Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 49c6cedaea3dc4b7d1627a1a03249d13e8968d8d
  1. 49c6ced COMPMID-3599: Enable SVE on armv8.6 and selectively enable MMLA_FP by Georgios Pinitas · 3 years, 9 months ago
  2. 245ba05 COMPMID-3783: Segfaulting in Reduction layer with NEON on Mate20 with HFNet by Sheri Zhang · 3 years, 9 months ago
  3. 9e698d5 COMPMID-3757: (u)int8: Don't select the 16-bit route on A53 for cases with very few rows by David Mansell · 3 years, 10 months ago
  4. 047c6fc COMPMID-3791: Add support for all activation types in NodeFusionMutator by Gian Marco Iodice · 3 years, 9 months ago
  5. 34654b2 COMPMID-3787: Update heuristic for m = 1 on CLGEMMReshapedOnlyRHSKernel by Gian Marco Iodice · 3 years, 9 months ago
  6. 6f93134 COMPMID-3671: Extend cl image support to f16 in CLGEMMMatrixMultiplyReshapedKernel by Gian Marco Iodice · 3 years, 10 months ago
  7. 82c1a1f COMPMID-3752: NEPermuteKernel does not support permutations2 by Michele Di Giorgio · 3 years, 10 months ago
  8. f110954 COMPMID-3184: Added no padding test for NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel by morgolock · 3 years, 10 months ago
  9. 16cf3c2 COMPMID-3764: Failures on fp16 for L2NormalizationLayer when zero inputs by Georgios Pinitas · 3 years, 10 months ago
  10. cffb2a3 COMPMID-3159: Remove padding from NEPoolingLayerKernel by Michalis Spyrou · 3 years, 10 months ago
  11. 1813422 COMPMID-3583: Add S32 support to NEElementwiseDivision by Georgios Pinitas · 3 years, 10 months ago
  12. 5489394 COMPMID-3774: Investigate NEReduceMean QASYMM8_SIGNED nightly failure by Michele Di Giorgio · 3 years, 10 months ago
  13. fa269bb MLCE-229: Fixed requantization per channel in asm kernel by morgolock · 3 years, 10 months ago
  14. bb88f89 COMPMID-3581 Add S32 support to NEPixelWiseMultiplication by SiCong Li · 3 years, 10 months ago
  15. d64444b Add Reduction operation layer node to graph API by thecha01 · 3 years, 10 months ago
  16. 3603aff Add L2Normalize layer node to Graph API by thecha01 · 3 years, 10 months ago
  17. 57f30a9 COMPMID-3767: Align documentation with trademark rules by Michele Di Giorgio · 3 years, 10 months ago
  18. e4340a4 COMPMID-3568: Add provenance of model for EDSR graph example by Michele Di Giorgio · 3 years, 10 months ago
  19. 4e28d60 COMPMID-3569: (3RDPARTY_UPDATE) Move Yolo v3 output detector graph example to 3rdparty by Michele Di Giorgio · 3 years, 10 months ago
  20. be33acd COMPMID-3645: Clarify graph examples' immutable governance by Georgios Pinitas · 3 years, 10 months ago
  21. 7d0adc6 COMPMID-3151: Remove NEDepthwiseConvolutionLayer3x3Kernel by Georgios Pinitas · 3 years, 10 months ago
  22. e8f05da Add ArgMinMax layer node to Graph API by thecha01 · 3 years, 10 months ago
  23. 7c850d5 COMPMID-3155: Remove padding from NEGEMMLowpOffsetContributionKernel by Michele Di Giorgio · 3 years, 10 months ago
  24. 8a14b2c COMPMID-3748: Compiler issue with Bfloat16 on gcc8 by Georgios Pinitas · 3 years, 10 months ago
  25. 903f8cc COMPMID-3580 Add S32 support to NEArithmeticSubtraction by SiCong Li · 3 years, 10 months ago
  26. 2d22139 COMPMID-3154: Deprecate NE/CL LocallyConnectedLayer by Georgios Pinitas · 3 years, 10 months ago
  27. cbf4d55 COMPMID-3755: Resize failing on input with trailing 1's by Georgios Pinitas · 3 years, 10 months ago
  28. 2bfadd9 Add StridedSliceLayerNode to graph API by thecha01 · 3 years, 11 months ago
  29. 0a05e6a Add DepthToSpace layer node to Graph API by thecha01 · 3 years, 10 months ago
  30. be058f4 Use shape broadcast for Mult inputs in EDSR graph by thecha01 · 3 years, 10 months ago
  31. b3182b1 COMPMID-3157: Remove padding from NEGEMMTranspose1xWKernel by Gian Marco Iodice · 3 years, 10 months ago
  32. feaea10 COMPMID-3143: Remove padding from NEGEMMInterleave4x4Kernel by Gian Marco Iodice · 3 years, 10 months ago
