Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / eaa01ab593428bc7267ebbe107b2d813a11b64b5 / src / runtime
  1. eaa01ab COMPMID-2671 use Signed32 for default output data type of ArgMinMax by Sang-Hoon Park · 4 years, 8 months ago
  2. 77d4252 COMPMID-2853: VGG16 regression for fp32 by Georgios Pinitas · 4 years, 8 months ago
  3. 63d4dbd COMPMID-2452: Fix 32-bit per-channel convolution for NEON. by Georgios Pinitas · 4 years, 8 months ago
  4. 5264b7d COMPMID-2576: Fuse activation in Winograd output transform. by Pablo Tello · 4 years, 9 months ago
  5. dbdea0d COMPMID-2308: NEConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters by Georgios Pinitas · 4 years, 9 months ago
  6. 0fc2d7a COMPMID-2862: remove forward declaration of ReductionOperation by Sang-Hoon Park · 4 years, 8 months ago
  7. 7ae80a9 COMPMID-2549: Add GLES Runtime Context interfaces. by Georgios Pinitas · 4 years, 9 months ago
  8. 62eeb53 COMPMID-2266: [CL] add support for Log Softmax by Sang-Hoon Park · 4 years, 8 months ago
  9. 44bfc3f COMPMID-1671: Allow fp mixed precision in CLFCLayer. by Georgios Pinitas · 4 years, 8 months ago
  10. 2697fd8 COMPMID-2707: add keep_dims parameter to Reduction Operation by Sang-Hoon Park · 4 years, 9 months ago
  11. df4cf57 COMPMID-2306: CLDepthwiseConvolution: support for QUANT8_PER_CHANNEL_SYMM by Michele Di Giorgio · 4 years, 9 months ago
  12. 8b72199 COMPMID-1889: Fuse bias addition and output stage in CLFCLayer. by Georgios Pinitas · 4 years, 8 months ago
  13. d985378 COMPMID-2588: Optimize the output detection kernel required by MobileNet-SSD (~27% improvement) by Giuseppe Rossini · 4 years, 9 months ago
  14. 279814b COMPMID-2481: Add InputQuantizationInfo!=OutputQuantization Info tests for DeconvolutionLayer by Manuel Bottini · 4 years, 9 months ago
  15. 0726398 COMPMID-2501: Support multiplier > 1 during QASYMM8 requantization for Quantized LSTM by Manuel Bottini · 4 years, 9 months ago
  16. 05069f0 COMPMID-2515: Merge optimized depthwise convolution to the generic depthwise convolution function by Manuel Bottini · 4 years, 9 months ago
  17. 48b3ef8 COMPMID-2577: Fuse bias addition and activation in gemm assembly kernels by Georgios Pinitas · 4 years, 9 months ago
  18. d93e263 COMPMID-2708 NEDepthwiseConvolution Generic: support for QUANT8_PER_CHANNEL_SYMM by Giorgio Arena · 4 years, 9 months ago
  19. fae513c COMPMID-2486: Remove/add disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  20. 3f8cc58 COMPMID-2813: Update the heuristic in CLDepthWiseConvolutionLayer by Gian Marco Iodice · 4 years, 9 months ago
  21. d24affe COMPMID-2265 add support for Log Softmax to NEON by Sang-Hoon Park · 4 years, 9 months ago
  22. 7c60c99 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  23. db8485a COMPMID-2205: CL runtime context. by Pablo Tello · 4 years, 10 months ago
  24. a046e16 COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM8 NHWC by Michele Di Giorgio · 4 years, 9 months ago
  25. 6bff195 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  26. 0d54804 COMPMID-2572: Update the heuristic in CLGEMM for FP16 by Gian Marco Iodice · 4 years, 9 months ago
  27. b27e13a COMPMID-2685: [CL] Use Weights manager by Michalis Spyrou · 4 years, 9 months ago
  28. 2ff0009 COMPMID-2661: Implement complex function dynamic tensor support. by Georgios Pinitas · 4 years, 9 months ago
  29. 58c71ef COMPMID-2257: Add support for QASYMM8 in NEGenerateProposals by Michele Di Giorgio · 4 years, 9 months ago
  30. d64a46c COMPMID-2699: Add support for QASYMM16 in NEQuantizationLayer by Michele Di Giorgio · 4 years, 9 months ago
  31. 79f88e6 COMPMID-2313: Implement CL INSTANCE_NORMALIZATION function by Manuel Bottini · 4 years, 10 months ago
