f32/f16Giorgio Arena
2021-10-13Removed unsupported NHWC from Pooling::validatePablo Tello
2021-10-13Improve performance of Softmax uint8 on GPUAdnan AlSinan
2021-10-12Add missing common functionalities for DirectConv3DGiorgio Arena
2021-10-12Remove padding in cpuPool2d NCHWFreddie Liardet
2021-10-11Fix precision issue in ChannelShuffleKernelPablo Tello
2021-10-08Create Fixture for DirectConv3DGiorgio Arena
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
2021-10-06Add missing ISA selection heuristicsGeorgios Pinitas
2021-10-06Optimize CpuScale NHWC F32/F16Gian Marco Iodice
2021-10-05Fix of linking errors to find CPPSplit symbols when compiling android nn driverramelg01
2021-10-05Fixed the compiler warning -Werror=type-limitsPablo Marquez Tello
2021-10-05Fix tolerance issue for Scale tests on OpenCLGian Marco Iodice
2021-10-04Provide logging for configure functions in all CPP functionsramelg01
2021-10-01Provide logging for configure functions in all CL functionsramelg01
2021-10-01Add OpenCL sources to Android.bp fileJakub Sujak
2021-09-29Add support for non-constant weights and biases in CpuFullyConnectedGiorgio Arena
2021-09-29FIX: seg fault when printing TensorInfo's quantization info per channelramelg01
2021-09-28Provide logging for configure functions in all gpu operatorsramelg01
2021-09-27Generate an operator configuration file from a list of tflite modelsGeorgios Pinitas