  33. ec4dee8 COMPMID-3750: Disable asm kernels when shifts are negative. by morgolock · 3 years, 10 months ago
  34. 12e0209 COMPMID-3772: Update GEMM selection heuristic for Mali-G76 (F32) by Gian Marco Iodice · 3 years, 10 months ago
  35. 7a7f4e0 COMPMID-3758 COMPMID-3759: Update documentation for cross compile and Android NDK toolchain by Sheri Zhang · 3 years, 10 months ago
  36. 026d045 COMPMID-3770: Add batch size in the OpenCL GEMM kernel selection by Gian Marco Iodice · 3 years, 10 months ago
  37. 1c76c1d COMPMID-3504: Add support for BOOL in NEON comparison operators by Michele Di Giorgio · 3 years, 10 months ago
  38. 5bdde85 COMPMID-3670 Extend cl image support to f16 in CLGEMMReshapeRHSMatrixKernel by SiCong Li · 3 years, 10 months ago
  39. ce7c441 COMPMID-3756 Update CommonGraphOptions documentations to include tuner-mode by SiCong Li · 3 years, 10 months ago
  40. 96209c7 COMPMID-3694 COMPMID-3695 COMPMID-3458: Softmax Axis by SiCong Li · 3 years, 10 months ago
  41. 5111264 COMPMID-3661: Added multidimension support to OMP scheduler. by morgolock · 3 years, 10 months ago
  42. 96a1400 Fix EltwiseLayerNode and QuantizationLayerNode by thecha01 · 4 years ago
  43. 90251bc COMPMID-3749: Adjust FP32 tolerance for NEScale validation by Sang-Hoon Park · 3 years, 10 months ago
  44. 747a2c6 COMPMID-3698: Fix segfault running inception_v3, inception_v4, resnet50, resnet_v2_50 when running as qasymm8 on mate20 GPU by Sheri Zhang · 3 years, 10 months ago
  45. 6d0b384 Update SONAME_VERSION in SConscript by Sang-Hoon Park · 3 years, 11 months ago
  46. 7e725cf COMPMID-3655: PixelWiseMultiplication incorrectly validated in Graph by Manuel Bottini · 3 years, 11 months ago
  47. f8e3584 Add support ElementwiseMax operator in graph API by thecha01 · 4 years ago
  48. ebd8fb4 COMPMID-3747 Remove unnecessary and problematic constness from non-static private members by SiCong Li · 3 years, 11 months ago
  49. a3e6b6d COMPMID-3696: Padded dilated Conv2D segmentation by Sheri Zhang · 3 years, 11 months ago
  50. 0bc80da MLCE-229: Support for negative shifts in asm kernels by morgolock · 3 years, 11 months ago
  51. c58f0ad COMPMID-3502: Add support of different quantization input/output for ReduceMean by Manuel Bottini · 3 years, 11 months ago
  52. 97c1a67 COMPMID-3689: Update function list in doxygen by Sang-Hoon Park · 3 years, 11 months ago
  53. adfaefb COMPMID-3690: Update release note by Sang-Hoon Park · 3 years, 11 months ago
  54. e357a25 COMPMID-3454 Patch1: Relocate data_type_from_name to core/Utils by SiCong Li · 3 years, 11 months ago
  55. a45abfd COMPMID-3687: Remove deprecated functions in 20.05 release by Sang-Hoon Park · 3 years, 11 months ago
  56. 547b2e7 COMPMID-3702: Update documentation by Gian Marco Iodice · 3 years, 11 months ago
  57. d72bd12 COMPMID-3743: Fix for benchmark_gemm_examples.sh by Gian Marco Iodice · 3 years, 11 months ago
  58. 27423f0 COMPMID-3608: Fix z index in gemmlowp_mm_reshaped_only kernel by Gian Marco Iodice · 3 years, 11 months ago
  59. 088d63a COMPMID-3337: Remove write paddings in both axes from CLGEMMMatrixMultiplyReshapedKernel by Gian Marco Iodice · 3 years, 11 months ago
  60. b10181b COMPMID-3456 Update gemm tuner documentation by SiCong Li · 3 years, 11 months ago
  61. dc12519 COMPMID-3699: Nightly failure CL DirectConvolution by Manuel Bottini · 3 years, 11 months ago
  62. 315a20e COMPMID-3339: Fix doxygen comments about VECTOR_SIZE and BOUNDARY_VECTOR_SIZE by SiCong Li · 3 years, 11 months ago
  63. 73cdaac COMPMID-3335: Remove x/y-axis padding from CLGEMMReshapeLHSMatrixKernel by Gian Marco Iodice · 3 years, 11 months ago
  64. f650ea5 COMPMID-3339: Patch2: Remove paddings from im2col*_nhwc cl kernel by SiCong Li · 3 years, 11 months ago
  65. 77d3d24 COMPMID-3607: Fix softmax summation logic for QASYMM8_SIGNED by Sang-Hoon Park · 3 years, 11 months ago
