Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 93f7c3fe1a9c8c98265c50376cacd5fd9ebb7a72
  1. 93f7c3f Add OpenCL sources to Android.bp file by Jakub Sujak · 2 years, 9 months ago
  2. 63e0beb Add support for non-constant weights and biases in CpuFullyConnected by Giorgio Arena · 2 years, 9 months ago
  3. b1ba1e3 FIX: seg fault when printing TensorInfo's quantization info per channel by ramelg01 · 2 years, 9 months ago
  4. 2e53f17 Provide logging for configure functions in all gpu operators by ramelg01 · 2 years, 9 months ago
  5. a717110 Generate an operator configuration file from a list of tflite models by Georgios Pinitas · 2 years, 11 months ago
  6. 93d6cf0 Decouple logging flag from debug and assert flags by ramelg01 · 2 years, 9 months ago
  7. 61b6e24 Use std::vector instead of Coordinates for ITensorInfo's _dims_state by Giorgio Arena · 2 years, 9 months ago
  8. 0bb6230 Fix inefficient store in gemmlowp_mm_reshaped_only_rhs_t by Gian Marco Iodice · 2 years, 9 months ago
  9. 732d879 Update errata by Sheri Zhang · 2 years, 10 months ago
  10. 79cb945 Update OpenCL header file to version 2020.12.18 by Sheri Zhang · 2 years, 10 months ago
  11. cbbb038 Provide logging for configure functions in all NEON functions by ramelg01 · 2 years, 10 months ago
  12. 3ae3d88 Provide logging for configure functions in all cpu operators by ramelg01 · 2 years, 10 months ago
  13. 2ec6163 Fix Build error with asserts=0 by Adnan AlSinan · 2 years, 10 months ago
  14. 9ac7b99 Revert "Add support for non-constant weights and biases in CpuFullyConnected" by Pablo Marquez Tello · 2 years, 10 months ago
  15. cc171f9 Provide tests for fusing pad layer in graph API by Gunes Bayir · 2 years, 10 months ago
  16. 9d6ddfc Fix nightly cl_image not supported issue by Sheri Zhang · 2 years, 10 months ago
  17. e4563a0 Adds Conv3d reference implementation support. by Adnan AlSinan · 2 years, 10 months ago
  18. e42a87f Update cpu heuristics for GEMM by Gunes Bayir · 2 years, 10 months ago
  19. 7bc1a77 Optimize ClScaleKernel on NHWC (f32/f16/int8) by Gian Marco Iodice · 2 years, 10 months ago
  20. 67b9d7f Remove WinogradInputTransform from operator list by Sheri Zhang · 2 years, 10 months ago
  21. 3841f4c Make the output consistent with other tests by Gunes Bayir · 2 years, 10 months ago
  22. 951d520 Remove padding from ClGemmMatrixMultiplyReshapedOnlyRhsKernel by Giorgio Arena · 2 years, 10 months ago
  23. 2f9ae16 Avoid checking on biases' constantness if nullptr by Giorgio Arena · 2 years, 10 months ago
  24. 88bd35d Fix vload_partial macros on OpenCL by Giorgio Arena · 2 years, 10 months ago
  25. bde2f35 Remove padding from ClGemmMatrixMultiplyReshapedKernel by Giorgio Arena · 2 years, 10 months ago
  26. 814bddf Fuse pad layer with subsequent convolution layer by Gunes Bayir · 2 years, 10 months ago
  27. aed63ee Add support for non-constant weights and biases in CpuFullyConnected by Michele Di Giorgio · 3 years ago
  28. 58d3c5a Fixed android nn driver compiler error by Pablo Marquez Tello · 2 years, 10 months ago
  29. d216f57 Update cpu depthwise kernels by Freddie Liardet · 2 years, 11 months ago
  30. 4e53c5a Revert "Remove padding from ClGemmMatrixMultiplyReshapedKernel" by Pablo Marquez Tello · 2 years, 10 months ago
  31. 8afe6c7 OpenCL job chaining support by Giorgio Arena · 2 years, 10 months ago
  32. 2c74f13 Fix Android.bp errors by Freddie Liardet · 2 years, 10 months ago
