Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 032cce9bd3d691c3f7e481f1c0015a5f2aa4b4f6
  1. 40df1e9 COMPMID-887 Valgrind invalid read in print_measurements by Michalis Spyrou · 6 years ago
  2. f75ab3f COMPMID-888 Valgrind invalid read in NEGEMVAArch64Kernel by Michalis Spyrou · 6 years ago
  3. 5ae9b69 COMPMID-885 Valgrind NEConvolutionSquare::configure relies on uninitialised values by Michalis Spyrou · 6 years ago
  4. 54f18c4 COMPMID-901 - Optimizing CLCol2ImKernel by Gian Marco · 6 years ago
  5. e9146ed COMPMID-879: Investigate CL mismatches in Convolution S16 by Georgios Pinitas · 6 years ago
  6. 6e464c3 COMPMID-828 - Add support for non square pool size - Part1 by Isabella Gottardi · 6 years ago
  7. 3364c4c COMPMID-893: Fix segfault in graph_squeezenet_v1_1 by Georgios Pinitas · 6 years ago
  8. c799ed8 COMPMID-895 - Optimizing CLDepthwiseConvolution3x3Kernel by Gian Marco · 6 years ago
  9. 604afc0 COMPMID-894: Segfault: neon_cnn on S5 neo by Georgios Pinitas · 6 years ago
  10. 562deff COMPMID-765 - Added LWS hint in CLIm2Col by Gian Marco · 6 years ago
  11. 101de50 COMPMID-896: Replace legacy 4x4 u8 GEMM kernel with safe version. by David Mansell · 6 years ago
  12. 679463a COMPMID-784: Added support for PADDING = SAME in Winograd layer. by Pablo Tello · 6 years ago
  13. 85e6f51 COMPMID-891 - Use OpenCL timer in CLTuner by Gian Marco · 6 years ago
  14. 76faef8 COMPMID-855 - Optimizing im2col on OpenCL (DCHW) by Gian Marco · 6 years ago
  15. b28f329 COMPMID-754: Add validation method to CLPermute kernel by Michele Di Giorgio · 6 years ago
  16. 2d40555 COMPMID-765 - Used GEMM instead of Direct into the GoogleNet graph example by Gian Marco · 6 years ago
  17. bc4484a COMPMID-889 - Implement Squeezenet 1.1 as a graph example by Isabella Gottardi · 6 years ago
  18. 53d1227 COMPMID-874: Improve default number of threads choice in the Scheduler by Georgios Pinitas · 6 years ago
  19. b7e3028 COMPMID-890: Valgrind: NEON Convolution Layer validation fails by Isabella Gottardi · 6 years ago
  20. f525eab COMPMID-871: Remove vst4q/vld4q from NEActivationLayer. by Georgios Pinitas · 6 years ago
  21. 6259e5f COMPMID-787: Add CL support for broadcast multiply by Michele Di Giorgio · 6 years ago
  22. 19d0547 COMPMID-765: Fix direct convolution output stage. by Georgios Pinitas · 6 years ago
  23. f6169d8 COMPMID-765: Fixed clangtidy warnings. by Pablo Tello · 6 years ago
  24. 456e479 COMPMID-765: Fixed CPU detection code to read larger buffer (was failing on Arm Cortex-A55 FPGA with 8 CPUs with lots of flags). by Pablo Tello · 6 years ago
  25. 52140b4 COMPMID-784: Winograd tramsforms refactoring by Pablo Tello · 6 years ago
  26. 054a714 COMPMID-765 Small fixes to MobileNet dwc dataset by Giorgio Arena · 6 years ago
  27. 33ff9ef APPBROWSER-400: Implement the tensorshift kernel for fixing DC's alignment issue on OpenGL ES by Xinghang Zhou · 6 years ago
  28. 1c0d0ff COMPMID-832: Decrease validation coverage of QS8/QS16 by Anthony Barbier · 6 years ago
  29. cdd1e85 APPBROWSER-394: GLES fails to compile Dropout kernel on S5 by steli01 · 6 years ago
  30. 18d352a COMPMID-765: Added tolerance of 1 for CL Convolution S16 while the issue is investigated by Anthony Barbier · 6 years ago
  31. 0021d75 IVGCVSW-863 Broadcast support in CL/NEON Arithmetic Add by Diego Lopez Recas · 7 years ago
  32. 5b6904b COMPMID-866: Integrate SGEMV Neon Assembly from RSH by Michele Di Giorgio · 6 years ago
