aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2022-06-27Implement new Elementwise Dynamic Fusion Operators: Div, FloorMichalis Spyrou
2022-06-24Improve LUT Neon Hard-SwishPablo Marquez Tello
2022-06-23Select neon LUT Hard-Swish kernel on all devicesPablo Marquez Tello
2022-06-23Enable loading OpenCL symbols in Android App native code, NDK environment.ohadagoogle
2022-06-17Drop support on armv7a on AndroidMichalis Spyrou
2022-06-16Fix SVE2 implementation of quantized SoftMax 1DViet-Hoa Do
2022-06-15Fix build error v8.2-a-svePablo Marquez Tello
2022-06-15Add support OpenCL 3.0 non-uniform workgroupViet-Hoa Do
2022-06-15Fix performance regression in Winograd Output Transform (OpenCL)Gian Marco Iodice
2022-06-13Add support for 2d and 3d indices for axis 1Pablo Marquez Tello
2022-06-09Fix crash in CpuActivationKernelPablo Marquez Tello
2022-06-07Compute Hard-Swish with a Lookup table for qasymm8.Pablo Marquez Tello
2022-06-06Allow clearer suppression of toolchain and compiler prefixesSiCong Li
2022-06-06Fix build errors in GCC12Pablo Marquez Tello
2022-06-01Fix reference example for fusion of conv2d and addditionSiCong Li
2022-05-31Add cl_khr_integer_dot_product extension supportViet-Hoa Do
2022-05-31Add missing new-line to doxygen documentationSiCong Li
2022-05-31Fix compilation error in 32-bit with logging buildViet-Hoa Do
2022-05-30Fix doxygen typosViet-Hoa Do
2022-05-26Disable unsafe FP optimizations causing accuracy issuesGunes Bayir
2022-05-24[arm_gemm] Import fixed-format kernels from gemm_linux.Francesco.Petrogalli@arm.com
2022-05-19Properly format SConscript filesMichalis Spyrou
2022-05-18Fix doxygen page layoutSiCong Li
2022-05-17DepthwiseConv reports full assembly kernel namePablo Marquez Tello
2022-05-17Update ErrataAdnan AlSinan
2022-05-17Update READMEAdnan AlSinan
2022-05-16Update SONAME_VERSION in SConscriptMohammed Suhail Munshi
2022-05-12Revert "Add support for 2d and 3d indices for axis 0"Mohammed Suhail Munshi
2022-05-11Fix inclusion guard for dynamic fusion moduleSiCong Li
2022-05-10Add support for 2d and 3d indices for axis 0Pablo Marquez Tello
2022-05-09Mismatches in dynamically fused direct conv2d + add kernelMichalis Spyrou
2022-05-06Integrate Dynamic Fusion patchesSiCong Li
2022-05-06Add a note to clarify pretranspose option in GEMM and GEMMLowp fixturesAdnan AlSinan
2022-05-06Updating a64_gemm_u8 a64_gemm_s8 kernels headersramelg01
2022-05-06QLSTM add support for different qinfoMike Kelly
2022-05-06Use svcreate instead of list initializations.Michalis Spyrou
2022-05-06Extend GEMM to support batch matmul operationMohammed Suhail Munshi
2022-05-06Extend GemmLowp reference to support BATCH MATMUL for quantized data typeAdnan AlSinan
2022-05-05Fix for Neon™ Depthwise Android P VTS test failureramelg01
2022-05-04Add a missing validation check to CPU Pool3dAdnan AlSinan
2022-05-03Update public mailing list in READMESiCong Li
2022-04-29Add a few sections on security consernsMichalis Spyrou
2022-04-27Add security related / good coding practicesMichalis Spyrou
2022-04-26Update Neon™ depthwise kernelramelg01
2022-04-25Update Neon™ pooling kernelramelg01
2022-04-25Document data layout of weight tensors in convolution layersSiCong Li
2022-04-25Add LU_BOUNDED_RELU support for QSYMM16Pablo Marquez Tello
2022-04-22[CpuGemmConv2d] Extract skip_im2col and skip_col2im computation.Francesco.Petrogalli@arm.com
2022-04-21Add missing noexcept.Michalis Spyrou
2022-04-21NEQLSTM: perform type conversion in prepare method.Pablo Marquez Tello
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-12 19:06:17 +0000