aboutsummaryrefslogtreecommitdiff
path: root/src/runtime/NEON
AgeCommit message (Expand)Author
2022-12-21Optimize MeanReduce by integer acc. and removing upfront dequant.Omar Al Khatib
2022-09-16Optimize Quantized/Integer Bilinear Scale for Neon™Gunes Bayir
2022-09-09Optimize FP32/16 Bilinear Scale Kernel for Neon™Gunes Bayir
2022-08-03[ONCPUML-968] Fixed format kernel support in additional APIsMilos Puzovic
2022-07-26Fix for inclusion of "arm_gemm" from src into "Types.h" from coreRamy Elgammal
2022-07-19[ONCPUML-951] Variable weight support for Convolution.Francesco Petrogalli
2022-07-14Integrate new winograd APIs from MLTechramelg01
2022-05-06QLSTM add support for different qinfoMike Kelly
2022-04-21NEQLSTM: perform type conversion in prepare method.Pablo Marquez Tello
2022-04-01Add CPU Pool3d FP16/32 implementationAdnan AlSinan
2022-03-29NEQLSTM: Add support for QASYMM8_SIGNED for input_to_forget_weightsPablo Marquez Tello
2022-03-24QLSTM add support for different qinfo in weightsPablo Marquez Tello
2022-02-16Fixed threshould argument order in NE/CL/LSTMPablo Marquez Tello
2022-02-14Port MaxUnpoolingLayer kernel and add KernelSelect vaidation testDana Zlotnik
2022-02-09Remove deprecated remap functions.Adnan AlSinan
2021-11-15Initialise quantization info in NEPadLayerPablo Marquez Tello
2021-10-18DirectConv3d support refineSheri Zhang
2021-10-15Conv3d supportSheri Zhang
2021-10-04Provide logging for configure functions in all CPP functionsramelg01
2021-09-22Provide logging for configure functions in all NEON functionsramelg01
2021-08-25Move CPU/GPU files from Core/Runtime to the respective backend foldersGeorgios Pinitas
2021-08-20Rename [Cl|Cpu]GemmConvolution to [Cl|Gpu]GemmConv2dGeorgios Pinitas
2021-08-19Address comments on avoiding releasing weights if used by multiple functionsGiorgio Arena
2021-08-13Avoid releasing weights if they are used by multiple functionsGeorgios Pinitas
2021-08-13Ensure correct transformed matrices are used in CpuGemmConvolutionGeorgios Pinitas
2021-08-12Ensure that correct transformed matrices are used in CpuFullyConnectedGeorgios Pinitas
2021-07-30Reintroduce implementation of NEConvolutionLayer::get_convolution_methodMichele Di Giorgio
2021-07-29Port NEConvolutionLayerMichalis Spyrou
2021-07-28Reduce binary footprint of CpuConvertFullyConnectedWeightsKernelMichele Di Giorgio
2021-07-23Port NEFullyConnectedLayer to memory injecting interfaceMichele Di Giorgio
2021-07-22Expose fast_math mode for GEMM through BFloat16Georgios Pinitas
2021-07-22Update GEMM assembly kernelsGeorgios Pinitas
2021-07-16Avoid multiple Rhs matrix transformation on ClGemmGeorgios Pinitas
2021-07-15Disabled DirectConv method for NCHW and kernel > 15Pablo Marquez Tello
2021-07-15Port NEGEMMConvolutionLayerManuel Bottini
2021-07-13Port NEWinogradConvolutionLayerMichalis Spyrou
2021-07-09Port NECol2ImKernelManuel Bottini
2021-07-08Port NEGEMMLowp Part 2Manuel Bottini
2021-07-06Port NEIm2ColKernelManuel Bottini
2021-07-02Port NEGEMM to memory injecting interface (Part 3)Michele Di Giorgio
2021-06-29Port NEGEMM to memory injecting interface (Part 2)Michele Di Giorgio
2021-06-29Port NEGEMM to memory injecting interface (Part 1)Michele Di Giorgio
2021-06-25Port NEGEMMConv2d to memory injecting interfaceMichele Di Giorgio
2021-06-23Create core library using high priority operatorsMichalis Spyrou
2021-06-22Port NEGEMMLowp Part 1Manuel Bottini
2021-06-22Add FP16 support to CLRemapFreddie Liardet
2021-06-18Integrate improved CPU depthwise convolution kernelsMichele Di Giorgio
2021-06-18Remove implementation headers from NESoftmaxLayer public headerGeorgios Pinitas
2021-06-15Fix incorrect memory handling in ported functionsManuel Bottini
2021-06-09Fixed segfault in NEGEMMConv2dPablo Tello
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-23 02:21:13 +0000