Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 12833d063259cb7809a97a4262f821efdc40554f / src / runtime
  1. 12833d0 COMPMID-2204: RuntimeContext interface for NEON functions. by Georgios Pinitas · 5 years ago
  2. ed0e35b COMPMID-2246: Implement NEBoundingBoxTransform. by Pablo Tello · 4 years, 10 months ago
  3. c2a6059 COMPMID-2639: CLPadLayer support for 4D padding by Matthew Jackson · 4 years, 10 months ago
  4. 3f632f3 COMPMID-2418: CLDequantizationLayer support for QASYMM8_PER_CHANNEL by Michalis Spyrou · 4 years, 11 months ago
  5. d75f9e9 COMPMID-2318: Implement NEROIAlignLayer by Pablo Tello · 4 years, 11 months ago
  6. b9070a4 COMPMID-2605: Add asymmetric padding support for Deconvolution layer by Matthew Jackson · 4 years, 11 months ago
  7. 601ba3f COMPMID-2336: Validate multiplier and offset calculation in LSTMQuantized and DepthwiseConvolution functions by Michele Di Giorgio · 4 years, 11 months ago
  8. 35ea9a7 COMPMID-2317: Add new QASYMM16 data type by Michele Di Giorgio · 4 years, 11 months ago
  9. c853021 COMPMID-2417: Add new QASYMM8_PER_CHANNEL data type by Michalis Spyrou · 4 years, 11 months ago
  10. ec8cce8 COMPMID-2602: FullyConnected VTS failure on CL and Neon TENSOR_QUANT8_ASYMM by Gian Marco Iodice · 4 years, 11 months ago
  11. 205eed8 COMPMID-2080 Create a new kernel for CLPad with CONSTANT mode by Giorgio Arena · 5 years ago
  12. ecb1427 COMPMID-2492 Fix Segfault in NEDeconvolutionLayer for NHWC by SiCong Li · 4 years, 11 months ago
  13. 9f0d5ec COMPMID-2597: Checking bias type in NEDeconvolutionLayer::validate even when bias == nullptr by Manuel Bottini · 4 years, 11 months ago
  14. 0c5191c COMPMID-2336: Fix call to validate in NEDeconvolutionLayer by Michele Di Giorgio · 5 years ago
  15. 70e890e COMPMID-2541 Remove DepthwiseSeparableConvolutionLayer for NEON/CL by Giorgio Arena · 5 years ago
  16. f44fe3d COMPMID-2568: NEON Convolution layer failure by giuros01 · 5 years ago
  17. 93c70b8 COMPMID-2547: CLSpaceToBatchLayer causes NN Test Failures on QUANT8_ASYMM Data Type by Michele Di Giorgio · 5 years ago
  18. 7786f25 COMPMID-2526: Disabled Winograd when padding > half_kernel_size by Pablo Tello · 5 years ago
  19. a7acb3c COMPMID-1849: Implement CPPDetectionPostProcessLayer by Isabella Gottardi · 5 years ago
  20. 607339f COMPMID-2527: Remove activation function validation in CLWinogradConvolutionLayer by Gian Marco Iodice · 5 years ago
  21. f3622be COMPMID-1979: Fuse Activation Function in CLGEMM - part 4 by Gian Marco Iodice · 5 years ago
  22. 4d600c7 COMPMID-2500: Report error in Int8 Conv2d if multiplier > 1. by Georgios Pinitas · 5 years ago
  23. a231ea6 COMPMID-2336: Fix GEMMLowp 32bit check by Georgios Pinitas · 5 years ago
  24. 5d42b46 COMPMID-2467 Include IP information to the tuning config by Giorgio Arena · 5 years ago
  25. 883bad7 COMPMID-1849: Add DetectorPostProcess operator by Isabella Gottardi · 5 years ago
  26. bd9097d COMPMID-2336: Rename the new generic depthwise convolution on NEON by Gian Marco Iodice · 5 years ago
  27. 44f5572 COMPMID-2179 New generic depthwise convolution for NEON F32 NHWC by Giorgio Arena · 5 years ago
  28. cfa2bba COMPMID-2178: Update GEMM assembly code. by Georgios Pinitas · 5 years ago
  29. 10c53f1 COMPMID-2307: QUANTIZED_16BIT_LSTM operator for CL by Manuel Bottini · 5 years ago
  30. d25af67 COMPMID-2456: NEDeconvolutionLayer.cpp, NHWC is not supported by Manuel Bottini · 5 years ago
