Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / a2b89ca5407532257a959ad1852f29187e1be4ac
  1. a2b89ca IVGCVSW-631 Neon support for Softmax beta parameter (F32 only) by Pablo Palmier · 7 years ago
  2. 5948634 COMPMID-617 Add window validation to CLDirectConvolutionLayer by Giorgio Arena · 7 years ago
  3. 424eb5d COMPMID-556: Fix dangling references in NEFillBorder by Georgios Pinitas · 7 years ago
  4. e82cd72 COMPMID-556: Add SoftmaxLayer benchmarks by Georgios Pinitas · 7 years ago
  5. 4af62a0 APPBROWSER-289 DirectConvolution1*1 optimization for FP16, and fix a typo in PoolingLayer by Xinghang Zhou · 7 years ago
  6. 7c435f2 COMPMID-728 - Added validation for transpose by Gian Marco · 7 years ago
  7. 07c37f9 APPBROWSER-313: Performance improvement for softmax layer by Joel Liang · 7 years ago
  8. d9f8071 Add missing break by Kevin Petit · 7 years ago
  9. 5124be5 COMPMID-661: Convolution quantized (#32) by Chunosov · 7 years ago
  10. 9873ea3 COMPMID-556: Revert COMPMID-652 by Georgios Pinitas · 7 years ago
  11. b8ab997 COMPMID-617 Add validation window to CLSoftmaxLayer by Giorgio Arena · 7 years ago
  12. e5384ff APPBROWSER-306, APPBROWSER-298: Code refactoring for fill_border.cs by Joel Liang · 7 years ago
  13. 4f7f255 APPBROWSER-332 Code refactoring for batchnormalization_layer.cs by zhenglin · 7 years ago
  14. b9d38ee APPBROWSER-312 Fully connected performance optimization by Frank Lei · 7 years ago
  15. 397d58a COMPMID-617: Add validate support for NEON ArithmeticLayer by Ioan-Cristian Szabo · 7 years ago
  16. 6f6639d COMPMID-632: Make sure we hit the dot product kernel for cpu 0xd0f on the fast_model by Pablo Tello · 7 years ago
  17. c7f9b89 COMPMID-722 - Support for vector-matrix in GEMMLowp (NEON) by Gian Marco · 7 years ago
  18. 23ac91b APPBROWSER-290: DC5x5 optimization for FP16 by ASIAPAC\steli01 · 7 years ago
  19. 923241e APPBROWSER-314: Performance optimazation for BatchNormalizationLayer by zhenglin · 7 years ago
  20. 0bc5a25 COMPMID-556 - Fix SGEMM example by Gian Marco · 7 years ago
  21. 3bcf15d COMPMID-675: NEGEMMLowp Assembly, fixed ananke's dot product kernel mismatches by Pablo Tello · 7 years ago
  22. 0a878ae COMPMID-556: Added a rounding policy to the quantize function by Jaroslaw Rzepecki · 7 years ago
  23. 8795ffb COMPMID-700: Adds CPPPermute function by Georgios Pinitas · 7 years ago
  24. ab49073 COMPMID-556 Fix build issues with Clang by Anthony Barbier · 7 years ago
  25. f8b41e9 APPBROWSER-294: Fix the validation failure issue of DepthConcatLayer by zhenglin · 7 years ago
  26. 5497bf6 COMPMID-718: Cleaned up NEWinogradLayerKernel header. by Pablo Tello · 7 years ago
  27. 8108d2e COMPMID-718: Added winograd benchmarking tests. by Pablo Tello · 7 years ago
  28. 3d4968a COMPMID-687: Winograd refactoring by Pablo Tello · 7 years ago
  29. b40879e COMPMID-556: Preserve case-sensitivity of positional arguments by Georgios Pinitas · 7 years ago
  30. fcd52fb COMPMID-661: Vectorize im2col and add lws heuristics for convolution kernels #46 by Anthony Barbier · 7 years ago
  31. 666635c APPBROWSER-324 FP16 Weights optimization in DirectConvolution1x1 by zhenglin · 7 years ago
  32. 83f8265 COMPMID-724: Moved exception throwing to Error.cpp by Anthony Barbier · 7 years ago
  33. 5b73ce1 APPBROWSER-313: medium value and relative standard deviation by Joel Liang · 7 years ago
  34. c5114d3 APPBROWSER-331: Code refactoring for absdiff shader and fix the example running issue by Joel Liang · 7 years ago
