aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2021-03-23Extend direct convolution (F32/F16/QASYMM8)Gian Marco Iodice
2021-03-23Make ClDirectConvolutionKernel statelessSheri Zhang
2021-03-23Make ClPixelWiseMultiplicationKernel statelessSheri Zhang
2021-03-23Fix typo from AclCpuCapabalities to AclCpuCapabilitiesGeorgios Pinitas
2021-03-23Port CpuTranspose to new APITeresa Charlin
2021-03-22Fix SVE build on newer compilersMichalis Spyrou
2021-03-22Increase tolerance for winograd input transform F32 NHWCGiorgio Arena
2021-03-19Added Qasymm8 datatype support to NEROIPoolingLayer with TestsSuhail Munshi
2021-03-17Updated cpu detectionPablo Marquez Tello
2021-03-16Add test case for memory managed softmax layerSang-Hoon Park
2021-03-16Port Arm(R) Neon(TM) Scale to new APIManuel Bottini
2021-03-15Revert "Close loaded library on OpenCL symbols destruction"Georgios Pinitas
2021-03-12Port OpenCL Scale to new APIManuel Bottini
2021-03-11Port OpenCL Dequantization to new APIManuel Bottini
2021-03-11Add CpuPRelu operatorsSang-Hoon Park
2021-03-11Change the order of internal tensor allocation in CLSoftmaxLayerSang-Hoon Park
2021-03-11Port Arm(R) Neon(TM) Dequantization to new APIManuel Bottini
2021-03-10Update release note for data type decouplingGiorgio Arena
2021-03-10Port OpenCL Quantization to new APIManuel Bottini
2021-03-10Port Arm(R) Neon(TM) Quantization to new APIManuel Bottini
2021-03-10Use memalign on bare metalMichalis Spyrou
2021-03-10Remove valid region calculation from CpuElementwiseSang-Hoon Park
2021-03-10Fix segmentation fault on CLSoftmaxLayerSang-Hoon Park
2021-03-08Add dynamic tensor support to CpuElementwiseSang-Hoon Park
2021-03-08Make Softmax kernels on OpenCL statelessSang-Hoon Park
2021-03-08Fix cl_gemmlowp_reshaped_rhs_only_fused_output_stage_fixedpoint exampleSiCongLi
2021-03-08Extend .gitignore file to exclude IDE foldersGeorgios Pinitas
2021-03-08Make auxiliary tensor within NEGEMMConvolutionLayer resizableGeorgios Pinitas
2021-03-08Remove usage of valid window region in NHWC CPU kernels - Part2SiCongLi
2021-03-08Remove usage of valid window region in NHWC CPU kernels - Part1SiCongLi
2021-03-05Fix build errors for functions requiring SVE2 extensionSang-Hoon Park
2021-03-05Add log on memory allocation failure in CpuContextSang-Hoon Park
2021-03-05Move utility functions to NE/SVEMathSang-Hoon Park
2021-03-04Add tuner mode support in GeMM benchmarkGian Marco Iodice
2021-03-03Create ClPRelu operatorSang-Hoon Park
2021-03-03Remove Compute Vision CL supportMichalis Spyrou
2021-03-03Add QASYMM8_SIGNED support to graph examples via graph mutatorSiCongLi
2021-03-02Update documentation with instructions for building Android using NDK >= r19Giorgio Arena
2021-03-02Set up configure-only flag for validation. First trial with DepthwiseConvoltionGiorgio Arena
2021-03-01Fix bug on CLCast from float to int8Giorgio Arena
2021-03-01Fix bug on CLGEMMMatrixMultiplyReshapedOnlyRHS testsGiorgio Arena
2021-02-25Update int8 A55 kernelsGeorgios Pinitas
2021-02-25Update errata with failures in CLCast and CLGEMMMatrixMultiplyReshapedOnlyRHS...Michele Di Giorgio
2021-02-25Add proper range checking when identifying CPU capabilitiesGeorgios Pinitas
2021-02-25Avoid division with zeroGeorgios Pinitas
2021-02-25Introduce Context opaque object of the new interfaceGeorgios Pinitas
2021-02-24Add errata for failure in quantized CLFullyConnectedLayerMichele Di Giorgio
2021-02-24Check cpu index is within a valid range when populating cpu informationGeorgios Pinitas
2021-02-24Account Ksections correctly for interleaved and hybrid_indirect gemm kernelsGeorgios Pinitas
2021-02-24Use vector resizing instead of temporary assign in gemm_hybrid_indirectGeorgios Pinitas
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-23 03:49:03 +0000