Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / c63c3703db0bf351fc8d17fc1c0d3721abb3cc80
  1. 3463a8b COMPMID-1534: Fix NEActivationLayer for FP16 by Georgios Pinitas · 6 years ago
  2. 2113b9d COMPMID-1246: Don't call CLFinish at the end of benchmark / validation if opencl is not available by Anthony Barbier · 6 years ago
  3. 890ad1b COMPMID-1246: Fix bug in handling backends that can't be loaded in the Graph API by Anthony Barbier · 6 years ago
  4. aaba4c6 COMPMID-1188: Add support for activation in NEBatchNormalization. by Georgios Pinitas · 6 years ago
  5. 630d941 COMPMID-1246: Cleaned up 3rdparty folder and updated data folder (3RDPARTY_UPDATE)(DATA_UPDATE) by Anthony Barbier · 6 years ago
  6. 8a04211 COMPMID-1188: Revert change to DummyAccessor, fixed NPY and Image loaders by Anthony Barbier · 6 years ago
  7. 80040bc COMPMID-1246: Check OpenCL is available before re-creating the CL Context and Queue by Anthony Barbier · 6 years ago
  8. 84cb75d COMPMID-1524 - Release Branch: CL GEMMDilatedConvolutionLayer FP16 mismatches by Gian Marco Iodice · 6 years ago
  9. a7cbc74 COMPMID-1188 - Fixed DummyAccessor by Gian Marco Iodice · 6 years ago
  10. 368e635 COMPMID-1047 Extract Flatten function from Im2Col for NEON by Giorgio Arena · 6 years ago
  11. 125bb5b COMPMID-1144:(3RDPARTY_UPDATE)(DATA_UPDATE) Add DragonBench Headers by Georgios Pinitas · 6 years ago
  12. be2772a COMPMID-1508: Add Inception ResNet V2 model by Georgios Pinitas · 6 years ago
  13. 6c95c2d COMPMID-1188: Static tuning of CLScale by Georgios Pinitas · 6 years ago
  14. 1049020 COMPMID-1188: Set all arguments to const in NEDepthwiseConvolutionLayer::validate() by Georgios Pinitas · 6 years ago
  15. bcafc4d COMPMID-1486 - CLGEMMDilatedConvolutionLayer FP16 / FP32 failing in nightlies by Gian Marco Iodice · 6 years ago
  16. 2a2db59 COMPMID-1505: Add native grouping support at graph level by Georgios Pinitas · 6 years ago
  17. c1961b5 COMPMID-1509: (Nightly) CLDeconvolution fails for QASYMM8 by Michele Di Giorgio · 6 years ago
  18. 25f45a4 COMPMID-1060 LSTM FP32 NEON by Michalis Spyrou · 6 years ago
  19. 26b2216 COMPMID-1480 Add support for NHWC QASYMM8/FP32(non-optimized) to NEON DepthwiseConvolution by Giorgio Arena · 6 years ago
  20. bc92a34 COMPMID-1188: Fix subtensor check by Georgios Pinitas · 6 years ago
  21. 1d38259 COMPMID-1366 Implement NECopy by Michalis Spyrou · 6 years ago
  22. 3941295 COMPMID-1506 NPY Loader doesn't work for NHWC pipelines by Michalis Spyrou · 6 years ago
  23. d30714a COMPMID-1188 - Fix CLWinogradConvolutionLayer for NHWC by Gian Marco Iodice · 6 years ago
  24. 1b65807 COMPMID-1188 - Enabled NHWC in graph_squeezenet_v1 for NEON by Gian Marco Iodice · 6 years ago
  25. 916d1bc COMPMID-1498 - Enable grouping in CLGEMMConvolutionLayer by Gian Marco Iodice · 6 years ago
  26. 61de78a COMPMID-1509: (Nightly) CLDeconvolution fails for QASYMM8 by Michele Di Giorgio · 6 years ago
  27. 7b2f026 COMPMID-145 : Create ResNet v2 graph example by Georgios Pinitas · 6 years ago
  28. 9fef38a COMPMID-1376: Add support for QASYMM8 in CLDeconvolutionLayer by Michele Di Giorgio · 6 years ago
  29. 72ccc44 COMPMID-1504: (Nightly) Segfaults on CL and android by Georgios Pinitas · 6 years ago
  30. 766b70c COMPMID-1456: Create mobilenet v2 1.0 224 graph example by Georgios Pinitas · 6 years ago
  31. 3a6163e COMPMID-1499: Fixed issues to build for FP16 on Android by Anthony Barbier · 6 years ago
  32. e3f1bd1 COMPMID-1246 Remove unused window iterator from NERNNLayer. by Michalis Spyrou · 6 years ago
  33. 29258e8 COMPMID-1188: Assign correct ticket to TODO in NEDerivativeKernel by Michele Di Giorgio · 6 years ago