  35. f6a43c5 COMPMID-617 CL window validation fixes by Giorgio Arena · 7 years ago
  36. 5a7e776 COMPMID-556: Rename CPP folder to reference by Georgios Pinitas · 7 years ago
  37. 2ecbada IVGCVSW-656 : added support (and unit tests) for asymmetric padding in by Jaroslaw Rzepecki · 7 years ago
  38. b81fa60 COMPMID-715 Shrink window to size 0 if static and not resizable by Giorgio Arena · 7 years ago
  39. 04a8f8c COMPMID-692 Consistent names for the interfaces by Giorgio Arena · 7 years ago
  40. 58c5794 COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point number by Gian Marco · 7 years ago
  41. 754e952 COMPMID-617: Add validate support for NEON PixelWiseMultiplication by Ioan-Cristian Szabo · 7 years ago
  42. 5542ba8 APPBROWSER-330: Workaround for the free unallocated value issue on Android by Joel Liang · 7 years ago
  43. d9a9c50 APPBROWSER-329: Fix the adjusting group size issues by zhenglin · 7 years ago
  44. 8951933 COMPMID-687: Winograd layer. by Pablo Tello · 7 years ago
  45. 2995f5b COMPMID-617 Add validation window to CLActivationLayer by Giorgio Arena · 7 years ago
  46. 0162436 COMPMID-684: 2D In-Map normalization support for CL by Georgios Pinitas · 7 years ago
  47. 45bcc3a COMPMID-661: QASYMM8 support for fully connected layer. by Georgios Pinitas · 7 years ago
  48. 303be90 COMPMID-617: Add validate support for NEON BatchNormalizationLayer. by Ioan-Cristian Szabo · 7 years ago
  49. 236bfe7 COMPIMID-553: MobileNet use case. by Georgios Pinitas · 7 years ago
  50. 9c450cc COMPMID-695: Update Phase and Validation Wrapping by John Richardson · 7 years ago
  51. fa0add1 Fix border handler for CLDepthwiseConvolution3x3 by Diego Lopez Recas · 7 years ago
  52. 4db041e COMPMID-701 Fixed std::bad_alloc in NEON DepthwiseConvolutionLayer by Michalis Spyrou · 7 years ago
  53. 5420b28 COMPMID-710 - Fix CLTranspose and NETranspose when the input shape is a vector by Gian Marco · 7 years ago
  54. a5e6d67 IVGCVSW-796 IVGCVSW-819 add NEON kernel U8 Reshape by Les Bell · 7 years ago
  55. 6fdfaa8 COMPMID-713: Address failures in OCLGrind for CLDirectConvolution by Georgios Pinitas · 7 years ago
  56. 47b5603 COMPMID-712: OCLGrind CLSoftmaxLayer quantized failures by Georgios Pinitas · 7 years ago
  57. 7062382 COMPMID-617 Add validation window to BatchNormalization, PixelwiseMultiplication, ArithmeticOps by Giorgio Arena · 7 years ago
  58. c000fb8 COMPMID-714: Resolve failures in OCLGrind for CLPhase by Georgios Pinitas · 7 years ago
  59. a2ea753 COMPMID-661 Add Bifrost lws heuristics for several depthwise_convolution kernels #49 by Anthony Barbier · 7 years ago
  60. d912fd8 COMPMID-617: Add validation to NEON functions. by Georgios Pinitas · 7 years ago
  61. b6f182d3 COMPMID-556: Fix CLDepthwiseConvolution3x3 Kernel. by Georgios Pinitas · 7 years ago
  62. 2fdc409 COMPMID-592: Ported GEMMInterleave4x4 tests. by Pablo Tello · 7 years ago
  63. 564ed39 COMPMID-632: Integrated Assembly kernel GEMM U8 for Arm Cortex-A53. by Michalis Spyrou · 7 years ago
  64. c23b633 COMPMID-617 Add validation window to CLNormalizationLayer by Giorgio Arena · 7 years ago
  65. 9f26b3e COMPMID-617 Add validation window to CLPoolingLayer by Giorgio Arena · 7 years ago
  66. c8da111 COMPMID-661 Add optimal lws heuristics for the Bifrost direct_convolution kernels #45 by Anthony Barbier · 7 years ago
  67. 05288a2 COMPMID-697 - Rework GEMMLowp interface on OpenCL by Gian Marco · 7 years ago