  31. 06be6f8 COMPMID-2096: Refactor the CLGEMMLowp function selection (heuristic) by Gian Marco Iodice · 5 years ago
  32. ff27192 COMPMID-2336: Fix validation for quantized NEDepthwiseConvolutionLayer by Michele Di Giorgio · 5 years ago
  33. ed75326 COMPMID-2283: Implement SIN operator for NEON by Manuel Bottini · 5 years ago
  34. ba27e44 COMPMID-2236: QUANTIZED_16BIT_LSTM operator for NEON by Michalis Spyrou · 5 years ago
  35. 4c75851 COMPMID-2421: Add 5x5 DepthwiseConv2d in the optimized path for NEON by Georgios Pinitas · 5 years ago
  36. c1b76fa COMPMID-2092: Refactoring interface for the deconvolution kernels (NEON/CL) by Manuel Bottini · 5 years ago
  37. d473386 COMPMID-2447: Align TFlite nearest neighbor NE/CL functions with ACL by Michalis Spyrou · 5 years ago
  38. 9c9b70b COMPMID-2410: Create a new GEMMLowpQuantizeDownInt32ToInt16ScaleKernel for CL by Manuel Bottini · 5 years ago
  39. ddec4d6 COMPMID-2458: Initialize uninitialized variables by Georgios Pinitas · 5 years ago
  40. 30271c7 COMPMID-2156: Optimized dilated convolution for NEON. by Georgios Pinitas · 5 years ago
  41. 37d080f COMPMID-2378: Sanitize GEMM configuration for NEON by Georgios Pinitas · 5 years ago
  42. 53860dd COMPMID-2432 Fix defects reported by Coverity by Michalis Spyrou · 5 years ago
  43. 5a1320b COMPMID-2429: Unexpected exception in destructor by Georgios Pinitas · 5 years ago
  44. 7b735dc COMPMID-2427: Remove structurally dead code by Georgios Pinitas · 5 years ago
  45. 338595b COMPMID-2234 : Add support for axis 3 in NE/CLConcatenateLayer by Vidhya Sudhan Loganathan · 5 years ago
  46. 7026b30 COMPMID-1979: Fuse Activation Function in CLGEMM - part 1 by Gian Marco Iodice · 5 years ago
  47. 49f8349 COMPMID-2428: Missing break statement. by Georgios Pinitas · 5 years ago
  48. 1109176 COMPMID-2245: Extend NEFuseBatchNormalization to support DepthwiseConvolution weights by Manuel Bottini · 5 years ago
  49. 26dcbc7 COMPMID-2158 Add SRGAN shapes in ConvolutionLayer heurists to dispatch direct convolution by Michalis Spyrou · 5 years ago
  50. bc415af COMPMID-2406: Create a new GEMMLowpQuantizeDownInt32ToInt16ScaleKernel for NEON by Gian Marco Iodice · 5 years ago
  51. 3d13af8 COMPMID-2235: Extend type support for CL/NEON DequantizationLayer. by Georgios Pinitas · 5 years ago
  52. a28aebc COMPMID-2383: DepthwiseConv use output qinfo by Pablo Tello · 5 years ago
  53. e16c890 COMPMID-2053: Fuse bias addition with CLGEMMMatrixMultiplyReshapedKernel by Gian Marco Iodice · 5 years ago
  54. 0cbfda6 COMPMID-2343: Add layer normalization support in NELSTMLayer by Michele Di Giorgio · 5 years ago
  55. 9175392 COMPMID-2387: Add support for NEMeanStdDevNormalizationLayer by Michele Di Giorgio · 5 years ago
  56. 2732cca COMPMID-2244: Extend CLFuseBatchNormalization to support DepthwiseConvolution weights by Manuel Bottini · 5 years ago
  57. 39438b4 COMPMID-2342: Add layer normalization support in CLLSTMLayer by Michele Di Giorgio · 5 years ago
  58. 5b48ad7 COMPMID-2386: Add support for CLMeanStdNormalizationLayer by Michele Di Giorgio · 5 years ago
  59. d513436 COMPMID-2321: PRELU support in NEActivationLayer by giuros01 · 5 years ago
  60. 6260e19 COMPMID-2394: (Nightly) Clang-tidy errors by Michalis Spyrou · 5 years ago
  61. d69b3b2 COMPMID-2238: Implement SPACE_TO_DEPTH for CL by Michalis Spyrou · 5 years ago
  62. b0f342e COMPMID-2171: Fuse bias addition with CLGEMMMatrixMultiplyReshapedOnlyRHSKernel by Georgios Pinitas · 5 years ago