  32. 20c2b50 COMPMID-2693 Weights manager to mark the initial weights as unsued by Michalis Spyrou · 4 years, 9 months ago
  33. b94c368 COMPMID-2645: Detection Post-Process fixes by Georgios Pinitas · 4 years, 9 months ago
  34. 3d8fe49 INFPRF-609:Performance Issue of the Latest ArmCL by giuros01 · 4 years, 9 months ago
  35. 5c4a8e9 COMPMID-2592 Create a new kernel for CLPad with SYMMETRIC and REFLECT mode by Giorgio Arena · 4 years, 10 months ago
  36. 879d131 COMPMID-2452: Fix compilation issues on armclang by Georgios Pinitas · 4 years, 9 months ago
  37. 40958ad COMPMID-2663: Interface to unbound mappings. by Georgios Pinitas · 4 years, 10 months ago
  38. 6b612f5 COMPMID-2310: CLGenerateProposalsLayer: support for QASYMM8 by Michele Di Giorgio · 4 years, 10 months ago
  39. 05639f6 COMPMID-2571: Add support for FP16 in CLGEMMReshaped - part 1 by Gian Marco Iodice · 4 years, 10 months ago
  40. 1a569a3 COMPMID-2161 [NEON] Create IWeightManager class by Michalis Spyrou · 4 years, 10 months ago
  41. 2725197 MLCE-140: Workaround multi-threading problem with NEON backend by Pablo Tello · 4 years, 10 months ago
  42. b785dd4 COMPMID-2670: [CL/GC] Create a test case for dynamic tensor support by Georgios Pinitas · 4 years, 10 months ago
  43. 4c268b9 COMPMID-2681: Use NE/CL/Pad in NE/CL/GenerateProposalsLayer by Michele Di Giorgio · 4 years, 10 months ago
  44. c9564cb COMPMID-2257: Implement NEGenerateProposals. by Pablo Tello · 4 years, 10 months ago
  45. 769c638 COMPMID-2314: Implement NEON INSTANCE_NORMALIZATION function by Manuel Bottini · 4 years, 11 months ago
  46. 26014cf COMPMID-2649: Generalize MemoryGroup. by Georgios Pinitas · 4 years, 10 months ago
  47. caa7dee COMPMID-2641 [NEON] Create a test case for dynamic tensor support by Michalis Spyrou · 4 years, 10 months ago
  48. 70ad619 COMPMID-2635: Add support for QASYMM8 in CPPBoxWithNonMaximaSuppressionLimit by Michele Di Giorgio · 4 years, 10 months ago
  49. 9032ee3 MLCE-129: NEPad 30x slower than TensorFlow's implementation by Manuel Bottini · 5 years ago
  50. 12833d0 COMPMID-2204: RuntimeContext interface for NEON functions. by Georgios Pinitas · 5 years ago
  51. ed0e35b COMPMID-2246: Implement NEBoundingBoxTransform. by Pablo Tello · 4 years, 10 months ago
  52. c2a6059 COMPMID-2639: CLPadLayer support for 4D padding by Matthew Jackson · 4 years, 10 months ago
  53. 3f632f3 COMPMID-2418: CLDequantizationLayer support for QASYMM8_PER_CHANNEL by Michalis Spyrou · 4 years, 11 months ago
  54. d75f9e9 COMPMID-2318: Implement NEROIAlignLayer by Pablo Tello · 4 years, 11 months ago
  55. b9070a4 COMPMID-2605: Add asymmetric padding support for Deconvolution layer by Matthew Jackson · 4 years, 11 months ago
  56. 601ba3f COMPMID-2336: Validate multiplier and offset calculation in LSTMQuantized and DepthwiseConvolution functions by Michele Di Giorgio · 4 years, 11 months ago
  57. 35ea9a7 COMPMID-2317: Add new QASYMM16 data type by Michele Di Giorgio · 4 years, 11 months ago
  58. c853021 COMPMID-2417: Add new QASYMM8_PER_CHANNEL data type by Michalis Spyrou · 4 years, 11 months ago
  59. ec8cce8 COMPMID-2602: FullyConnected VTS failure on CL and Neon TENSOR_QUANT8_ASYMM by Gian Marco Iodice · 4 years, 11 months ago
  60. 205eed8 COMPMID-2080 Create a new kernel for CLPad with CONSTANT mode by Giorgio Arena · 5 years ago
  61. ecb1427 COMPMID-2492 Fix Segfault in NEDeconvolutionLayer for NHWC by SiCong Li · 4 years, 11 months ago
  62. 9f0d5ec COMPMID-2597: Checking bias type in NEDeconvolutionLayer::validate even when bias == nullptr by Manuel Bottini · 4 years, 11 months ago
  63. 0c5191c COMPMID-2336: Fix call to validate in NEDeconvolutionLayer by Michele Di Giorgio · 5 years ago
