- b6af482 Per-operator build dependencies by Georgios Pinitas · 2 years, 10 months ago
- 41d886c Fixed the compiler warning -Werror=type-limits by Pablo Marquez Tello · 2 years, 9 months ago
- 63e0beb Add support for non-constant weights and biases in CpuFullyConnected by Giorgio Arena · 2 years, 10 months ago
- 9ac7b99 Revert "Add support for non-constant weights and biases in CpuFullyConnected" by Pablo Marquez Tello · 2 years, 10 months ago
- e42a87f Update cpu heuristics for GEMM by Gunes Bayir · 2 years, 10 months ago
- aed63ee Add support for non-constant weights and biases in CpuFullyConnected by Michele Di Giorgio · 3 years ago
- d216f57 Update cpu depthwise kernels by Freddie Liardet · 3 years ago
- c89998f Fix strict overflow warnings by Michalis Spyrou · 2 years, 11 months ago
- 6269f87 Fix depthwise convolution assembly kernels by Freddie Liardet · 3 years ago
- 6e90c12 Add missing limits include by Freddie Liardet · 3 years ago
- 9a1e28b Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1 by Gian Marco Iodice · 3 years ago
- a76e403 Fix A55 performance constant for fp16 hybrid gemm kernel by Georgios Pinitas · 3 years ago
- 120c87b Fix bare metal build issues by Freddie Liardet · 3 years ago
- 97426a7 Remove generated kernels that overlap hand-written ones by Georgios Pinitas · 3 years ago
- 387f80e Update GEMM assembly performance parameters by Georgios Pinitas · 3 years ago
- 5e61cb0 Add missing limits include by Freddie Liardet · 3 years ago
- 8bd2556 Fix vector_length identification mechanism for SVE by Georgios Pinitas · 3 years ago
- e7012a6 Fix bare metal build error by Freddie Liardet · 3 years ago
- 4ee8b15 Update GEMM assembly kernels by Georgios Pinitas · 3 years ago
- 0f033df Include limits header to fix errors reported by GCC11 by Michele Di Giorgio · 3 years ago
- 29599d0 Port NEGEMMConvolutionLayer by Manuel Bottini · 3 years ago
- 96f977e Port NEWinogradConvolutionLayer by Michalis Spyrou · 3 years ago
- 24b8920 Port NECol2ImKernel by Manuel Bottini · 3 years ago
- cfac51c Port NEGEMMLowp Part 2 by Manuel Bottini · 3 years, 1 month ago
- 9002899 Port NEIm2ColKernel by Manuel Bottini · 3 years ago
- 53832b2 Port NEGEMM to memory injecting interface (Part 2) by Michele Di Giorgio · 3 years, 1 month ago
- 93b75e0 Port NEGEMM to memory injecting interface (Part 1) by Michele Di Giorgio · 3 years, 1 month ago
- 5fdde99 Improve selection speed of CPU implementations by Georgios Pinitas · 3 years, 1 month ago
- 20fca52 Create core library using high priority operators by Michalis Spyrou · 3 years, 1 month ago
- ae58bdf Port NEGEMMLowp Part 1 by Manuel Bottini · 3 years, 1 month ago
- d02d5ed Integrate improved CPU depthwise convolution kernels by Michele Di Giorgio · 3 years, 6 months ago
- bdcdc39 Enable fat binary support by Georgios Pinitas · 3 years, 3 months ago
- 760b494 Fixed the compiler warning -Werror=type-limits by Pablo Marquez Tello · 3 years, 2 months ago
- b4bb6a0 Rename ported functions by Manuel Bottini · 3 years, 2 months ago
- 11d8415 Port DepthConvert to new Api by Georgios Pinitas · 3 years, 2 months ago
- f3c5259 Remove padding from NERemapKernel by Manuel Bottini · 3 years, 2 months ago
- 4f7693d Rename NEGEMMAssembly to CpuGemmAssembly by Sang-Hoon Park · 3 years, 2 months ago
- c4c595a Fix performance issues in NEReduction by Pablo Marquez Tello · 3 years, 2 months ago
- 7e9f34d Fix for tanh at small argument values by Aleksandr Nikolaev · 3 years, 2 months ago
- 6a5eee7 NEReduceMean failed on v8.2 debug build for Android by Manuel Bottini · 3 years, 2 months ago
- 6268742 Update operator list documentation. Part 2. by Teresa Charlin · 3 years, 2 months ago
- 223aba9 Remove stale/solved TODOs by Michele Di Giorgio · 3 years, 2 months ago
- 0758c4c Add missing limits include by Michalis Spyrou · 3 years, 3 months ago
- 778b95c Update assembly code by Michalis Spyrou · 3 years, 3 months ago
- 562bee5 Port CpuConvertFullyConnectedWeights to new API by Teresa Charlin · 3 years, 3 months ago
- b25883a Remove experimental tracing feature by Pablo Marquez Tello · 3 years, 3 months ago
- 60c3b0e Port DepthwiseConvolution to new API by Michalis Spyrou · 3 years, 3 months ago
- 9a81cd8 Fix bug on Implicit Padding for NEON FFT2D by Manuel Bottini · 3 years, 3 months ago
- 142e4ca Remove unused AccessWindow* includes by Michele Di Giorgio · 3 years, 3 months ago
- 327225d Port NEDirectConvolutionLayer to new API by Manuel Bottini · 3 years, 3 months ago
- 8a1ac61 Fix incorrect return statement in gemm_uint8 heuristic selection by Georgios Pinitas · 3 years, 3 months ago
- b71322d Fix convolution with bias segmentation fault issue by Sheri Zhang · 3 years, 3 months ago
- ca62c6f Mixed data-layout testing on high priority operators by Manuel Bottini · 3 years, 4 months ago