  34. 2a51818 COMPMID-1500: (Nightly) CLIm2ColGrouped std::bad_alloc and crashes by Georgios Pinitas · 6 years ago
  35. c3b2e07 COMPMID-1188 Remove some FixedPoint leftovers from tests by Giorgio Arena · 6 years ago
  36. 5a65cfd COMPMID-1478: Fixed Doxygen comments + minor fixes by Anthony Barbier · 6 years ago
  37. 8914e32 COMPMID-1473: Added missing TypePrinter for CPUModel, added accessor for number of CPUs by Anthony Barbier · 6 years ago
  38. db9d46d COMPMID-1485 - Add support for NHWC when running NEGEMMConvolutionLayer with FP16/QASYMM8 by Gian Marco Iodice · 6 years ago
  39. 980002b COMPMID-1343: Add grouping support to CLCol2ImKernel by Michele Di Giorgio · 6 years ago
  40. 0f17039 COMPMID-1342 Add grouping support to CLIm2ColKernel by Giorgio Arena · 6 years ago
  41. b6eb353 COMPMID-1478: Stop relying on static default OpenCL objects in cl2.hpp by Anthony Barbier · 6 years ago
  42. 1d1f32c COMPMID-1188 - Passed WIDTH_OFFSET at compile time in CLWidthDepthConcatenateLayerKernel by Gian Marco Iodice · 6 years ago
  43. 9f5a643 COMPMID-1496 (Nightly) Mismatches in CLMeanStd function for FP16 by Michalis Spyrou · 6 years ago
  44. 25747e2 COMPMID-1410 (Nightly) Mismatches in CLMeanStd function for float by Michalis Spyrou · 6 years ago
  45. 2318fcf COMPMID-1486 - CLGEMMDilatedConvolutionLayer FP16 / FP32 failing in nightlies by Gian Marco Iodice · 6 years ago
  46. d8b03dd MLCE-13: Sanitizing matrix argument in the Warp. by Pablo Tello · 6 years ago
  47. 7da6dcf COMPMID-1416 Fix Arithmetic Addition Reference by Giorgio Arena · 6 years ago
  48. dff601d COMPMID-1488 - Add support for NHWC when running CLGEMMConvolutionLayer with QASYMM8 by Gian Marco Iodice · 6 years ago
  49. 4dc96a9 COMPMID-1487 - CLIm2Col QASYMM8 failing in nightlies by Gian Marco Iodice · 6 years ago
  50. 8b2fdc9 COMPMID-1478: Updated OpenCL headers to the latest Khronos ones by Anthony Barbier · 6 years ago
  51. 4ead11a COMPMID-1479: Fixed non fortran_order NPY loading. by Anthony Barbier · 6 years ago
  52. 6b4e604 COMPMID-1303: CLDepthConvert : Add support for FP32 -> FP16 and FP16 -> FP32 + validate() function by Michele Di Giorgio · 6 years ago
  53. 088c2b0 COMPMID-1188 Fix WeightsReshape doc by Giorgio Arena · 6 years ago
  54. f2bd261 COMPMID-1188 - Removed the multiplication by 4 in NEGEMMInterleavedWrapper by Gian Marco Iodice · 6 years ago
  55. d51ea0a COMPMID-1243 Update doxygen to use Android ndk r17b by Anthony Barbier · 6 years ago
  56. 215b4ea COMPMID-1277 - Optimizing CLIm2ColKernel for NHWC. by Gian Marco Iodice · 6 years ago
  57. ad486e2 COMPMID-1188 - Fixed files extensions in GraphUtils.h by Gian Marco Iodice · 6 years ago
  58. c6aa49b COMPMID-1344 Add grouping support to CLWeightsReshapeKernel by Giorgio Arena · 6 years ago
  59. be41006 COMPMID-1481: CLCannyEdge still failing in some precommits by Michele Di Giorgio · 6 years ago
  60. d39e2b1 COMPMID-1188 - Fixed performance degradation with GEMM3D by Gian Marco Iodice · 6 years ago
  61. 20394d5 COMPMID-1248 Enabled memory manager in NEWinogradConvolutionLayer by Anthony Barbier · 6 years ago
  62. 3d677cc COMPMID-1406: Refactor gemm_interleaved to use our own types and scheduler by Anthony Barbier · 6 years ago
  63. 597a856 COMPMID-872 - Rework NEGEMMConvolutionLayer to use NEGEMM by Gian Marco Iodice · 6 years ago
  64. 883f489 COMPMID-1475: (OCLGrind) FP exception in NEGEMMConvolution by Georgios Pinitas · 6 years ago
  65. 195b0ba MLCE-36: FC tranpose weights by Georgios Pinitas · 6 years ago
  66. 57c4824 MLCE-37: Adds PermuteNode support in graph by Georgios Pinitas · 6 years ago
