aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
AgeCommit message (Expand)Author
2023-02-09Fix performance regression in Transposed ConvolutionGunes Bayir
2023-02-01Add new operator AddMulAdd for Neon™ backend for Float/Quantized typesGunes Bayir
2023-02-01Remove fixed format strides hackJonathan Deakin
2023-01-30Skip upsampling for deconvolution when not neededAnnop Wongwathanarat
2023-01-23Fix performance regression when stride equal to kernel sizeGunes Bayir
2023-01-20Add enable_fast_math for NEDeconvolutionLayerAnnop Wongwathanarat
2023-01-18Revert "Update the heuristic for CLDepthwiseConvolutionNative kernel"Gian Marco Iodice
2023-01-12Update the heuristic for CLDepthwiseConvolutionNative kernelGian Marco Iodice
2022-12-30Move DWC native heuristic into the heuristic folderGian Marco Iodice
2022-12-29Update the ClConv2d heuristicGian Marco Iodice
2022-12-21Optimize MeanReduce by integer acc. and removing upfront dequant.Omar Al Khatib
2022-12-14Optimize Transposed Convolution for CL backend (Quantized)Gunes Bayir
2022-12-09Use heuristics for setting dynamic fusion direct conv2d tile sizesRamy Elgammal
2022-12-09Implement the OpenCL kernel to compute the indirect convolutionGian Marco Iodice
2022-11-22Remove dynamic fusion prototype with tests and examplesSiCong Li
2022-11-18Add num_threads_to_use to OMPScheduler based on workload sizecfRod
2022-11-14Optimize Transposed Convolution for CL backend (FP32/16)Gunes Bayir
2022-10-06Rework DepthwiseConvolution heuristic on OpenCLGian Marco Iodice
2022-09-16Optimize Quantized/Integer Bilinear Scale for Neon™Gunes Bayir
2022-09-09Optimize FP32/16 Bilinear Scale Kernel for Neon™Gunes Bayir
2022-09-07Optimize depthwise convolution on OpenCLGian Marco Iodice
2022-09-01Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer repeat...Murray Kornelsen
2022-08-24Fix validation problem in CLQLSTMLayerPablo Marquez Tello
2022-08-11Fix CTS/SLTS failure related to Depthwise ConvolutionGunes Bayir
2022-08-03[ONCPUML-968] Fixed format kernel support in additional APIsMilos Puzovic
2022-08-01Fix for OpenMP scheduler work breakdownMilos 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
2022-07-13Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16Gunes Bayir
2022-07-07Add missing flag when building cl graph examples and fixMichalis Spyrou
2022-05-31Fix compilation error in 32-bit with logging buildViet-Hoa Do
2022-05-06Integrate Dynamic Fusion patchesSiCong Li
2022-05-06QLSTM add support for different qinfoMike Kelly
2022-04-21NEQLSTM: perform type conversion in prepare method.Pablo Marquez Tello
2022-04-14Enable dynamic cl tuning for dynamically fused kernelsSiCong Li
2022-04-13Add DirectConvolution2D kernel component for dynamic fusionGunes Bayir
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
2022-03-15Implementation of ClPooling3dramelg01
2022-03-10Added windows native build supportPablo Tello
2022-03-08Merge kernel prototype patchGiorgio Arena
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
2022-01-25Add OpenBSD/arm64 support.Kevin Lo
2021-11-16Implement 1D Adaptive Workload Splitting in CPPSchedulerDana Zlotnik
2021-11-15Initialise quantization info in NEPadLayerPablo Marquez Tello
2021-11-12Fix PostOp dependencySiCongLi
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-20 17:00:31 +0000