Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 173ba9bbb19ea83f951318d9989e440768b4de8f / src / core / NEON / kernels
  1. bb123bd MLCE-139 add align_corners parameter to NEScale by Sang-Hoon Park · 4 years, 6 months ago
  2. a5eb591 COMPMID-2819: Fix data layout in NEScaleKernel for nhwc. by Georgios Pinitas · 4 years, 6 months ago
  3. 4536193 COMPMID-2801: Add support for QASYMM8_SIGNED in NEDirectConvolutionLayerOutputStageKernel by Michele Di Giorgio · 4 years, 7 months ago
  4. 807ce59 COMPMID-2999: Nighliy Build Failure [655] - Bare metal build for armv7 by Michele Di Giorgio · 4 years, 6 months ago
  5. c6d9a8b COMPMID-2979 Remove padding from NEWinogradLayer by morgolock · 4 years, 7 months ago
  6. fb6aaeb COMPMID-2773 [NE] add support for QASYMM8_SIGNED to QuantizationLayer by Sang-Hoon Park · 4 years, 8 months ago
  7. f29d1b7 COMPMID-2608: Enable quantization with multiplier greater than 1 on NEON by Michele Di Giorgio · 4 years, 9 months ago
  8. deb3ac4 COMPMID-2807: Add support for QASYMM8_SIGNED in NEGEMMMatrixVectorMultiplyKernel by Michele Di Giorgio · 4 years, 7 months ago
  9. 0e4556c COMPMID-2819: Retain data layout in NESpaceToDepth and NEDepthToSpace by Georgios Pinitas · 4 years, 7 months ago
  10. 64e738f COMPMID-2819: Restrict cases where optimized NEPadLayer runs. by Georgios Pinitas · 4 years, 7 months ago
  11. c3a7420 COMPMID-2775 [NE] add support for QASYMM8_SIGNED to SoftmaxLayer by Sang-Hoon Park · 4 years, 8 months ago
  12. d817647 COMPMID-2767 [NEON] add support for QASYMM8_SIGNED to DequantizationLayer by Sang-Hoon Park · 4 years, 7 months ago
  13. e7be8a0 COMPMID-2980 (Nightly) armv7a build failures by Michalis Spyrou · 4 years, 7 months ago
  14. 62bdd8c COMPMID-2819: Retain configuration step data layout to avoid side-effects. by Pablo Tello · 4 years, 7 months ago
  15. 14d9d98 COMPMID-2819: Retain configuration step data layout to avoid side-effects. by Georgios Pinitas · 4 years, 7 months ago
  16. d7d7e90 COMPMID-2819: Update data type auto_init in Elementwise kernels. by Georgios Pinitas · 4 years, 7 months ago
  17. 27f223d COMPMID-2819: Perform sqrt in double domain for L2 pooling. by Georgios Pinitas · 4 years, 7 months ago
  18. 52ea9c2 COMPMID-2811: QASYMM8_SIGNED support in NEPixelwiseMultiplication. by Pablo Tello · 4 years, 7 months ago
  19. af486c1 COMPMID-2819: Remove invalid check in NEDirectConvolutionLayerOutputStageKernel by Georgios Pinitas · 4 years, 7 months ago
  20. 3384356 COMPMID-2754: Add support for QASYMM8_SIGNED in NE kernels/functions. by Georgios Pinitas · 4 years, 7 months ago
  21. f2cdce3 COMPMID-2841: Enable aarch32 builds by Georgios Pinitas · 4 years, 7 months ago
  22. 6f58b37 COMPMID-2798 Add support for QASYMM8_SIGNED in NEArithmeticSubtraction by Michalis Spyrou · 4 years, 7 months ago
  23. 8d4d1b8 COMPMID-2796: Add support for QASYMM8_SIGNED in NEActivationLayer and NEPReluLayer by Michalis Spyrou · 4 years, 8 months ago
  24. f01201a COMPMID-2305: NEDepthwiseConvolution 3x3: support for QUANT8_PER_CHANNEL_SYMM by Giuseppe Rossini · 4 years, 8 months ago
  25. 6e1791b COMPMID-2764: Add support for QASYMM8_SIGNED in NEConvolutionLayer. by Georgios Pinitas · 4 years, 7 months ago
  26. bc4d7c2 COMPMID-2797 Add support for QASYMM8_SIGNED in NEArithmeticAddition by Michalis Spyrou · 4 years, 7 months ago
  27. b714b1d COMPMID-2819: Fix output stage kernel dispatch selection. by Georgios Pinitas · 4 years, 7 months ago
  28. 448a81f COMPMID-2805: Add QASYMM8_SIGNED support in NEGEMMLowpOutputStage by Georgios Pinitas · 4 years, 8 months ago
  29. 0922dbb IVGBENCH-1661: Segfault on FP16 for NEON by Georgios Pinitas · 4 years, 8 months ago
  30. 21079dd COMPMID-2700: Use NEON wrapper on SoftmaxLayer by Manuel Bottini · 4 years, 9 months ago