  64. 70e890e COMPMID-2541 Remove DepthwiseSeparableConvolutionLayer for NEON/CL by Giorgio Arena · 5 years ago
  65. f44fe3d COMPMID-2568: NEON Convolution layer failure by giuros01 · 5 years ago
  66. 93c70b8 COMPMID-2547: CLSpaceToBatchLayer causes NN Test Failures on QUANT8_ASYMM Data Type by Michele Di Giorgio · 5 years ago
  67. 7786f25 COMPMID-2526: Disabled Winograd when padding > half_kernel_size by Pablo Tello · 5 years ago
  68. a7acb3c COMPMID-1849: Implement CPPDetectionPostProcessLayer by Isabella Gottardi · 5 years ago
  69. 607339f COMPMID-2527: Remove activation function validation in CLWinogradConvolutionLayer by Gian Marco Iodice · 5 years ago
  70. f3622be COMPMID-1979: Fuse Activation Function in CLGEMM - part 4 by Gian Marco Iodice · 5 years ago
  71. 4d600c7 COMPMID-2500: Report error in Int8 Conv2d if multiplier > 1. by Georgios Pinitas · 5 years ago
  72. a231ea6 COMPMID-2336: Fix GEMMLowp 32bit check by Georgios Pinitas · 5 years ago
  73. 5d42b46 COMPMID-2467 Include IP information to the tuning config by Giorgio Arena · 5 years ago
  74. 883bad7 COMPMID-1849: Add DetectorPostProcess operator by Isabella Gottardi · 5 years ago
  75. bd9097d COMPMID-2336: Rename the new generic depthwise convolution on NEON by Gian Marco Iodice · 5 years ago
  76. 44f5572 COMPMID-2179 New generic depthwise convolution for NEON F32 NHWC by Giorgio Arena · 5 years ago
  77. cfa2bba COMPMID-2178: Update GEMM assembly code. by Georgios Pinitas · 5 years ago
  78. 10c53f1 COMPMID-2307: QUANTIZED_16BIT_LSTM operator for CL by Manuel Bottini · 5 years ago
  79. d25af67 COMPMID-2456: NEDeconvolutionLayer.cpp, NHWC is not supported by Manuel Bottini · 5 years ago
  80. 06be6f8 COMPMID-2096: Refactor the CLGEMMLowp function selection (heuristic) by Gian Marco Iodice · 5 years ago
  81. ff27192 COMPMID-2336: Fix validation for quantized NEDepthwiseConvolutionLayer by Michele Di Giorgio · 5 years ago
  82. ed75326 COMPMID-2283: Implement SIN operator for NEON by Manuel Bottini · 5 years ago
  83. ba27e44 COMPMID-2236: QUANTIZED_16BIT_LSTM operator for NEON by Michalis Spyrou · 5 years ago
  84. 4c75851 COMPMID-2421: Add 5x5 DepthwiseConv2d in the optimized path for NEON by Georgios Pinitas · 5 years ago
  85. c1b76fa COMPMID-2092: Refactoring interface for the deconvolution kernels (NEON/CL) by Manuel Bottini · 5 years ago
  86. d473386 COMPMID-2447: Align TFlite nearest neighbor NE/CL functions with ACL by Michalis Spyrou · 5 years ago
  87. 9c9b70b COMPMID-2410: Create a new GEMMLowpQuantizeDownInt32ToInt16ScaleKernel for CL by Manuel Bottini · 5 years ago
  88. ddec4d6 COMPMID-2458: Initialize uninitialized variables by Georgios Pinitas · 5 years ago
  89. 30271c7 COMPMID-2156: Optimized dilated convolution for NEON. by Georgios Pinitas · 5 years ago
  90. 37d080f COMPMID-2378: Sanitize GEMM configuration for NEON by Georgios Pinitas · 5 years ago
  91. 53860dd COMPMID-2432 Fix defects reported by Coverity by Michalis Spyrou · 5 years ago
  92. 5a1320b COMPMID-2429: Unexpected exception in destructor by Georgios Pinitas · 5 years ago
  93. 7b735dc COMPMID-2427: Remove structurally dead code by Georgios Pinitas · 5 years ago
  94. 338595b COMPMID-2234 : Add support for axis 3 in NE/CLConcatenateLayer by Vidhya Sudhan Loganathan · 5 years ago
  95. 7026b30 COMPMID-1979: Fuse Activation Function in CLGEMM - part 1 by Gian Marco Iodice · 5 years ago
  96. 49f8349 COMPMID-2428: Missing break statement. by Georgios Pinitas · 5 years ago
  97. 1109176 COMPMID-2245: Extend NEFuseBatchNormalization to support DepthwiseConvolution weights by Manuel Bottini · 5 years ago
  98. 26dcbc7 COMPMID-2158 Add SRGAN shapes in ConvolutionLayer heurists to dispatch direct convolution by Michalis Spyrou · 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