  63. 4c5469b COMPMID-2225: Add interface support for new quantized data types. by Georgios Pinitas · 5 years ago
  64. 5b7d537 COMPMID-2237 Implement SPACE_TO_DEPTH for NEON by Manuel Bottini · 5 years ago
  65. 649962c COMPMID-2239 Implement DEPTH_TO_SPACE for CL by Michalis Spyrou · 5 years ago
  66. 6a4d542 COMPMID-2159 Implement Round for CL by Usama Arif · 5 years ago
  67. 0a5a57a COMPMID-2160: Implement Round for NEON by Usama Arif · 5 years ago
  68. 43c1bf8 COMPMID-2336: Add clang-tidy checks in assembly subfolder by Michalis Spyrou · 5 years ago
  69. 22f917c COMPMID-2240 Implement DEPTH_TO_SPACE for NEON by Michalis Spyrou · 5 years ago
  70. 1e6e1b8 COMPMID-2322: PRELU support in CLActivationLayer by giuros01 · 5 years ago
  71. 048b0f3 COMPMID-2278: Implement REDUCE_MAX operator for CL. by Usama Arif · 5 years ago
  72. 9e631c2 COMPMID-2252 NECast. by Usama Arif · 5 years ago
  73. 28f0dd9 COMPMID-2279: Implement REDUCE_MAX operator for NEON by Usama Arif · 5 years ago
  74. a4a08ad COMPMID-2280: Implement REDUCE_MIN operator for NEON by Usama Arif · 5 years ago
  75. b289050 COMPMID-2281: Implement REDUCE_MIN operator for CL by Usama Arif · 5 years ago
  76. 725b173 COMPMID-2214: Remove std::vector<std::unique_ptr<>> where possible. by Georgios Pinitas · 5 years ago
  77. ac33d7e COMPMID-2264: Implement LOG operator for CL by Usama Arif · 5 years ago
  78. 09f2497 COMPMID-2109: Remove CL/NE Width/Depth ConcatenateLayer functions. by Georgios Pinitas · 5 years ago
  79. f24411f COMPMID-2255: Implement ABS operator for CL by giuros01 · 5 years ago
  80. 5fc07aa COMPMID-2338: Remove CLGEMMInterleave4x4 and CLGEMMTranspose1xW by Gian Marco Iodice · 5 years ago
  81. 0af4418 COMPMID-2282: Implement SIN operator for CL by Michalis Spyrou · 5 years ago
  82. 32bd4dd IVGCVSW-2794: Return correct status for ReduceMean operations. by Georgios Pinitas · 5 years ago
  83. 6ac5992 COMPMID-2254 Implement NEAbsLayer by Manuel Bottini · 5 years ago
  84. 52c54f6 COMPMID-2270: Implement POW operator for CL by Usama Arif · 5 years ago
  85. eb312ef COMPMID-2267: Implement NEG for CL by Usama Arif · 5 years ago
  86. f391fff COMPMID-2302 NEDeconvolution: support for FP16 by Manuel Bottini · 5 years ago
  87. 68c6a79 COMPMID-2331: Fix FFTConvolutionLayer when no bias is used. by Georgios Pinitas · 5 years ago
  88. deaed2d COMPMID-2334: Extend search space for the EXHAUSTIVE OpenCL tuner by Gian Marco Iodice · 5 years ago
  89. 81e671e COMPMID-2269: Implement POW operator for NEON by Usama Arif · 5 years ago
  90. c255aa7 COMPMID-2263: Implement NELogLayer by Usama Arif · 5 years ago
  91. 4b5c588 COMPMID-2248 L2NormalizeLayer: negative axis by Manuel Bottini · 5 years ago
  92. 083a069 COMPMID-1995: Change CLTuner default mode to NORMAL by Michalis Spyrou · 5 years ago
  93. f6e475c COMPMID-2268: Implement NEG for NEON. by Usama Arif · 5 years ago
  94. bcfd09a COMPMID-2177 Fix clang warnings by Michalis Spyrou · 5 years ago
  95. 46a49a0 COMPMID-1635: Optimize CLDeconvolutionLayer - Part III by giuros01 · 5 years ago
  96. 154bc1c COMPMID-1973: Implement FFTConvolutionLayer on NEON by giuros01 · 5 years ago
  97. 299fdd3 COMPMID-2177 Fix clang warnings by Michalis Spyrou · 5 years ago
  98. 05fb448 COMPMID-1963: Implement FFT (2D) on NEON by giuros01 · 5 years ago
  99. a4f378d COMPMID-1995: Fix clang-tidy warnings by Michalis Spyrou · 5 years ago
  100. 8ec0bb6 COMPMID-2117 : Use FFT convolution if output feature map depth is less than input by Vidhya Sudhan Loganathan · 5 years ago