Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / refs/heads/branches/arm_compute_21_05 / src
  1. 3bf76b1 Fix heuristic in Int8 CLDirectConvolutionKernel by Gian Marco Iodice · 3 years, 1 month ago branches/arm_compute_21_05 dev/21_05_int8_optim v21.05
  2. 72d6239 Update heuristic for CLConvolutionLayer by Gian Marco Iodice · 3 years, 2 months ago
  3. 4e38aff Suppress unused variable warning that is present on empty backend builds by Georgios Pinitas · 3 years, 2 months ago
  4. 83079d2 Fix Macros.h include in NEScale by Michele Di Giorgio · 3 years, 2 months ago
  5. 5b81e84 Fix integer overflow and null dereference by Michalis Spyrou · 3 years, 2 months ago
  6. 466b40c Fix missing DATA_TYPE in DOT_PRODUCT4_INTEGER8 OpenCL macro by Gian Marco Iodice · 3 years, 2 months ago
  7. 8a124bc Remove TODOs by Sheri Zhang · 3 years, 2 months ago
  8. b24aa80 Fix performance issues in NEReduction by Pablo Marquez Tello · 3 years, 2 months ago
  9. 7e9f34d Fix for tanh at small argument values by Aleksandr Nikolaev · 3 years, 2 months ago
  10. 1fac037 Fix bug on CLReductionOperation by Giorgio Arena · 3 years, 2 months ago
  11. 6a5eee7 NEReduceMean failed on v8.2 debug build for Android by Manuel Bottini · 3 years, 2 months ago
  12. 0dc0d8e Rename PixelwiseMultiplications to Mul for simplicity by Georgios Pinitas · 3 years, 2 months ago
  13. b699940 Add support for new CPU variants by Georgios Pinitas · 3 years, 2 months ago
  14. 6268742 Update operator list documentation. Part 2. by Teresa Charlin · 3 years, 2 months ago
  15. 50929ef Add optimization for global pooling in pooling_layer.cl by Gian Marco Iodice · 3 years, 2 months ago
  16. baebdb9 Remove Global pooling optimization by Michalis Spyrou · 3 years, 2 months ago
  17. 3ecf9fe Remove OpenCL padding: CLReductionOperationKernel by Giorgio Arena · 3 years, 2 months ago
  18. 8ed3ac1 Add config_id for CLPixelWiseMultiplication by Gian Marco Iodice · 3 years, 2 months ago
  19. 223aba9 Remove stale/solved TODOs by Michele Di Giorgio · 3 years, 2 months ago
  20. 9f6111a Fix Global Pooling failures by Michalis Spyrou · 3 years, 2 months ago
  21. c3c352e Add Queue support by Georgios Pinitas · 3 years, 3 months ago
  22. e253515 Fix for performance regression on G71 (mate9) for direct convolution by Aleksandr Nikolaev · 3 years, 2 months ago
  23. e92b045 Add per-channel quantization support for CLDeconvolutionLayer by Freddie Liardet · 3 years, 2 months ago
  24. 2b7fee0 Add explicit cast on GEMMLowp kernel by Michalis Spyrou · 3 years, 2 months ago
  25. 40471d1 Add optimization for global pooling in pooling_layer.cl by Gian Marco Iodice · 3 years, 2 months ago
  26. 3eb5d29 Remove padding from CLROIPoolingLayerKernel by Gian Marco Iodice · 3 years, 2 months ago
  27. 5c3eeec Fixed CTS failures CLInstanceNorm by Pablo Tello · 3 years, 2 months ago
  28. a7a7436 Fix Depthwise failure in Cpu backend by Michalis Spyrou · 3 years, 2 months ago
  29. 6717688 [Nightly #1129] CL/Winograd/ConvolutionLayer/F16 mismatch on Mate9 by Manuel Bottini · 3 years, 2 months ago
  30. 0758c4c Add missing limits include by Michalis Spyrou · 3 years, 2 months ago
  31. dd2d013 Fix bug on CLPixelWiseMultiplication broadcasted for Quantized types by Giorgio Arena · 3 years, 2 months ago
  32. 402740d Add support for CLVK by Michalis Spyrou · 3 years, 2 months ago
  33. bff2f9f Remove unused yolo_layer OpenCL kernel by Michele Di Giorgio · 3 years, 2 months ago