  33. 9dc558f Review all shapes in datasets to account for padding removal Part 1 by Gian Marco Iodice · 3 years, 8 months ago
  34. 8fce496 Remove padding from ClPool2dKernel NCHW by Giorgio Arena · 2 years, 10 months ago
  35. b8025b3 List OpenCL kernels in Android.bp script by Michele Di Giorgio · 2 years, 10 months ago
  36. aed61f2 Fix CLNormalizationLayer NCHW border calculation by SiCongLi · 2 years, 10 months ago
  37. 50335fd Remove padding from ClGemmMatrixMultiplyReshapedKernel by Michele Di Giorgio · 2 years, 10 months ago
  38. e2276cb Fix README.md formatting by Freddie Liardet · 2 years, 10 months ago
  39. e920d6a Printing operators parameters, currently for CpuAdd operator only. by Ramy Elgammal · 2 years, 10 months ago
  40. b1db6e1 Fixed compiler error by Pablo Marquez Tello · 2 years, 10 months ago
  41. c89998f Fix strict overflow warnings by Michalis Spyrou · 2 years, 10 months ago
  42. 7891a73 Move CPU/GPU files from Core/Runtime to the respective backend folders by Georgios Pinitas · 2 years, 10 months ago
  43. a46c9c9 Sync backend only if allocated rather than supported by Giorgio Arena · 2 years, 10 months ago
  44. 3cfd329 Fix cl_gemm_reshaped.cpp example by Gian Marco Iodice · 2 years, 10 months ago
  45. 9c67d38 Remove map/unmap overhead for input/output accessor when using DummyAccessor by Giorgio Arena · 2 years, 10 months ago
  46. 87a74ef Re-use auxiliary memory withing CpuWinogradConv2d operators by Georgios Pinitas · 2 years, 10 months ago
  47. 511771f Remove padding from ClScaleKernel by Giorgio Arena · 2 years, 10 months ago
  48. 1988463 Rename [Cl|Cpu]GemmConvolution to [Cl|Gpu]GemmConv2d by Georgios Pinitas · 2 years, 11 months ago
  49. 73df931 Address comments on avoiding releasing weights if used by multiple functions by Giorgio Arena · 2 years, 11 months ago
  50. df5bcb6 Enable fast_math on CpuGemmConvolution by Georgios Pinitas · 2 years, 11 months ago
  51. ebbd529 Update the heuristic to call direct convolution in clConv2d by Gian Marco Iodice · 2 years, 11 months ago
  52. f5d51f3 Retain weights in ClGemm when reconfiguring the operator with retention by Georgios Pinitas · 2 years, 11 months ago
  53. 8273676 Update Errata by Gian Marco Iodice · 2 years, 11 months ago
  54. 77014ff Update Release Notes by Freddie Liardet · 2 years, 11 months ago
  55. 45fbf9f Avoid releasing weights if they are used by multiple functions by Georgios Pinitas · 2 years, 11 months ago
  56. 37a4611 Add test for validating batched-GEMM on CPU by Gian Marco Iodice · 2 years, 11 months ago
  57. 7c29657 increase CL/BatchNormalizationLayer Fp16 absolute threshold by Gunes Bayir · 2 years, 11 months ago
  58. d4a5bc5 Ensure correct transformed matrices are used in CpuGemmConvolution by Georgios Pinitas · 2 years, 11 months ago
  59. 39aebd1 Fixing the Issue when building for Android using compress_kernels=1 and python 3 by Adnan AlSinan · 2 years, 11 months ago
  60. fa1db17 Ensure that correct transformed matrices are used in CpuFullyConnected by Georgios Pinitas · 2 years, 11 months ago
  61. d761a3e Fix performance regression due to clFinish() by Gian Marco Iodice · 2 years, 11 months ago
  62. 288d3cb Fix compiler error in CLActivationLayer by Pablo Marquez Tello · 2 years, 11 months ago
  63. ced49dc Remove TODO, FIXME and COMPMID comments where possible by Freddie Liardet · 2 years, 11 months ago
  64. acb4d93 Fix compiler error in GCC 7.4 + Ubuntu 16 by Pablo Marquez Tello · 2 years, 11 months ago
