Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 399f623e29500e28c34e8a5adb07dd15e7f26c0c / src / runtime / NEON
  1. 53832b2 Port NEGEMM to memory injecting interface (Part 2) by Michele Di Giorgio · 3 years, 2 months ago
  2. 93b75e0 Port NEGEMM to memory injecting interface (Part 1) by Michele Di Giorgio · 3 years, 2 months ago
  3. d7316eb Port NEGEMMConv2d to memory injecting interface by Michele Di Giorgio · 3 years, 2 months ago
  4. 20fca52 Create core library using high priority operators by Michalis Spyrou · 3 years, 3 months ago
  5. ae58bdf Port NEGEMMLowp Part 1 by Manuel Bottini · 3 years, 2 months ago
  6. ef5aac6 Add FP16 support to CLRemap by Freddie Liardet · 3 years, 3 months ago
  7. d02d5ed Integrate improved CPU depthwise convolution kernels by Michele Di Giorgio · 3 years, 7 months ago
  8. a341791 Remove implementation headers from NESoftmaxLayer public header by Georgios Pinitas · 3 years, 2 months ago
  9. 94f799e Fix incorrect memory handling in ported functions by Manuel Bottini · 3 years, 3 months ago
  10. a5c428a Fixed segfault in NEGEMMConv2d by Pablo Tello · 3 years, 3 months ago
  11. 8ae3cda Revert "Implement memory injection in CpuDirectGemmConv2d" by Michele Di Giorgio · 3 years, 3 months ago
  12. b4bb6a0 Rename ported functions by Manuel Bottini · 3 years, 3 months ago
  13. b3be457 Implement memory injection in CpuDirectGemmConv2d by Sang-Hoon Park · 3 years, 3 months ago
  14. d89e2fa Create CpuGemmDirectConv2d by Sang-Hoon Park · 3 years, 3 months ago
  15. 11d8415 Port DepthConvert to new Api by Georgios Pinitas · 3 years, 4 months ago
  16. f3c5259 Remove padding from NERemapKernel by Manuel Bottini · 3 years, 4 months ago
  17. 9e1f074 Port NEFlatten layer to a memory injecting interface by Georgios Pinitas · 3 years, 3 months ago
  18. 0c19cbd Move memory management out of CpuPooling by Michele Di Giorgio · 3 years, 4 months ago
  19. 4f7693d Rename NEGEMMAssembly to CpuGemmAssembly by Sang-Hoon Park · 3 years, 4 months ago
  20. 13c497a Fix Macros.h include in NEScale by Michele Di Giorgio · 3 years, 4 months ago
  21. 78e7691 Remove TODOs by Sheri Zhang · 3 years, 4 months ago
  22. ef516e8 Rename Quantization/Dequantization kernels/operators to imperative mood by Georgios Pinitas · 3 years, 4 months ago
  23. 0dc0d8e Rename PixelwiseMultiplications to Mul for simplicity by Georgios Pinitas · 3 years, 4 months ago
  24. 223aba9 Remove stale/solved TODOs by Michele Di Giorgio · 3 years, 4 months ago
  25. a7a7436 Fix Depthwise failure in Cpu backend by Michalis Spyrou · 3 years, 4 months ago
  26. 3294449 Fix biases check in NEDepthwise by Michalis Spyrou · 3 years, 4 months ago
  27. 562bee5 Port CpuConvertFullyConnectedWeights to new API by Teresa Charlin · 3 years, 5 months ago
  28. 60c3b0e Port DepthwiseConvolution to new API by Michalis Spyrou · 3 years, 5 months ago
  29. 327225d Port NEDirectConvolutionLayer to new API by Manuel Bottini · 3 years, 5 months ago
  30. 28fcc35 Substitute NEFullyConnectedLayerReshapeWeights by NETranspose by Teresa Charlin · 3 years, 5 months ago
  31. 9d061b0 Add per channel quantization support for NEDeconvolutionLayer by Freddie Liardet · 3 years, 5 months ago
  32. ca62c6f Mixed data-layout testing on high priority operators by Manuel Bottini · 3 years, 5 months ago
  33. 33f41fa Fix trademarks throughout the codebase by Michele Di Giorgio · 3 years, 6 months ago
