Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / bbf2e7477be984702e1a51f2a23910ee8349b867
  1. e920d6a Printing operators parameters, currently for CpuAdd operator only. by Ramy Elgammal · 3 years ago
  2. b1db6e1 Fixed compiler error by Pablo Marquez Tello · 2 years, 11 months ago
  3. c89998f Fix strict overflow warnings by Michalis Spyrou · 3 years ago
  4. 7891a73 Move CPU/GPU files from Core/Runtime to the respective backend folders by Georgios Pinitas · 3 years ago
  5. a46c9c9 Sync backend only if allocated rather than supported by Giorgio Arena · 3 years ago
  6. 3cfd329 Fix cl_gemm_reshaped.cpp example by Gian Marco Iodice · 3 years ago
  7. 9c67d38 Remove map/unmap overhead for input/output accessor when using DummyAccessor by Giorgio Arena · 3 years ago
  8. 87a74ef Re-use auxiliary memory withing CpuWinogradConv2d operators by Georgios Pinitas · 3 years ago
  9. 511771f Remove padding from ClScaleKernel by Giorgio Arena · 3 years ago
  10. 1988463 Rename [Cl|Cpu]GemmConvolution to [Cl|Gpu]GemmConv2d by Georgios Pinitas · 3 years ago
  11. 73df931 Address comments on avoiding releasing weights if used by multiple functions by Giorgio Arena · 3 years ago
  12. df5bcb6 Enable fast_math on CpuGemmConvolution by Georgios Pinitas · 3 years ago
  13. ebbd529 Update the heuristic to call direct convolution in clConv2d by Gian Marco Iodice · 3 years ago
  14. f5d51f3 Retain weights in ClGemm when reconfiguring the operator with retention by Georgios Pinitas · 3 years ago
  15. 8273676 Update Errata by Gian Marco Iodice · 3 years ago
  16. 77014ff Update Release Notes by Freddie Liardet · 3 years ago
  17. 45fbf9f Avoid releasing weights if they are used by multiple functions by Georgios Pinitas · 3 years ago
  18. 37a4611 Add test for validating batched-GEMM on CPU by Gian Marco Iodice · 3 years ago
  19. 7c29657 increase CL/BatchNormalizationLayer Fp16 absolute threshold by Gunes Bayir · 3 years ago
  20. d4a5bc5 Ensure correct transformed matrices are used in CpuGemmConvolution by Georgios Pinitas · 3 years ago
  21. 39aebd1 Fixing the Issue when building for Android using compress_kernels=1 and python 3 by Adnan AlSinan · 3 years ago
  22. fa1db17 Ensure that correct transformed matrices are used in CpuFullyConnected by Georgios Pinitas · 3 years ago
  23. d761a3e Fix performance regression due to clFinish() by Gian Marco Iodice · 3 years ago
  24. 288d3cb Fix compiler error in CLActivationLayer by Pablo Marquez Tello · 3 years ago
  25. ced49dc Remove TODO, FIXME and COMPMID comments where possible by Freddie Liardet · 3 years ago
  26. acb4d93 Fix compiler error in GCC 7.4 + Ubuntu 16 by Pablo Marquez Tello · 3 years ago
  27. 760c783 Specify GPU high priority files in SConscript by Michele Di Giorgio · 3 years ago
  28. f289e57 Update build documentation by Freddie Liardet · 3 years ago
  29. dc43a98 Update operators list in Doxygen by Freddie Liardet · 3 years ago
  30. 1562af3 Update SONAME_VERSION in SConscript by Freddie Liardet · 3 years ago
  31. 3f74389 Remove 21.08 deprecated code by Freddie Liardet · 3 years ago
  32. 0f6ca4b Report error for unsupported non-constant weights in CpuFullyConnected by Michele Di Giorgio · 3 years ago
  33. 6269f87 Fix depthwise convolution assembly kernels by Freddie Liardet · 3 years ago
  34. 38ce29d Fix CL direct conv layer test FP32 absolute tolerance issue by Gunes Bayir · 3 years ago
  35. 6634194 Avoid over-allocation of temporary buffers within CpuWinogradConv2d by Georgios Pinitas · 3 years ago
  36. 4164814 Implement Operator API by Georgios Pinitas · 3 years ago
  37. 6e90c12 Add missing limits include by Freddie Liardet · 3 years ago
  38. ba2dd82 Benchmark and set default LWS for GEMM, Direct convolution and Winograd by Giorgio Arena · 3 years ago
  39. 06d1efd Port CLConvolutionLayer by Sheri Zhang · 3 years ago
  40. 529b5a2 Port ClFullyConnected to new API by Georgios Pinitas · 3 years ago
  41. a0efe69 Reintroduce implementation of NEConvolutionLayer::get_convolution_method by Michele Di Giorgio · 3 years ago
  42. 9a1e28b Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1 by Gian Marco Iodice · 3 years ago
  43. a76e403 Fix A55 performance constant for fp16 hybrid gemm kernel by Georgios Pinitas · 3 years ago
  44. b55f8e8 Port NEConvolutionLayer by Michalis Spyrou · 3 years ago
  45. 8e2f64f Create custom flags for enabling fp16 support by Georgios Pinitas · 3 years ago
  46. a86433a Reduce binary footprint of CpuConvertFullyConnectedWeightsKernel by Michele Di Giorgio · 3 years ago
  47. 120c87b Fix bare metal build issues by Freddie Liardet · 3 years ago
  48. bb5d42c Fix cpu GEMM fp16 issue by Freddie Liardet · 3 years ago
  49. f81f51c Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago
  50. 97426a7 Remove generated kernels that overlap hand-written ones by Georgios Pinitas · 3 years ago
  51. 9805583 Fix memory lifetime issue by Georgios Pinitas · 3 years ago
  52. d87aded Port CLGEMMConvolutionLayer by Manuel Bottini · 3 years ago
  53. 4718706 Dispatch Conv2d using the Direct method when necessary by Georgios Pinitas · 3 years ago
  54. 387f80e Update GEMM assembly performance parameters by Georgios Pinitas · 3 years ago
  55. 5e61cb0 Add missing limits include by Freddie Liardet · 3 years ago
  56. e92c23e Fix allocation of prepare tensor on ClWinogradConv2d by Georgios Pinitas · 3 years ago
  57. 7075fe2 Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years, 1 month ago
  58. 22f5ed5 Avoid allocation of auxiliary memory in CpuGemmConvolution by Georgios Pinitas · 3 years ago
  59. 8bd2556 Fix vector_length identification mechanism for SVE by Georgios Pinitas · 3 years ago
  60. d9cdf14 Port NEFullyConnectedLayer to memory injecting interface by Michele Di Giorgio · 3 years, 1 month ago
  61. a8297fb Pass fast math flag for correct GEMM3D validation support by Georgios Pinitas · 3 years ago
  62. 6575ef8 Fix formatting issue with blank profiler header by Freddie Liardet · 3 years ago
  63. f67034e Fix NN driver build script for Android R by Michele Di Giorgio · 3 years ago
  64. e7012a6 Fix bare metal build error by Freddie Liardet · 3 years ago
  65. dae5e1e Remove printing Android version detected by the build system by Pablo Marquez Tello · 3 years ago
  66. 69a9ac4 Expose fast_math mode for GEMM through BFloat16 by Georgios Pinitas · 3 years ago
  67. 1fa27ad Inject temporary tensors to pack in they don't exist in CpuSoftmax by Georgios Pinitas · 3 years ago
  68. f113f37 Print the Android version detected by the build system by Pablo Marquez Tello · 3 years ago
  69. f4e84fb Port ClGemmLowp to new API by Georgios Pinitas · 3 years, 1 month ago
  70. 767dbf9 Fix oclgrind int overflow warning by Freddie Liardet · 3 years ago
  71. 4ee8b15 Update GEMM assembly kernels by Georgios Pinitas · 3 years ago
  72. 59fd7a7 Add layer data to JSON output by Freddie Liardet · 3 years, 1 month ago
  73. 67354e0 Update OpenCL Header file to version v.2020.03.13 by Sheri Zhang · 3 years, 1 month ago
  74. 0f033df Include limits header to fix errors reported by GCC11 by Michele Di Giorgio · 3 years ago
  75. 2b147ee Avoid multiple Rhs matrix transformation on ClGemm by Georgios Pinitas · 3 years, 1 month ago
  76. d0c5df2 Disabled armv8-2a on Android P by Pablo Marquez Tello · 3 years ago
  77. d844c08 Port CLIm2ColKernel to ClIm2ColKernel by Manuel Bottini · 3 years ago
  78. 0b27133 Disabled DirectConv method for NCHW and kernel > 15 by Pablo Marquez Tello · 3 years, 1 month ago
  79. 29599d0 Port NEGEMMConvolutionLayer by Manuel Bottini · 3 years, 1 month ago
  80. 13ef176 Improve filelist for GPU by Georgios Pinitas · 3 years ago
  81. 7b23732 Port CLCol2ImKernel to ClCol2ImKernel by Manuel Bottini · 3 years ago
  82. e5d76e1 Increase tolerance for NEMeanStdDevNormalization by Georgios Pinitas · 3 years ago
  83. c38ca38 Fix CL kernel compilation failure by Michalis Spyrou · 3 years ago
  84. a387e27 Add in-place calculation support for CL elementwise arithmetic kernels by Sheri Zhang · 3 years, 1 month ago
  85. 6fc7d52 Override arch option to alow building for armv8-2a by Pablo Marquez Tello · 3 years, 1 month ago
  86. 96f977e Port NEWinogradConvolutionLayer by Michalis Spyrou · 3 years, 1 month ago
  87. 04b39e8 Limit the LOOP_UNROLLING on the kernel height by Gian Marco Iodice · 3 years, 1 month ago
  88. 24b8920 Port NECol2ImKernel by Manuel Bottini · 3 years, 1 month ago
  89. da81675 Remove redundant implementations of Add/Sub operators by Georgios Pinitas · 3 years, 1 month ago
  90. 4411e1f Change CLConvolution selection to run Direct approach on large kernels by Georgios Pinitas · 3 years, 1 month ago
  91. dd23f2a Add LayerData to all nodes by Freddie Liardet · 3 years, 1 month ago
  92. cfac51c Port NEGEMMLowp Part 2 by Manuel Bottini · 3 years, 1 month ago
  93. 06ac6e4 Add basic Operator interface by Georgios Pinitas · 3 years, 1 month ago
  94. 4587594 Validate unsupported data types with runtime information by Georgios Pinitas · 3 years, 1 month ago
  95. 5e28181 Fix manual LOOP_UNROLLING by Gian Marco Iodice · 3 years, 1 month ago
  96. 9002899 Port NEIm2ColKernel by Manuel Bottini · 3 years, 1 month ago
  97. 6132c7a Rework README.md structure by Gian Marco Iodice · 3 years, 1 month ago
  98. 5ee0d95 Improve implementation selection speed of CpuElementwiseUnary by Georgios Pinitas · 3 years, 1 month ago
  99. 8155c02 Rework OpenCL Depthwise Convolution by Gian Marco Iodice · 3 years, 3 months ago
  100. 2eb5d16 Align kernel/operator header layout by Georgios Pinitas · 3 years, 1 month ago