  65. 760c783 Specify GPU high priority files in SConscript by Michele Di Giorgio · 2 years, 11 months ago
  66. f289e57 Update build documentation by Freddie Liardet · 2 years, 11 months ago
  67. dc43a98 Update operators list in Doxygen by Freddie Liardet · 2 years, 11 months ago
  68. 1562af3 Update SONAME_VERSION in SConscript by Freddie Liardet · 2 years, 11 months ago
  69. 3f74389 Remove 21.08 deprecated code by Freddie Liardet · 2 years, 11 months ago
  70. 0f6ca4b Report error for unsupported non-constant weights in CpuFullyConnected by Michele Di Giorgio · 2 years, 11 months ago
  71. 6269f87 Fix depthwise convolution assembly kernels by Freddie Liardet · 2 years, 11 months ago
  72. 38ce29d Fix CL direct conv layer test FP32 absolute tolerance issue by Gunes Bayir · 2 years, 11 months ago
  73. 6634194 Avoid over-allocation of temporary buffers within CpuWinogradConv2d by Georgios Pinitas · 2 years, 11 months ago
  74. 4164814 Implement Operator API by Georgios Pinitas · 2 years, 11 months ago
  75. 6e90c12 Add missing limits include by Freddie Liardet · 2 years, 11 months ago
  76. ba2dd82 Benchmark and set default LWS for GEMM, Direct convolution and Winograd by Giorgio Arena · 3 years ago
  77. 06d1efd Port CLConvolutionLayer by Sheri Zhang · 3 years ago
  78. 529b5a2 Port ClFullyConnected to new API by Georgios Pinitas · 3 years ago
  79. a0efe69 Reintroduce implementation of NEConvolutionLayer::get_convolution_method by Michele Di Giorgio · 2 years, 11 months ago
  80. 9a1e28b Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1 by Gian Marco Iodice · 3 years ago
  81. a76e403 Fix A55 performance constant for fp16 hybrid gemm kernel by Georgios Pinitas · 3 years ago
  82. b55f8e8 Port NEConvolutionLayer by Michalis Spyrou · 3 years ago
  83. 8e2f64f Create custom flags for enabling fp16 support by Georgios Pinitas · 3 years ago
  84. a86433a Reduce binary footprint of CpuConvertFullyConnectedWeightsKernel by Michele Di Giorgio · 3 years ago
  85. 120c87b Fix bare metal build issues by Freddie Liardet · 3 years ago
  86. bb5d42c Fix cpu GEMM fp16 issue by Freddie Liardet · 3 years ago
  87. f81f51c Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago
  88. 97426a7 Remove generated kernels that overlap hand-written ones by Georgios Pinitas · 3 years ago
  89. 9805583 Fix memory lifetime issue by Georgios Pinitas · 3 years ago
  90. d87aded Port CLGEMMConvolutionLayer by Manuel Bottini · 3 years ago
  91. 4718706 Dispatch Conv2d using the Direct method when necessary by Georgios Pinitas · 3 years ago
  92. 387f80e Update GEMM assembly performance parameters by Georgios Pinitas · 3 years ago
  93. 5e61cb0 Add missing limits include by Freddie Liardet · 3 years ago
  94. e92c23e Fix allocation of prepare tensor on ClWinogradConv2d by Georgios Pinitas · 3 years ago
  95. 7075fe2 Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago
  96. 22f5ed5 Avoid allocation of auxiliary memory in CpuGemmConvolution by Georgios Pinitas · 3 years ago
  97. 8bd2556 Fix vector_length identification mechanism for SVE by Georgios Pinitas · 3 years ago
  98. d9cdf14 Port NEFullyConnectedLayer to memory injecting interface by Michele Di Giorgio · 3 years ago
  99. a8297fb Pass fast math flag for correct GEMM3D validation support by Georgios Pinitas · 3 years ago
  100. 6575ef8 Fix formatting issue with blank profiler header by Freddie Liardet · 3 years ago