  67. ebbb7f2 COMPMID-1188 - Fixed CLGEMMConvolutionLayer/NEGEMMConvolutionLayer for NHWC by Gian Marco Iodice · 6 years ago
  68. 4cb3909 COMPMID-1439: Fix invalidation of iterator while iterating by Georgios Pinitas · 6 years ago
  69. 9036749 COMPMID-1445: Fixed NEON GEMM assembly dispatch for QASYMM8 by Anthony Barbier · 6 years ago
  70. 415a2bf COMPMID-1432: Enable by default NHWC in graph examples by Georgios Pinitas · 6 years ago
  71. 68a3f56 COMPMID-1276 - Allow GEMM to work with 3D input tensor by Gian Marco Iodice · 6 years ago
  72. 4e0d381 COMPMID-1437: (Nightly) OCLGrind failures in CLDepthwiseConvolution QA8 nhwc by Georgios Pinitas · 6 years ago
  73. ef91516 COMPMID-1359: (Nightly) CLCannyEdge failures by Michele Di Giorgio · 6 years ago
  74. c55cef1 COMPMID-1188: Expose FullyConnectedLayer info metadata at graph level by Georgios Pinitas · 6 years ago
  75. ff4bbce COMPMID-1188 - Fixed get_convolution_method in CLConvolutionLayer by Gian Marco Iodice · 6 years ago
  76. fb0b280 COMPMID-1438: MobilenetV1 regression. by Georgios Pinitas · 6 years ago
  77. 8bc745d COMPMID-1124: Validate CLLSTM by Georgios Pinitas · 6 years ago
  78. 201cea1 COMPMID-1290 - Update CLTuner documentation by Gian Marco Iodice · 6 years ago
  79. 366628a COMPMID-1188 Added missing type printer for TensorInfo by Anthony Barbier · 6 years ago
  80. 40ed6d8 COMPMID-1440: Access original B in gemm assembly when not pretransposed. by Georgios Pinitas · 6 years ago
  81. 2f1366a COMPMID-1188: Add quantization info support in graph FC layer. by Georgios Pinitas · 6 years ago
  82. ea0147d COMPMID-1188: Fix squeesenetv1.1 input shape by Georgios Pinitas · 6 years ago
  83. eb84d6b COMPMID-1434: Fix NEWinograd for NHWC and sub-tensors by Georgios Pinitas · 6 years ago
  84. c50da38 COMPMID-1431 Use either arm_dot or arm_dot_acc for CLGEMMLowp based on what is supported by Giorgio Arena · 6 years ago
  85. a4658ae COMPMID-1429: NEGEMMNativeWrapperKernel fails when ran for Winograd by Georgios Pinitas · 6 years ago
  86. ead90b5 COMPMID-1188: Remove graph system tests by Georgios Pinitas · 6 years ago
  87. e222055 COMPMID-1367: Enable NHWC in graph examples by Georgios Pinitas · 6 years ago
  88. eff8d95 COMPMID-1316 Using 8 bit dot product instruction in CLDepthWiseConvolution with QASYMM8 by Giorgio Arena · 6 years ago
  89. 74b671b COMPMID-1188: Remove FP16 capabilities check form NEReshapeLayer. by Georgios Pinitas · 6 years ago
  90. ef776a8 COMPMID-1386: Add FC convert weights on NEON by Georgios Pinitas · 6 years ago
  91. a855af1 COMPMID-1401 Implement NEFullyConnectedLayer for QASYMM8 by Giorgio Arena · 6 years ago
  92. 5a3ee4f COMPMID-1347: Simplified CPUInfo enum by Anthony Barbier · 6 years ago
  93. eaefd00 COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templated by Anthony Barbier · 6 years ago
  94. c8e84b5 COMPMID-1405: Create our own gemm_native kernel / function. by Anthony Barbier · 6 years ago
  95. 3efb375 COMPMID-1347: Fixed fallback CPUInfo populate function and added latest CPUs by Anthony Barbier · 6 years ago
  96. 96fc1d6 COMPMID-1394: Fixed OCLGrind failures ColorConvert by Pablo Tello · 6 years ago
  97. 40606df COMPMID-1414: Print the image being validated during graph validation by Anthony Barbier · 6 years ago
  98. 7d66a8e COMPMID-1386: Add support for converting weights for CL. by Georgios Pinitas · 6 years ago
  99. ae54e02 COMPMID-1364: Add support for NHWC in NEDepthConcatenateLayer by Georgios Pinitas · 6 years ago
  100. b0b3717 COMPMID-1417: (Nightly) OCLGrind failures in winograd_output_transform_nhwc by Georgios Pinitas · 6 years ago