  34. 5f91b5d Remove alignment FIXME by Michele Di Giorgio · 3 years, 5 months ago
  35. 26c5c0f NEGEMMConvolution and NEGEMMConv2d produce different results by Manuel Bottini · 3 years, 5 months ago
  36. 1e3ab42 Make CpuPixelWiseMultiplicationKernel stateless by Sheri Zhang · 3 years, 5 months ago
  37. 383de02 Fixed compiler errors by Pablo Marquez Tello · 3 years, 5 months ago
  38. d1dc09c Port CpuTranspose to new API by Teresa Charlin · 3 years, 6 months ago
  39. ab84088 Added Qasymm8 datatype support to NEROIPoolingLayer with Tests by Suhail Munshi · 3 years, 7 months ago
  40. 10b3826 Port Arm(R) Neon(TM) Scale to new API by Manuel Bottini · 3 years, 6 months ago
  41. 6b0bf99 Add CpuPRelu operators by Sang-Hoon Park · 3 years, 6 months ago
  42. 00f4dfc Port Arm(R) Neon(TM) Dequantization to new API by Manuel Bottini · 3 years, 6 months ago
  43. 0ded4c4 Port Arm(R) Neon(TM) Quantization to new API by Manuel Bottini · 3 years, 6 months ago
  44. 668ccdc Add dynamic tensor support to CpuElementwise by Sang-Hoon Park · 3 years, 7 months ago
  45. 023efb3 Make auxiliary tensor within NEGEMMConvolutionLayer resizable by Georgios Pinitas · 3 years, 6 months ago
  46. 473cb01 Remove Compute Vision CL support by Michalis Spyrou · 3 years, 6 months ago
  47. 9a67178 Avoid division with zero by Georgios Pinitas · 3 years, 6 months ago
  48. 27e67f0 Remove Compute Vision Neon support by Michalis Spyrou · 3 years, 6 months ago
  49. ac6499a Comply with Trademark rules for use of Neon, Arm and Mali by Sheri Zhang · 3 years, 7 months ago
  50. f55e3fb Free _gemm_output_3d's memory region after run() by Giorgio Arena · 3 years, 6 months ago
  51. d820ed7 Set _gemm_output_3d's padding as the output's in NEGEMMConvolutionLayer by Giorgio Arena · 3 years, 6 months ago
  52. 5b50f42 Update deprecation notices by Giorgio Arena · 3 years, 6 months ago
  53. 2ee9801 Handle Conv2d layer with implicit output padding in NHWC by Georgios Pinitas · 3 years, 6 months ago
  54. 373b407 Make Softmax kernels and operator stateless by Michalis Spyrou · 3 years, 7 months ago
  55. 1928904 Make NEON Pooling kernels and functions state-less by Michele Di Giorgio · 3 years, 7 months ago
  56. 655e8c6 Make data_layout an attribute of the Scale function by Michele Di Giorgio · 3 years, 7 months ago
  57. 26cf798 Fix NEON/CL CustomConvolution failures by Manuel Bottini · 3 years, 7 months ago
  58. 1e0208a Make CLArithmeticAddition kernel and function state-less by Michele Di Giorgio · 3 years, 7 months ago
  59. 7249f15 Rename functions/classes for elementwise unary operations by Sang-Hoon Park · 3 years, 7 months ago
  60. 63001ac Rename functions/classes for elementwise operations by Sang-Hoon Park · 3 years, 7 months ago
  61. 2a0939d Fixed segfault NEDeconvLayer due to overflow. by Pablo Marquez Tello · 3 years, 7 months ago
  62. 0094c02 Add window parameter to scheduler by Sang-Hoon Park · 3 years, 7 months ago
  63. fc6744a Make Sub kernel and operator stateless by Sheri Zhang · 3 years, 8 months ago
  64. d556d7b Integrate improved pooling layer on NEON by Michele Di Giorgio · 3 years, 10 months ago
  65. 0f7ef8a Make memset/copy functions state-less by Georgios Pinitas · 3 years, 8 months ago
  66. 6124390 Make Add kernel and operator stateless by Sheri Zhang · 3 years, 8 months ago
  67. 61ba069 Make Concatenate kernels and operator stateless by Georgios Pinitas · 3 years, 8 months ago
