Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 251b5145309e941a32c6c7691062544f2fd243fb / src / runtime
  1. a3e57c2 Add dynamic weights for CPU fully connected layer by Viet-Hoa Do · 1 year, 6 months ago
  2. 4ceb453 Add CropInfo to BatchToSpace reference and fixture by SiCong Li · 1 year, 6 months ago
  3. 47f177e Fix LWS search space used by CLTuner by SiCong Li · 1 year, 6 months ago
  4. adfcacc Add weights_info as optional input for NEDeconvolutionLayer by Annop Wongwathanarat · 1 year, 6 months ago
  5. c4ed2fd Extend skip upsampling for deconvolution for non-1x1 kernels by Annop Wongwathanarat · 1 year, 7 months ago
  6. 5dc732e Fix performance regression in Transposed Convolution by Gunes Bayir · 1 year, 7 months ago
  7. ae72a46 Add new operator AddMulAdd for Neon™ backend for Float/Quantized types by Gunes Bayir · 1 year, 7 months ago
  8. 464ed20 Remove fixed format strides hack by Jonathan Deakin · 1 year, 8 months ago
  9. b609c93 Skip upsampling for deconvolution when not needed by Annop Wongwathanarat · 1 year, 7 months ago
  10. a6a1538 Fix performance regression when stride equal to kernel size by Gunes Bayir · 1 year, 7 months ago
  11. 11f7d7e Add enable_fast_math for NEDeconvolutionLayer by Annop Wongwathanarat · 1 year, 8 months ago
  12. a68df8d Revert "Update the heuristic for CLDepthwiseConvolutionNative kernel" by Gian Marco Iodice · 1 year, 7 months ago
  13. bc67208 Update the heuristic for CLDepthwiseConvolutionNative kernel by Gian Marco Iodice · 1 year, 8 months ago
  14. 9d3bd41 Move DWC native heuristic into the heuristic folder by Gian Marco Iodice · 1 year, 8 months ago
  15. a5cb79f Update the ClConv2d heuristic by Gian Marco Iodice · 1 year, 8 months ago
  16. e317baf Optimize MeanReduce by integer acc. and removing upfront dequant. by Omar Al Khatib · 1 year, 8 months ago
  17. a0ae8d2 Optimize Transposed Convolution for CL backend (Quantized) by Gunes Bayir · 1 year, 9 months ago
  18. df6a3b0 Use heuristics for setting dynamic fusion direct conv2d tile sizes by Ramy Elgammal · 1 year, 9 months ago
  19. 76335eb Implement the OpenCL kernel to compute the indirect convolution by Gian Marco Iodice · 1 year, 9 months ago
  20. 31df05a Remove dynamic fusion prototype with tests and examples by SiCong Li · 1 year, 10 months ago
  21. d2475c7 Add num_threads_to_use to OMPScheduler based on workload size by cfRod · 1 year, 9 months ago
  22. ec0113d Optimize Transposed Convolution for CL backend (FP32/16) by Gunes Bayir · 1 year, 10 months ago
  23. ad9a7ed Rework DepthwiseConvolution heuristic on OpenCL by Gian Marco Iodice · 2 years ago
  24. c4f2743 Optimize Quantized/Integer Bilinear Scale for Neon™ by Gunes Bayir · 2 years ago
  25. 0eed305 Optimize FP32/16 Bilinear Scale Kernel for Neon™ by Gunes Bayir · 2 years ago
  26. 211a55d Optimize depthwise convolution on OpenCL by Gian Marco Iodice · 2 years ago
  27. cd083cf Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer repeatedly when mapping multiple children of the same parent. by Murray Kornelsen · 2 years, 1 month ago
  28. 8bab588 Fix validation problem in CLQLSTMLayer by Pablo Marquez Tello · 2 years ago
  29. 52695f5 Fix CTS/SLTS failure related to Depthwise Convolution by Gunes Bayir · 2 years, 1 month ago
  30. 13b623e [ONCPUML-968] Fixed format kernel support in additional APIs by Milos Puzovic · 2 years, 1 month ago
  31. 385dad2 Fix for OpenMP scheduler work breakdown by Milos Puzovic · 2 years, 1 month ago