  68. c827990 COMPMID-556 - Add QASYMM8 support for missing OpenCL kernels by Gian Marco · 7 years ago
  69. e8895f8 COMPMID-694: merge opencl_timer flag with the opencl flag by Anthony Barbier · 7 years ago
  70. 857e32c COMPMID-699 - Add NEON functions for im2col and col2im by Gian Marco · 7 years ago
  71. 11f0999 COMPMID-556: Fix lws_hint CLSoftmaxLayer by Georgios Pinitas · 7 years ago
  72. 27066c2 COMPMID-632: Integrated Assembly kernel GEMM S8 for Arm Cortex-A53. by Pablo Tello · 7 years ago
  73. 53d8c5c COMPMID-464 Implement Depthwise separable convolution on NEON by Michalis Spyrou · 7 years ago
  74. 7bfe4c5 COMPMID-554 Add Nodes by Michalis Spyrou · 7 years ago
  75. f3dfa27 COMPMID-632 Assembly: Integrate gemmlowp assembly version by Michalis Spyrou · 7 years ago
  76. f202e50 COMPMID-556 Improved indentation and error handling in format_doxygen.py by Anthony Barbier · 7 years ago
  77. dbfb31c COMPMID-556 Print tests list using printers rather than cout by Anthony Barbier · 7 years ago
  78. c809712 COMPMID-556 Add saturation to 8-bit activation. This prevents undefined overflow by Rob Hughes · 7 years ago
  79. b7b3153 COMPMID-464 Implement Depthwise separable convolution on NEON by Michalis Spyrou · 7 years ago
  80. 02bf80d COMPMID-661: Fix scale border issue (#38) by Daniil Efremov · 7 years ago
  81. 6194145 COMPMID-694: Fix condition which decides whether or not to profile a run by Anthony Barbier · 7 years ago
  82. d7779da COMPMID-556 - Passed _lws_hint in the run() method where was missing by Gian Marco · 7 years ago
  83. cc441cb COMPMID-696: Integrated assembly SGEMM for Arm Cortex-A55 and Arm Cortex-A55r1. by Pablo Tello · 7 years ago
  84. ee8be2d COMPMID-556: Set CLSoftmaxLayer temp buffers to resizable. by Georgios Pinitas · 7 years ago
  85. 4d55e0a COMPMID-677: Integrate HGEMM assembly kernel (generic CPUs) by Pablo Tello · 7 years ago
  86. b28f29d COMPMID-652 - Graph examples shouldn't need to link against OpenCL by Isabella Gottardi · 7 years ago
  87. a3b1b46 COMPMID-667: Add validation static method to NEON GEMMlowp by Georgios Pinitas · 7 years ago
  88. fc35b51 COMPMID-580 - Implement reference and CL/NEON validation for Remap by Sanghoon Lee · 7 years ago
  89. 37908d9 COMPMID-560 - Validation mismatches Gaussian Pyramid Half Scale by Gian Marco · 7 years ago
  90. 93dcd83 COMPMID-645: MobileNet network and benchmark by Georgios Pinitas · 7 years ago
  91. 6b77e91 COMPMID-665 - NEON: Add QASYMM8 in place Activation layer by Gian Marco · 7 years ago
  92. b3c81cb COMPMID-632: Updated Ananke_r1's SDOT product kernel. by Pablo Tello · 7 years ago
  93. 30902ed COMPMID-617: Add validation methods to ML CL functions. by Georgios Pinitas · 7 years ago
  94. 77f0f87 COMPMID-621: Disable colours when printing to file by Anthony Barbier · 7 years ago
  95. 3e80c7f COMPMID-661: Optimize FC layer with 2 new Bifrost kernels and LWS tuning (#33) by Anton Lokhmotov · 7 years ago
  96. d7295b7 COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3x3 kernel (#28) by Dmitry Savenko · 7 years ago
  97. 900b78f COMPMID-556 - Fixed static window in NEGEMMMatrixAccumulateBiasesKernel by Gian Marco · 7 years ago
  98. 540d008 COMPMID-556: Fixes bias in CLDirectConvolutionLayer to be int32. by Georgios Pinitas · 7 years ago
  99. 43ce898 COMPMID-670 - Extend Sobel tests by Isabella Gottardi · 7 years ago
  100. c1294fa COMPMID-494: Fixing values to const by Sanghoon Lee · 7 years ago