  68. 8d5337e Add explicit cast to fix gcc10 build error by Sang-Hoon Park · 3 years, 7 months ago
  69. ddd79f5 Release winograd transformed weights if not needed on NEON by Georgios Pinitas · 3 years, 7 months ago
  70. f8f0442 Make CpuActivation stateless by Georgios Pinitas · 3 years, 8 months ago
  71. 70eb53b Make CpuFloorKernel kernel stateless by Georgios Pinitas · 3 years, 8 months ago
  72. ea7de7b Enable FFT for FP16 by Giorgio Arena · 3 years, 9 months ago
  73. c53266e Remove (CL/NE)UpsampleLayer in favor to (NE/CL)Scale by Georgios Pinitas · 3 years, 9 months ago
  74. 0b1c2db Remove (NE/CL)YoloLayer support by Georgios Pinitas · 3 years, 9 months ago
  75. ec2256b Move NEGEMMAssemblyDispatch as an internal function by Georgios Pinitas · 3 years, 9 months ago
  76. e2696b1 Wrap Flatten layer over reshape by Georgios Pinitas · 3 years, 9 months ago
  77. 8c3c0e7 Remove (NE/CL)ComputeAllAnchors function by Georgios Pinitas · 3 years, 9 months ago
  78. f7c5a41 Remove support for NEIm2Col, NECol2Im, NEGEMMInterleave4x4, NEGEMMTranspose1xW by Georgios Pinitas · 3 years, 9 months ago
  79. 7b48166 Fix NEGEMMLowpMatrixMultiplyCore nonfused activation by SiCong Li · 3 years, 9 months ago
  80. 96b16b6 Remove support for (NE/CL)LocallyConnectedLayer by Georgios Pinitas · 3 years, 9 months ago
  81. 4c634e0 Initialize batches variable in NEGEMMAssemblyDispatch by Georgios Pinitas · 3 years, 9 months ago
  82. 40f51a6 Update default C++ standard to C++14 by Georgios Pinitas · 3 years, 9 months ago
  83. 71696ba Initialize unitialized M parameter in NEGEMMAssemblyDispatch by Georgios Pinitas · 3 years, 9 months ago
  84. 3909670 Validate support of fused activation in NEFullyConnectedLayer by Georgios Pinitas · 3 years, 9 months ago
  85. 58bce68 COMPMID-3962: Add Logical And, Or, Not support on NEON by Georgios Pinitas · 3 years, 10 months ago
  86. c0b6f76 COMPMID-3776: Indirect GEMM by Georgios Pinitas · 3 years, 10 months ago
  87. ebcebf1 COMPMID-3638: Move NEON kernels by Michalis Spyrou · 3 years, 10 months ago
  88. 9f89375 COMPMID-3876: Fix wrong validation logic in QLSTM by Sang-Hoon Park · 3 years, 10 months ago
  89. 68dd25f COMPMID-3637: Move utility headers from arm_compute to src by Sang-Hoon Park · 3 years, 10 months ago
  90. e4558b5 COMPMID-3163: Remove padding from NEDepthwiseConvolutionLayerNativeKernel by Sang-Hoon Park · 4 years ago
  91. 87350f4 COMPMID-3144: Remove padding from NEDirectConvolutionLayerKernel by Manuel Bottini · 4 years ago
  92. f316e9a MLCE-229: enabled gemmlowp asm kernel for neg shifts by morgolock · 3 years, 11 months ago
  93. 4d91dc6 COMPMID-3181: Remove padding from NEReductionOperationKernel by Sheri Zhang · 4 years ago
  94. fc2f6d0 COMPMID-3145: Remove padding from NEScaleKernel by Manuel Bottini · 4 years ago
  95. 840a72c COMPMID-3773: Fix the accumulation of projection in QLSTM by Sang-Hoon Park · 4 years ago
  96. 245ba05 COMPMID-3783: Segfaulting in Reduction layer with NEON on Mate20 with HFNet by Sheri Zhang · 4 years ago
  97. 9e698d5 COMPMID-3757: (u)int8: Don't select the 16-bit route on A53 for cases with very few rows by David Mansell · 4 years ago
  98. fa269bb MLCE-229: Fixed requantization per channel in asm kernel by morgolock · 4 years ago
  99. 7d0adc6 COMPMID-3151: Remove NEDepthwiseConvolutionLayer3x3Kernel by Georgios Pinitas · 4 years ago
  100. ec4dee8 COMPMID-3750: Disable asm kernels when shifts are negative. by morgolock · 4 years ago