  34. 3294449 Fix biases check in NEDepthwise by Michalis Spyrou · 3 years, 2 months ago
  35. 778b95c Update assembly code by Michalis Spyrou · 3 years, 2 months ago
  36. dcf4c87 CLDepthwiseConvolutionLayer rework - Part 1 by Giorgio Arena · 3 years, 2 months ago
  37. 562bee5 Port CpuConvertFullyConnectedWeights to new API by Teresa Charlin · 3 years, 3 months ago
  38. ada6cbc Remove OpenCL padding: CLPixelWiseMultiplicationKernel by Giorgio Arena · 3 years, 2 months ago
  39. 031d6a9 [Nightly #1129] CL/Winograd/ConvolutionLayer/F16 mismatch on Mate9 by Manuel Bottini · 3 years, 2 months ago
  40. b25883a Remove experimental tracing feature by Pablo Marquez Tello · 3 years, 2 months ago
  41. ae1c9fe Added S32 Integer support to DIV operator in CLElementWiseOperations with Tests by Suhail Munshi · 3 years, 3 months ago
  42. fe7ae81 CLInstanceNormalizationLayer NHWC optimisation by Pablo Marquez Tello · 3 years, 4 months ago
  43. 60c3b0e Port DepthwiseConvolution to new API by Michalis Spyrou · 3 years, 3 months ago
  44. 4f1650f Remove padding from CLNormalizePlanarYUVLayerKernel by Sheri Zhang · 3 years, 3 months ago
  45. c6fcfb4 Add Tensor related utilities to the new API by Sang-Hoon Park · 3 years, 3 months ago
  46. fe56edb Add padding consideration to pooling index computation by Sang-Hoon Park · 3 years, 3 months ago
  47. 9a81cd8 Fix bug on Implicit Padding for NEON FFT2D by Manuel Bottini · 3 years, 3 months ago
  48. d05f67f Remove unnecessary use AccessWindows by Michele Di Giorgio · 3 years, 3 months ago
  49. 3795491 Add GEMM heuristic for Mali-G78 by Gian Marco Iodice · 3 years, 3 months ago
  50. 142e4ca Remove unused AccessWindow* includes by Michele Di Giorgio · 3 years, 3 months ago
  51. 035004e Add support for a global allocator for OpenCL tensors by Georgios Pinitas · 3 years, 3 months ago
  52. 327225d Port NEDirectConvolutionLayer to new API by Manuel Bottini · 3 years, 3 months ago
  53. 21c2895 Remove OpenCL padding: CLNormalizationLayerKernel by Manuel Bottini · 3 years, 3 months ago
  54. 91b7f74 Port CLConvertFullyConnectedWeights to new API by Teresa Charlin · 3 years, 3 months ago
  55. 598e3a8 Fix TILE initialization in direct convolution and winograd transforms by Gian Marco Iodice · 3 years, 3 months ago
  56. f4edddb Check data type lower bound when creating a tensor by Georgios Pinitas · 3 years, 3 months ago
  57. 21fda6f Fix T_LOAD too few parameters issue by Sheri Zhang · 3 years, 3 months ago
  58. 0a66abe Fix CLDepthwiseConvolutionLayer QSYMM8_PER_CHANNEL mismatches by Giorgio Arena · 3 years, 3 months ago
  59. 0b76f7d Add support for cl_image in CLDirectConvolutionLayer by Gian Marco Iodice · 3 years, 3 months ago
  60. 6dbcc0e Fix OpenCL kernel compiling failure with array initializer by Sheri Zhang · 3 years, 3 months ago
  61. 0aee2dd Fix validation in reshape kernel [cpu,gpu] by Gian Marco Iodice · 3 years, 3 months ago
  62. 99b1a1c Fix bug on Implicit Padding for CL GEMMMatrixMultiplyInterleavedTransposed by Manuel Bottini · 3 years, 3 months ago
  63. 83eee19 Winograd Output transform 7x7 rework by Giorgio Arena · 3 years, 3 months ago
  64. ec82b95 Fix OpenCL kernel compiling failure with array initilizer by Sheri Zhang · 3 years, 3 months ago
  65. 8778108 Rewritten Winograd (4x4, 5x5) output transformation by Aleksandr Nikolaev · 3 years, 3 months ago
  66. 8a1ac61 Fix incorrect return statement in gemm_uint8 heuristic selection by Georgios Pinitas · 3 years, 3 months ago