  33. f1df346 COMPMID-765: Allow RSH's code to not have default cases in their switches by Anthony Barbier · 6 years ago
  34. 2219dea APPBROWSER-390,397,398: bugfix and fully connected validation issue on specific dataset by zhenglin · 6 years ago
  35. 11c3b33 COMPMID-861: updated RSH Gemm's transforms. by Pablo Tello · 6 years ago
  36. fc9bda3 COMPMID-815: Fixed Winograd 5x5 padding bug. by Pablo Tello · 6 years ago
  37. d466c2d COMPMID-833 Direct convolution, Normalization and by Michalis Spyrou · 6 years ago
  38. c0079e9 COMPMID-564: CustomConvolution Test Name updated by Sanghoon Lee · 6 years ago
  39. c78d4bc COMPMID-765 - Added third dimension for CLTuner by Gian Marco · 6 years ago
  40. 0434d75 COMPMID-588: Port Equalize Histogram to new validation by John Richardson · 7 years ago
  41. fb8dda2 COMPMID-765 Fixed missing cast that was breaking the bare metal build by Anthony Barbier · 6 years ago
  42. fc1ffe6 COMPMID-837: Fixed remap tests failures in Valgrind. by Pablo Tello · 6 years ago
  43. 4df0575 APPBROWSER-395: Random error in FullyConnectedLayer by steli01 · 6 years ago
  44. 35ceeb2 IVGCVSW-798 Add Softmax NEON support for QASYMM8 by Diego Lopez Recas · 7 years ago
  45. 97cf249 COMPMID-564: CustomConvolution issue fixed by Sanghoon Lee · 6 years ago
  46. d6ca478 COMPMID-784: Added support for biases in WinogradLayer. by Pablo Tello · 6 years ago
  47. d05dce4 COMPMID-791: Generic Depthwise Convolution Layer NEON QASYMM8 by Georgios Pinitas · 6 years ago
  48. 5d9d019 COMPMID-863: Only output (end-start) for OpenCL timers by Anthony Barbier · 6 years ago
  49. e6630e4 COMPMID-790 - NEON: Add QASYMM8 support to Convolution by Isabella Gottardi · 6 years ago
  50. b99d57d COMPMID-765: Clangtidy warnings by Pablo Tello · 6 years ago
  51. c9afce5 COMPMID-863: Remove some of the post-processing from the JSON backend by Anthony Barbier · 6 years ago
  52. f6402dd COMPMID-834 Fix arm_compute_nightly_validation getting killed by Michalis Spyrou · 6 years ago
  53. bd0e612 COMPMID-848 NEPoolingLayerKernel incorrectly reports by Michalis Spyrou · 6 years ago
  54. 36a0a46 COMPMID-748 - Integrating optimized SGEMM for bifrost by Gian Marco · 6 years ago
  55. 46edf63 COMPMID-765: Fixed output accessor in LeNet example, and disabled colors when not running in a terminal by Anthony Barbier · 6 years ago
  56. c8d2316 COMPMID-564: Implement reference and CL/NEON validation for CustomConvolution (output S16) by Sanghoon Lee · 6 years ago
  57. 503cec8 COMPMID-765: Added missing <errno.h> include by Anthony Barbier · 6 years ago
  58. 33d2207 COMPMID-860: Neon HGEMM integrated assembly kernel from RSH for Arm Cortex-A55r1. by Pablo Tello · 6 years ago
  59. e8a4983 COMPMID-798 Add instrumentation to NEON kernels by Anthony Barbier · 6 years ago
  60. fa7dc84 COMPMID-765: Enable fp16 extension for arm64-v8.2-a by Pablo Tello · 6 years ago
  61. 7b4d547 COMPMID-816 - Optimizing CLGEMMLowpMatrixMultiplyCore - Part1 by Gian Marco · 6 years ago
  62. dde3ad9 COMPMID-842: Add NEON QASYMM8 RELU Activation by Michele Di Giorgio · 6 years ago
  63. 967f86d COMPMID-858: Assert in ICLKernel on higher window dimensions moved to enqueue by Anthony Barbier · 6 years ago
  64. a1f7e33 COMPMID-841: Add CL QASYMM8 RELU Activation by Michele Di Giorgio · 6 years ago
  65. 9efceaf COMPMID-765 - Add issue_template for github by Michalis Spyrou · 6 years ago
  66. 989f1b5 COMPMID-857 ARMCV Failure to Build on RHEL platform by Michalis Spyrou · 6 years ago