- 33f41fa Fix trademarks throughout the codebase by Michele Di Giorgio · 3 years, 4 months ago
- c6f9510 Remove Computer Vision generic interfaces and types by Georgios Pinitas · 3 years, 3 months ago
- a00180a Update U8 mmla kernel by Michalis Spyrou · 3 years, 4 months ago
- 1e3ab42 Make CpuPixelWiseMultiplicationKernel stateless by Sheri Zhang · 3 years, 4 months ago
- e81825b Workaround for compiler error in gcc-9.2 and 9.3 by Pablo Marquez Tello · 3 years, 4 months ago
- d1dc09c Port CpuTranspose to new API by Teresa Charlin · 3 years, 4 months ago
- 226169f Fix SVE build on newer compilers by Michalis Spyrou · 3 years, 4 months ago
- ab84088 Added Qasymm8 datatype support to NEROIPoolingLayer with Tests by Suhail Munshi · 3 years, 5 months ago
- a50f193 Updated cpu detection by Pablo Marquez Tello · 3 years, 4 months ago
- 10b3826 Port Arm(R) Neon(TM) Scale to new API by Manuel Bottini · 3 years, 5 months ago
- 00f4dfc Port Arm(R) Neon(TM) Dequantization to new API by Manuel Bottini · 3 years, 4 months ago
- 0ded4c4 Port Arm(R) Neon(TM) Quantization to new API by Manuel Bottini · 3 years, 4 months ago
- b88272e Remove usage of valid window region in NHWC CPU kernels - Part2 by SiCongLi · 3 years, 5 months ago
- c7b1e84 Remove usage of valid window region in NHWC CPU kernels - Part1 by SiCongLi · 3 years, 5 months ago
- b861074 Fix build errors for functions requiring SVE2 extension by Sang-Hoon Park · 3 years, 4 months ago
- dcf3c7e Move utility functions to NE/SVEMath by Sang-Hoon Park · 3 years, 4 months ago
- 473cb01 Remove Compute Vision CL support by Michalis Spyrou · 3 years, 5 months ago
- aac71e5 Update int8 A55 kernels by Georgios Pinitas · 3 years, 5 months ago
- 8a5146f Introduce Context opaque object of the new interface by Georgios Pinitas · 3 years, 6 months ago
- 6f45cf7 Account Ksections correctly for interleaved and hybrid_indirect gemm kernels by Georgios Pinitas · 3 years, 5 months ago
- 85e16c2 Use vector resizing instead of temporary assign in gemm_hybrid_indirect by Georgios Pinitas · 3 years, 5 months ago
- 27e67f0 Remove Compute Vision Neon support by Michalis Spyrou · 3 years, 5 months ago
- 0ad0129 Remove unreachable code in gemm_hybrid_quantized for computing k_block by Georgios Pinitas · 3 years, 5 months ago
- ac6499a Comply with Trademark rules for use of Neon, Arm and Mali by Sheri Zhang · 3 years, 5 months ago
- e28cf39 Regenerate kernels and update A55 versions by Georgios Pinitas · 3 years, 5 months ago
- bae2237 Fix data layout retention and handling of leftovers when there is no padding by Michele Di Giorgio · 3 years, 5 months ago
- 373b407 Make Softmax kernels and operator stateless by Michalis Spyrou · 3 years, 6 months ago
- 1928904 Make NEON Pooling kernels and functions state-less by Michele Di Giorgio · 3 years, 5 months ago
- cf87f50 Tweak scheduling use of SQDMULH in quantized AVG pooling by Michele Di Giorgio · 3 years, 5 months ago
- 74a142c Account for eventual padding in Pooling assembly kernels by Michele Di Giorgio · 3 years, 5 months ago
- 655e8c6 Make data_layout an attribute of the Scale function by Michele Di Giorgio · 3 years, 5 months ago
- c727d52 Add broadcasting support in NEPixelWiseMultiplicationKernel for FP16 by Pablo Marquez Tello · 3 years, 6 months ago
- ef28340 Force early exit of threads when output_height=1 and channels=1 in assembly pooling by Michele Di Giorgio · 3 years, 6 months ago
- 7249f15 Rename functions/classes for elementwise unary operations by Sang-Hoon Park · 3 years, 6 months ago
- 63001ac Rename functions/classes for elementwise operations by Sang-Hoon Park · 3 years, 6 months ago
- 360f576 Fix Scale CTS failures by Sheri Zhang · 3 years, 6 months ago
- f9943c8 Check for unsupported armv7a optimized pooling kernels by Michele Di Giorgio · 3 years, 6 months ago
- ae182f2 Check for FP16 CPU support in optimized pooling kernels by Michele Di Giorgio · 3 years, 6 months ago
- 098e94e Fix softmax SVE compiling failure without SVE2 support by Sheri Zhang · 3 years, 6 months ago
- fc6744a Make Sub kernel and operator stateless by Sheri Zhang · 3 years, 6 months ago
- d556d7b Integrate improved pooling layer on NEON by Michele Di Giorgio · 3 years, 9 months ago
- bd2c8e1 Fix doxygen references to new kernels by Michele Di Giorgio · 3 years, 6 months ago
- 0f7ef8a Make memset/copy functions state-less by Georgios Pinitas · 3 years, 6 months ago
- 6124390 Make Add kernel and operator stateless by Sheri Zhang · 3 years, 6 months ago
- 61ba069 Make Concatenate kernels and operator stateless by Georgios Pinitas · 3 years, 6 months ago
- b5a450a Add SVE for Softmax by Michalis Spyrou · 3 years, 6 months ago
- d2447bb Decouple data types of elementwise kernels by Sang-Hoon Park · 3 years, 6 months ago