  31. 581f178 COMPMID-2920: NEInstanceNormalization fails on NHWC validations by Manuel Bottini · 4 years, 8 months ago
  32. 8217c8e COMPMID-2895: Remove QASYMM8_PER_CHANNEL data type by Georgios Pinitas · 4 years, 8 months ago
  33. eaa01ab COMPMID-2671 use Signed32 for default output data type of ArgMinMax by Sang-Hoon Park · 4 years, 8 months ago
  34. 63d4dbd COMPMID-2452: Fix 32-bit per-channel convolution for NEON. by Georgios Pinitas · 4 years, 8 months ago
  35. 5264b7d COMPMID-2576: Fuse activation in Winograd output transform. by Pablo Tello · 4 years, 9 months ago
  36. dbdea0d COMPMID-2308: NEConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters by Georgios Pinitas · 4 years, 9 months ago
  37. fde0914 MLCE-146: VTS failures A55 by Pablo Tello · 4 years, 9 months ago
  38. 48b3ef8 COMPMID-2577: Fuse bias addition and activation in gemm assembly kernels by Georgios Pinitas · 4 years, 9 months ago
  39. d93e263 COMPMID-2708 NEDepthwiseConvolution Generic: support for QUANT8_PER_CHANNEL_SYMM by Giorgio Arena · 4 years, 9 months ago
  40. 84dca2d COMPMID-2486: Fix bare metal builds by Michalis Spyrou · 4 years, 9 months ago
  41. fae513c COMPMID-2486: Remove/add disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  42. d24affe COMPMID-2265 add support for Log Softmax to NEON by Sang-Hoon Park · 4 years, 9 months ago
  43. 7c60c99 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  44. 3d426c5 COMPMID-2697: Dynamic Tensors Type2 test case by Georgios Pinitas · 4 years, 9 months ago
  45. 6bff195 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  46. 58c71ef COMPMID-2257: Add support for QASYMM8 in NEGenerateProposals by Michele Di Giorgio · 4 years, 10 months ago
  47. d64a46c COMPMID-2699: Add support for QASYMM16 in NEQuantizationLayer by Michele Di Giorgio · 4 years, 9 months ago
  48. ae0fc86 COMPMID-2452: Dot product optimizations on merge/transforms by Georgios Pinitas · 4 years, 10 months ago
  49. 9637b2e COMPMID-2671: Change ArgMinMax NEON/CL output type to Signed32 by Michele Di Giorgio · 4 years, 10 months ago
  50. bc88c62 COMPMID-2452: Replace DOT assemble macro with the corresponding word directives. by Georgios Pinitas · 4 years, 10 months ago
  51. 572576a COMPMID-2674: Buffer overrun in GEMM assembly tranform kernels. by Georgios Pinitas · 4 years, 10 months ago
  52. c9564cb COMPMID-2257: Implement NEGenerateProposals. by Pablo Tello · 4 years, 10 months ago
  53. 769c638 COMPMID-2314: Implement NEON INSTANCE_NORMALIZATION function by Manuel Bottini · 4 years, 11 months ago
  54. e874ef9 COMPMID-2646: Wrap thread-related structure to ease bare-metal support by Georgios Pinitas · 4 years, 10 months ago
  55. 8d5dd86 COMPMID-2659: Activation.SQRT Failure on NEON by Michele Di Giorgio · 4 years, 10 months ago
  56. 9032ee3 MLCE-129: NEPad 30x slower than TensorFlow's implementation by Manuel Bottini · 5 years ago
  57. ffd31de COMPMID-2246: NEBoundingBoxTransform support QASYMM16 by Pablo Tello · 4 years, 10 months ago
  58. ed0e35b COMPMID-2246: Implement NEBoundingBoxTransform. by Pablo Tello · 4 years, 11 months ago
  59. b19c55d COMPMID-2640: Fix performance regression for Resnet101 Int8 on NEON by Gian Marco Iodice · 4 years, 11 months ago
  60. 3f632f3 COMPMID-2418: CLDequantizationLayer support for QASYMM8_PER_CHANNEL by Michalis Spyrou · 4 years, 11 months ago
  61. ebe2e8c COMPMID-2318: Implement NEROIAlignLayer by Pablo Tello · 4 years, 11 months ago
  62. d75f9e9 COMPMID-2318: Implement NEROIAlignLayer by Pablo Tello · 4 years, 11 months ago
  63. 3e183d9 COMPMID-2336: Update GEMM code by Michalis Spyrou · 4 years, 11 months ago
  64. 29a01c9 COMPMID-2417: NEDequantizationLayer support for QASYMM8_PER_CHANNEL by Michalis Spyrou · 5 years ago
  65. fb0fdcd COMPMID-2460: Add ELU activation on NEON,CL,GLES by Georgios Pinitas · 4 years, 11 months ago