  67. 7f530b3 COMPMID-847: Add MobileNet_v1_0.75_160. by Georgios Pinitas · 6 years ago
  68. 6c6e77a COMPMID-784: Doxygen fixes by Pablo Tello · 6 years ago
  69. 64c95a0 COMPMID-765: Updated changelog before 18.01 by Anthony Barbier · 6 years ago
  70. 657fb99 COMPMID-765 UPDATE_DATE Switching to use mpd-repository for data by Anthony Barbier · 6 years ago
  71. e855c23 APPBROWSER-377: GCConvoutionLayer support for FP16 by Stephen Li · 7 years ago
  72. 81ce008 COMPMID-847: DATA_UPDATE Add MobilenetV1 224,160 data. by Georgios Pinitas · 6 years ago
  73. 9ceebbe COMPMID-815: Updated NEWinogradLayer with the lastest code from Research. by Pablo Tello · 6 years ago
  74. 00afd11 COMPMID-719: NEPermuteKernel refactoring by Pablo Tello · 7 years ago
  75. 5237e01 COMPMID-838 Implement CLPermute by Michalis Spyrou · 6 years ago
  76. 652bde5 COMPMID-674 - Create Google InceptionV3 example by Georgios Pinitas · 6 years ago
  77. f72f936 COMPMID-791: Adds support of QASYMM8 in NEDepthwiseConvolution3x3 by Georgios Pinitas · 6 years ago
  78. a026e98 COMPMID-849: Changed default toolchain to Clang on Android by Anthony Barbier · 6 years ago
  79. 61ef5bf IVGCVSW-847 Fix {NEON/CL}PoolingLayerKernel config by Diego Lopez Recas · 7 years ago
  80. 9c42de9 COMPMID-753 Add benchmarks for ActivationLayers used in MobileNet by Giorgio Arena · 6 years ago
  81. a0d1183 COMPMID-751 QASYMM8 ActivationLayer optimisation: don't requantize if not necessary by Giorgio Arena · 6 years ago
  82. 51a6730 COMPMID-832: Clean up tests. by Georgios Pinitas · 6 years ago
  83. 944d3f7 COMPMID-751 Processing 8 elements makes computation up to 80us faster on MobileNet QASYMM8 dwc layers by Giorgio Arena · 6 years ago
  84. 200b6e3 COMPMID-839 Added method to clear the Kernel Library's program cache by Anthony Barbier · 6 years ago
  85. 826c769 COMPMID-835: Valgrind make UNIT/Utils/RoundFloatToNearestUp fail on aarch64 by Pablo Tello · 6 years ago
  86. a66eaa2 COMPMID-752 Creating an example for QASYMM8 MobileNet by Giorgio Arena · 7 years ago
  87. 621965e COMPMID-769 Add asymmetric padding support in NEON kernels. by Michalis Spyrou · 6 years ago
  88. 20d7848 COMPMID-816 - Enabled CLConvolutionLayer to use CLGEMM function instead by Gian Marco · 6 years ago
  89. 84f3ae8 COMPMID-830 Fix hang in arm_compute_benchmark NEON by Michalis Spyrou · 6 years ago
  90. 86fb1e7 COMPMID-752: DATA_UPDATE Add MobilenetV1 QASYMM8 data. by Georgios Pinitas · 6 years ago
  91. 7c10f48 COMPMID-765 - Reduced to 4 the batch size for AlexNet by Gian Marco · 6 years ago
  92. 5518671 COMPMID-785: Add QASYMM8 support for pooling layer by Georgios Pinitas · 6 years ago
  93. 1ff480b COMPMID-765: Fixed unused variable warning by Anthony Barbier · 6 years ago
  94. 72856ab COMPMID-786: Remove all the fill() calls in benchmarks by Anthony Barbier · 6 years ago
  95. 2b5f0f2 COMPMID-782 Port examples to the new format by Michalis Spyrou · 6 years ago
  96. 571b18a COMPMID-565 - Implement reference and CL/NEON validation for CustomConvolutionSeparable by Sanghoon Lee · 7 years ago
  97. 4b9c58a COMPMID-800: Display build_information() at the beginning of the runs by Anthony Barbier · 6 years ago
  98. 093adbc COMPMID-753 Add benchmarks for GEMM/GEMMLowp used in AlexNet by Giorgio Arena · 6 years ago
  99. bcbc970 IVGCVSW-863 calculate_max_window..() family takes ValidRegion by Diego Lopez Recas · 7 years ago
  100. 1bfc784 APPBROWSER-376: Work around for scale validation error. by Frank Lei · 7 years ago