  32. 9178002 Fix for inclusion of "arm_gemm" from src into "Types.h" from core by Ramy Elgammal · 2 years, 1 month ago
  33. 553f695 [ONCPUML-951] Variable weight support for Convolution. by Francesco Petrogalli · 2 years, 2 months ago
  34. a1f7851 Integrate new winograd APIs from MLTech by ramelg01 · 2 years, 2 months ago
  35. 4bfc70e Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16 by Gunes Bayir · 2 years, 9 months ago
  36. 22dd8b9 Add missing flag when building cl graph examples and fix by Michalis Spyrou · 2 years, 2 months ago
  37. f28abef Fix compilation error in 32-bit with logging build by Viet-Hoa Do · 2 years, 3 months ago
  38. b63b119 Integrate Dynamic Fusion patches by SiCong Li · 2 years, 7 months ago
  39. 5873358 QLSTM add support for different qinfo by Mike Kelly · 2 years, 4 months ago
  40. 1bae0f9 NEQLSTM: perform type conversion in prepare method. by Pablo Marquez Tello · 2 years, 4 months ago
  41. 0a486cf Enable dynamic cl tuning for dynamically fused kernels by SiCong Li · 2 years, 5 months ago
  42. 16c5697 Add DirectConvolution2D kernel component for dynamic fusion by Gunes Bayir · 2 years, 5 months ago
  43. 171fc3d Add CPU Pool3d FP16/32 implementation by Adnan AlSinan · 2 years, 5 months ago
  44. a5d61bf NEQLSTM: Add support for QASYMM8_SIGNED for input_to_forget_weights by Pablo Marquez Tello · 2 years, 5 months ago
  45. bfd10a1 QLSTM add support for different qinfo in weights by Pablo Marquez Tello · 2 years, 5 months ago
  46. 3751569 Implementation of ClPooling3d by ramelg01 · 2 years, 6 months ago
  47. 4e66d70 Added windows native build support by Pablo Tello · 2 years, 6 months ago
  48. 232c452 Merge kernel prototype patch by Giorgio Arena · 2 years, 6 months ago
  49. 9454cf7 Fixed threshould argument order in NE/CL/LSTM by Pablo Marquez Tello · 2 years, 6 months ago
  50. 149203b Port MaxUnpoolingLayer kernel and add KernelSelect vaidation test by Dana Zlotnik · 2 years, 7 months ago
  51. 6863fa0 Remove deprecated remap functions. by Adnan AlSinan · 2 years, 7 months ago
  52. 7195f71 Add OpenBSD/arm64 support. by Kevin Lo · 2 years, 8 months ago
  53. d7154db Implement 1D Adaptive Workload Splitting in CPPScheduler by Dana Zlotnik · 2 years, 10 months ago
  54. e7a5b0e Initialise quantization info in NEPadLayer by Pablo Marquez Tello · 2 years, 10 months ago
  55. 3177861 Fix PostOp dependency by SiCongLi · 2 years, 10 months ago
  56. 579ca84 Add PostOp support to GEMM and CLGEMM operators and functions Part 2 by SiCongLi · 2 years, 10 months ago
  57. 1af5416 Add experimental PostOp interface to ClGemmMatrixMultiplyReshapedKernel Part 1 by SiCongLi · 2 years, 11 months ago
  58. 5dda217 DirectConv3d support refine by Sheri Zhang · 2 years, 11 months ago
  59. c9cecc0 Remove legacy GeMM kernels on OpenCL by Gian Marco Iodice · 2 years, 11 months ago
  60. 6d9c982 Conv3d support by Sheri Zhang · 3 years ago
  61. 945ae9e Implement CLDirectConv3D f32/f16 by Giorgio Arena · 2 years, 11 months ago
  62. b6af482 Per-operator build dependencies by Georgios Pinitas · 3 years ago
  63. 8229e5a Fix of linking errors to find CPPSplit symbols when compiling android nn driver by ramelg01 · 2 years, 11 months ago
  64. 4a6d9e8 Provide logging for configure functions in all CPP functions by ramelg01 · 2 years, 11 months ago
  65. 6d89157 Provide logging for configure functions in all CL functions by ramelg01 · 2 years, 11 months ago
  66. cbbb038 Provide logging for configure functions in all NEON functions by ramelg01 · 3 years ago