  66. 400abc8 COMPMID-2596 MobilenetSSD produce wrong results by Michalis Spyrou · 5 years ago
  67. 81d7e78 COMPMID-2595: (Nightly) Mismatches in NEArgMinMax for FP16 by Michele Di Giorgio · 5 years ago
  68. 9d3e7f9 COMPMID-2569: Fix access window in NEGEMMTranspose1xWKernel and NEGEMMLowpMatrixMultiplyKernel by Michele Di Giorgio · 5 years ago
  69. 93c70b8 COMPMID-2547: CLSpaceToBatchLayer causes NN Test Failures on QUANT8_ASYMM Data Type by Michele Di Giorgio · 5 years ago
  70. 4746326 COMPMID-2336 Fix valgrind error for BatchNormalizationLayer on NEON with NHWC layout by Giorgio Arena · 5 years ago
  71. 1c29ffc COMPMID-2336: Fix build issues. by Georgios Pinitas · 5 years ago
  72. c4d5136 COMPMID-2493: Update qs8 in Depthwise assembly by Georgios Pinitas · 5 years ago
  73. f33484f COMPMID-2336: Guard quint8 gemm files for aarch64 only. by Georgios Pinitas · 5 years ago
  74. bd9097d COMPMID-2336: Rename the new generic depthwise convolution on NEON by Gian Marco Iodice · 5 years ago
  75. 44f5572 COMPMID-2179 New generic depthwise convolution for NEON F32 NHWC by Giorgio Arena · 5 years ago
  76. c050e0c COMPMID-2490: (Nightly) Valgrind error in NEON Scale by Michalis Spyrou · 5 years ago
  77. cfa2bba COMPMID-2178: Update GEMM assembly code. by Georgios Pinitas · 5 years ago
  78. f59b16f COMPMID-2336: Set the correct valid region to the concatenation layer output by Isabella Gottardi · 5 years ago
  79. 7faa0ec Use .inst directives instead of .int directives. by Ramana Radhakrishnan · 5 years ago
  80. cb6858f Update copyright years by Ramana Radhakrishnan · 5 years ago
  81. 10c53f1 COMPMID-2307: QUANTIZED_16BIT_LSTM operator for CL by Manuel Bottini · 5 years ago
  82. ff27192 COMPMID-2336: Fix validation for quantized NEDepthwiseConvolutionLayer by Michele Di Giorgio · 5 years ago
  83. ed75326 COMPMID-2283: Implement SIN operator for NEON by Manuel Bottini · 5 years ago
  84. ba27e44 COMPMID-2236: QUANTIZED_16BIT_LSTM operator for NEON by Michalis Spyrou · 5 years ago
  85. cd0b8b5 COMPMID-2236: Move assembly implementation interfaces to src folder by Georgios Pinitas · 5 years ago
  86. 4c75851 COMPMID-2421: Add 5x5 DepthwiseConv2d in the optimized path for NEON by Georgios Pinitas · 5 years ago
  87. d473386 COMPMID-2447: Align TFlite nearest neighbor NE/CL functions with ACL by Michalis Spyrou · 5 years ago
  88. 01fd6cf COMPMID-2336: Fix build for v8.2-a architectures by Georgios Pinitas · 5 years ago
  89. 30271c7 COMPMID-2156: Optimized dilated convolution for NEON. by Georgios Pinitas · 5 years ago
  90. ebdde65 COMPMID-2432: Fix defects reported by Coverity by Michalis Spyrou · 5 years ago
  91. 37d080f COMPMID-2378: Sanitize GEMM configuration for NEON by Georgios Pinitas · 5 years ago
  92. 95f9361 COMPMID-2185: Implement direct convolution 9x9 (NHWC) on NEON by Gian Marco Iodice · 5 years ago
  93. 7bb56c6 COMPMID-2409: Add QSYMM16 support for PixelWiseMultiplication for NEON by Manuel Bottini · 5 years ago
  94. 4646d2e COMPMID-2072: Use a constexpr for num_elems_processed_per_iteration where possible by Michele Di Giorgio · 5 years ago
  95. c9573f3 COMPMID-2407: Add (logistic and tanh) activation support for QSYMM16 for NEON by giuros01 · 5 years ago
  96. 3262042 COMPMID-2426: Logical dead code fix by Georgios Pinitas · 5 years ago
  97. 338595b COMPMID-2234 : Add support for axis 3 in NE/CLConcatenateLayer by Vidhya Sudhan Loganathan · 5 years ago
  98. 1109176 COMPMID-2245: Extend NEFuseBatchNormalization to support DepthwiseConvolution weights by Manuel Bottini · 5 years ago
  99. bc415af COMPMID-2406: Create a new GEMMLowpQuantizeDownInt32ToInt16ScaleKernel for NEON by Gian Marco Iodice · 5 years ago
  100. 3d13af8 COMPMID-2235: Extend type support for CL/NEON DequantizationLayer. by Georgios Pinitas · 5 years ago