  67. 4a5f73d Ensure OpenCL runtimes are initialized first by Marco Antognini · 3 years, 3 months ago
  68. b71322d Fix convolution with bias segmentation fault issue by Sheri Zhang · 3 years, 3 months ago
  69. 534b889 Rework the OpenCL Winograd Input Transformations NHWC by Gian Marco Iodice · 3 years, 3 months ago
  70. 6850889 Substitute CLFullyConnectedLayerReshapeWeights by CLTranspose by Teresa Charlin · 3 years, 3 months ago
  71. 28fcc35 Substitute NEFullyConnectedLayerReshapeWeights by NETranspose by Teresa Charlin · 3 years, 3 months ago
  72. 3b5981c Implement Fanout mode in CPPScheduler by SiCongLi · 3 years, 4 months ago
  73. 9d061b0 Add per channel quantization support for NEDeconvolutionLayer by Freddie Liardet · 3 years, 3 months ago
  74. c5b1bee Correct Copyright dates by Michalis Spyrou · 3 years, 3 months ago
  75. 3f26ef4 Add tensor related data structures for the new API by Georgios Pinitas · 3 years, 4 months ago
  76. 7a452fe Remove OpenCL padding: CLL2NormalizeLayerKernel by Manuel Bottini · 3 years, 3 months ago
  77. ca62c6f Mixed data-layout testing on high priority operators by Manuel Bottini · 3 years, 3 months ago
  78. 4ed7b39 Added Qasymm8 datatype support to CLROIPoolingLayer with Tests by Suhail Munshi · 3 years, 3 months ago
  79. 33f41fa Fix trademarks throughout the codebase by Michele Di Giorgio · 3 years, 4 months ago
  80. 5f91b5d Remove alignment FIXME by Michele Di Giorgio · 3 years, 3 months ago
  81. c6f9510 Remove Computer Vision generic interfaces and types by Georgios Pinitas · 3 years, 3 months ago
  82. 2788609 Port ClTranspose to new API by Teresa Charlin · 3 years, 4 months ago
  83. a00180a Update U8 mmla kernel by Michalis Spyrou · 3 years, 3 months ago
  84. 702dc0c Remove usage of valid window region CL - NHWC by Michalis Spyrou · 3 years, 3 months ago
  85. 26c5c0f NEGEMMConvolution and NEGEMMConv2d produce different results by Manuel Bottini · 3 years, 3 months ago
  86. 2ca5b08 New variant of OpenCL Winograd (4x4,5x5) input transformation by Aleksandr Nikolaev · 3 years, 3 months ago
  87. 1e3ab42 Make CpuPixelWiseMultiplicationKernel stateless by Sheri Zhang · 3 years, 4 months ago
  88. e81825b Workaround for compiler error in gcc-9.2 and 9.3 by Pablo Marquez Tello · 3 years, 3 months ago
  89. 97e2580 Check biases pointer before referencing in CLDirectConvolutionLayer by Michele Di Giorgio · 3 years, 3 months ago
  90. 40efd53 Remove GLES-related code by Michele Di Giorgio · 3 years, 3 months ago
  91. a8903c8 Improve performance of Winograd Output Transform 3x3 by Gian Marco Iodice · 3 years, 3 months ago
  92. 32e0646 Fix indexing of SVE ArithmeticAddition kernel by Sang-Hoon Park · 3 years, 3 months ago
  93. b5323cf Fix gemmlowp kernel crash when n0==16 by SiCongLi · 3 years, 4 months ago
  94. 383de02 Fixed compiler errors by Pablo Marquez Tello · 3 years, 3 months ago
  95. 049989a Improve performance of Winograd Input transform 3x3 by Giorgio Arena · 3 years, 3 months ago
  96. 5c9eed8 Extend direct convolution (F32/F16/QASYMM8) by Gian Marco Iodice · 3 years, 3 months ago
  97. 1efed92 Make ClDirectConvolutionKernel stateless by Sheri Zhang · 3 years, 4 months ago
  98. f9ab9f9 Make ClPixelWiseMultiplicationKernel stateless by Sheri Zhang · 3 years, 4 months ago
  99. d1dc09c Port CpuTranspose to new API by Teresa Charlin · 3 years, 4 months ago
  100. 226169f Fix SVE build on newer compilers by Michalis Spyrou · 3 years, 3 months ago