  67. 8afe6c7 OpenCL job chaining support by Giorgio Arena · 3 years ago
  68. 7891a73 Move CPU/GPU files from Core/Runtime to the respective backend folders by Georgios Pinitas · 3 years ago
  69. 87a74ef Re-use auxiliary memory withing CpuWinogradConv2d operators by Georgios Pinitas · 3 years ago
  70. 511771f Remove padding from ClScaleKernel by Giorgio Arena · 3 years ago
  71. 1988463 Rename [Cl|Cpu]GemmConvolution to [Cl|Gpu]GemmConv2d by Georgios Pinitas · 3 years ago
  72. 73df931 Address comments on avoiding releasing weights if used by multiple functions by Giorgio Arena · 3 years ago
  73. df5bcb6 Enable fast_math on CpuGemmConvolution by Georgios Pinitas · 3 years ago
  74. ebbd529 Update the heuristic to call direct convolution in clConv2d by Gian Marco Iodice · 3 years ago
  75. f5d51f3 Retain weights in ClGemm when reconfiguring the operator with retention by Georgios Pinitas · 3 years ago
  76. 45fbf9f Avoid releasing weights if they are used by multiple functions by Georgios Pinitas · 3 years ago
  77. d4a5bc5 Ensure correct transformed matrices are used in CpuGemmConvolution by Georgios Pinitas · 3 years ago
  78. fa1db17 Ensure that correct transformed matrices are used in CpuFullyConnected by Georgios Pinitas · 3 years ago
  79. d761a3e Fix performance regression due to clFinish() by Gian Marco Iodice · 3 years, 1 month ago
  80. 288d3cb Fix compiler error in CLActivationLayer by Pablo Marquez Tello · 3 years, 1 month ago
  81. acb4d93 Fix compiler error in GCC 7.4 + Ubuntu 16 by Pablo Marquez Tello · 3 years, 1 month ago
  82. 3f74389 Remove 21.08 deprecated code by Freddie Liardet · 3 years, 1 month ago
  83. 0f6ca4b Report error for unsupported non-constant weights in CpuFullyConnected by Michele Di Giorgio · 3 years, 1 month ago
  84. 6634194 Avoid over-allocation of temporary buffers within CpuWinogradConv2d by Georgios Pinitas · 3 years, 1 month ago
  85. 4164814 Implement Operator API by Georgios Pinitas · 3 years, 1 month ago
  86. 06d1efd Port CLConvolutionLayer by Sheri Zhang · 3 years, 1 month ago
  87. 529b5a2 Port ClFullyConnected to new API by Georgios Pinitas · 3 years, 1 month ago
  88. a0efe69 Reintroduce implementation of NEConvolutionLayer::get_convolution_method by Michele Di Giorgio · 3 years, 1 month ago
  89. b55f8e8 Port NEConvolutionLayer by Michalis Spyrou · 3 years, 1 month ago
  90. a86433a Reduce binary footprint of CpuConvertFullyConnectedWeightsKernel by Michele Di Giorgio · 3 years, 1 month ago
  91. 9805583 Fix memory lifetime issue by Georgios Pinitas · 3 years, 1 month ago
  92. d87aded Port CLGEMMConvolutionLayer by Manuel Bottini · 3 years, 1 month ago
  93. 4718706 Dispatch Conv2d using the Direct method when necessary by Georgios Pinitas · 3 years, 1 month ago
  94. e92c23e Fix allocation of prepare tensor on ClWinogradConv2d by Georgios Pinitas · 3 years, 1 month ago
  95. 22f5ed5 Avoid allocation of auxiliary memory in CpuGemmConvolution by Georgios Pinitas · 3 years, 1 month ago
  96. d9cdf14 Port NEFullyConnectedLayer to memory injecting interface by Michele Di Giorgio · 3 years, 2 months ago
  97. a8297fb Pass fast math flag for correct GEMM3D validation support by Georgios Pinitas · 3 years, 1 month ago
  98. 69a9ac4 Expose fast_math mode for GEMM through BFloat16 by Georgios Pinitas · 3 years, 1 month ago
  99. 1fa27ad Inject temporary tensors to pack in they don't exist in CpuSoftmax by Georgios Pinitas · 3 years, 1 month ago
  100. f4e84fb Port ClGemmLowp to new API by Georgios Pinitas · 3 years, 2 months ago