  66. 03d8a89 COMPMID-3339: Patch1: Fix incorrect select casting in im2col nhwc kernels by SiCong Li · 3 years, 11 months ago
  67. 996c777 COMPMID-3700: ArmNN OOB test failure by Sheri Zhang · 3 years, 11 months ago
  68. 4aed4aa COMPMID-3683: Fix performance regression on Mali-G76 (Fully connected) by Gian Marco Iodice · 3 years, 11 months ago
  69. 9c7fed8 COMPMID-3656: Disabled reduce_axis in LOG_SOFTMAX and SOFTMAX by morgolock · 3 years, 11 months ago
  70. b972ae6 COMPMID-3652 Fix CLFullyConnectedLayer failure on S10 by SiCong Li · 4 years ago
  71. 187558f Added missing parameter num_groups to the validate call of NEConvolutionLayer. by Alexander Jung · 3 years, 11 months ago
  72. dd4cfc0 COMPMID-3516: Update documentation for new operators in 20.08 by Sheri Zhang · 4 years ago
  73. 4d81d75 COMPMID-2450: Implement CLMaxUnpoolingLayer by Gian Marco Iodice · 4 years ago
  74. 801bbcb COMPMID-2479: Extend CLPoolingLayer max pooling to extract indices by Sheri Zhang · 4 years ago
  75. 0499dff COMPMID-3392: Collapse TensorMaps into a single TensorPack by Georgios Pinitas · 4 years ago
  76. ac4c030 COMPMID-3618 Add support for export_to_cl_image_rhs in GEMMTuner.py by SiCong Li · 4 years ago
  77. ad411e0 COMPMID-3526: LOGISTIC support for values bigger than [-40.f,40.f] by Michalis Spyrou · 4 years ago
  78. 3b64e3e COMPMID-3653 CL GEMM kernel creation error on certain combinations of N and N0 by SiCong Li · 4 years ago
  79. 7a81d2a COMPMID-3624: CTS failure on Resize quantized in Neon and CL by Michele Di Giorgio · 4 years ago
  80. ef6ec50 COMPMID-3324: Fix oclgrind warnings by Michalis Spyrou · 4 years ago
  81. a179798 COMPMID-3585: Android R while_fib_n_5_quant8 failure on CpuAcc by Michele Di Giorgio · 4 years ago
  82. 42e5736 COMPMID-2078: Remove legacy TODOs by Georgios Pinitas · 4 years ago
  83. 1009e87 COMPMID-3385: Async support to CLArithmetic* kernels/functions Pt.2 by Michalis Spyrou · 4 years ago
  84. 3351f2a COMPMID-3575: Mixed preicision in NEInstanceNormalizationLayerKernel by Sang-Hoon Park · 4 years ago
  85. ad7515d COMPMID-3385: Async support to CLArithmetic* kernels/functions Pt.1 by Michalis Spyrou · 4 years ago
  86. 6c6619b [ONCPUML-120]: Tweak of the launch heuristics for hybrid_u8u32_dot_16x4 kernel by Aleksandr Nikolaev · 4 years ago
  87. 09cad72 COMPMID-3393: Minor tweaks on memory injection interface by Georgios Pinitas · 4 years ago
  88. 318c9f4 COMPMID-3578: Update FP32/int8 kernel selection. by David Mansell · 4 years ago
  89. 40aad9b COMPMID-3600: Fix requantization in NEPixelWiseMultiplicationKernel by Michele Di Giorgio · 4 years ago
  90. 15205d9 COMPMID-3549: GEMM Tuner - Validate input parameters by Eren Kopuz · 4 years ago
  91. aa95ddc COMPMID-3535: 9x9 Direct convolution support for CL and NHWC by Georgios Pinitas · 4 years ago
  92. f932d2c COMPMID-3386: Support memory injection in CLConcatenate functions/kernels by Michele Di Giorgio · 4 years ago
  93. f20d6d6 COMPMID-3390: Async support to CLStridedSliceLayerKernel kernels/functions by Michalis Spyrou · 4 years ago
  94. c6eaec3 COMPMID-3326; Update heuristic for GEMMReshaped and GEMMReshapedOnlyRHS by Gian Marco Iodice · 4 years ago
  95. a449a36 COMPMID-3600: MUL unit test failing with data type QUANT8_ASYMM by Sheri Zhang · 4 years ago
  96. 406a13f COMPMID-3331 Remove y load padding from CLGEMMMatrixMultiplyReshapedOnlyRHSKernel and CLGEMMMatrixMultiplyNativeKernel by SiCong Li · 4 years ago
  97. f6f7876 COMPMID-3532: Align data type support between doxygen and implementation - CL by Michele Di Giorgio · 4 years ago
  98. 954051f COMPMID-3532: Nighly tolerance failure on CLDirectConvolutionLayer 9x9 by Michele Di Giorgio · 4 years ago
  99. 9c82e01 COMPMID-3604: Graph failures during tuning by Georgios Pinitas · 4 years ago
  100. ba2cc1a COMPMID-3577: 9x9 CLDirectConvolution failures by Michele Di Giorgio · 4 years ago