Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 2ec6163cdbd274ec9207a7b4ee6e144f93440b4f / src
  1. 9ac7b99 Revert "Add support for non-constant weights and biases in CpuFullyConnected" by Pablo Marquez Tello · 2 years, 10 months ago
  2. cc171f9 Provide tests for fusing pad layer in graph API by Gunes Bayir · 2 years, 10 months ago
  3. e4563a0 Adds Conv3d reference implementation support. by Adnan AlSinan · 2 years, 10 months ago
  4. e42a87f Update cpu heuristics for GEMM by Gunes Bayir · 2 years, 10 months ago
  5. 7bc1a77 Optimize ClScaleKernel on NHWC (f32/f16/int8) by Gian Marco Iodice · 2 years, 10 months ago
  6. 951d520 Remove padding from ClGemmMatrixMultiplyReshapedOnlyRhsKernel by Giorgio Arena · 2 years, 10 months ago
  7. 2f9ae16 Avoid checking on biases' constantness if nullptr by Giorgio Arena · 2 years, 10 months ago
  8. 88bd35d Fix vload_partial macros on OpenCL by Giorgio Arena · 2 years, 10 months ago
  9. bde2f35 Remove padding from ClGemmMatrixMultiplyReshapedKernel by Giorgio Arena · 2 years, 10 months ago
  10. 814bddf Fuse pad layer with subsequent convolution layer by Gunes Bayir · 2 years, 10 months ago
  11. aed63ee Add support for non-constant weights and biases in CpuFullyConnected by Michele Di Giorgio · 3 years ago
  12. d216f57 Update cpu depthwise kernels by Freddie Liardet · 2 years, 11 months ago
  13. 4e53c5a Revert "Remove padding from ClGemmMatrixMultiplyReshapedKernel" by Pablo Marquez Tello · 2 years, 10 months ago
  14. 8afe6c7 OpenCL job chaining support by Giorgio Arena · 2 years, 10 months ago
  15. 8fce496 Remove padding from ClPool2dKernel NCHW by Giorgio Arena · 2 years, 10 months ago
  16. aed61f2 Fix CLNormalizationLayer NCHW border calculation by SiCongLi · 2 years, 10 months ago
  17. 50335fd Remove padding from ClGemmMatrixMultiplyReshapedKernel by Michele Di Giorgio · 2 years, 10 months ago
  18. e920d6a Printing operators parameters, currently for CpuAdd operator only. by Ramy Elgammal · 2 years, 11 months ago
  19. c89998f Fix strict overflow warnings by Michalis Spyrou · 2 years, 10 months ago
  20. 7891a73 Move CPU/GPU files from Core/Runtime to the respective backend folders by Georgios Pinitas · 2 years, 11 months ago
  21. a46c9c9 Sync backend only if allocated rather than supported by Giorgio Arena · 2 years, 10 months ago
  22. 9c67d38 Remove map/unmap overhead for input/output accessor when using DummyAccessor by Giorgio Arena · 2 years, 11 months ago
  23. 87a74ef Re-use auxiliary memory withing CpuWinogradConv2d operators by Georgios Pinitas · 2 years, 11 months ago
  24. 511771f Remove padding from ClScaleKernel by Giorgio Arena · 2 years, 11 months ago
  25. 1988463 Rename [Cl|Cpu]GemmConvolution to [Cl|Gpu]GemmConv2d by Georgios Pinitas · 2 years, 11 months ago
  26. 73df931 Address comments on avoiding releasing weights if used by multiple functions by Giorgio Arena · 2 years, 11 months ago
  27. df5bcb6 Enable fast_math on CpuGemmConvolution by Georgios Pinitas · 2 years, 11 months ago
  28. ebbd529 Update the heuristic to call direct convolution in clConv2d by Gian Marco Iodice · 2 years, 11 months ago
  29. f5d51f3 Retain weights in ClGemm when reconfiguring the operator with retention by Georgios Pinitas · 2 years, 11 months ago
  30. 45fbf9f Avoid releasing weights if they are used by multiple functions by Georgios Pinitas · 2 years, 11 months ago
  31. d4a5bc5 Ensure correct transformed matrices are used in CpuGemmConvolution by Georgios Pinitas · 2 years, 11 months ago
  32. fa1db17 Ensure that correct transformed matrices are used in CpuFullyConnected by Georgios Pinitas · 2 years, 11 months ago
  33. d761a3e Fix performance regression due to clFinish() by Gian Marco Iodice · 2 years, 11 months ago
  34. 288d3cb Fix compiler error in CLActivationLayer by Pablo Marquez Tello · 2 years, 11 months ago
  35. acb4d93 Fix compiler error in GCC 7.4 + Ubuntu 16 by Pablo Marquez Tello · 2 years, 11 months ago
  36. 3f74389 Remove 21.08 deprecated code by Freddie Liardet · 2 years, 11 months ago
  37. 0f6ca4b Report error for unsupported non-constant weights in CpuFullyConnected by Michele Di Giorgio · 2 years, 11 months ago
  38. 6269f87 Fix depthwise convolution assembly kernels by Freddie Liardet · 2 years, 11 months ago
  39. 6634194 Avoid over-allocation of temporary buffers within CpuWinogradConv2d by Georgios Pinitas · 3 years ago
  40. 4164814 Implement Operator API by Georgios Pinitas · 2 years, 11 months ago
  41. 6e90c12 Add missing limits include by Freddie Liardet · 2 years, 11 months ago
  42. ba2dd82 Benchmark and set default LWS for GEMM, Direct convolution and Winograd by Giorgio Arena · 3 years ago
  43. 06d1efd Port CLConvolutionLayer by Sheri Zhang · 3 years ago
  44. 529b5a2 Port ClFullyConnected to new API by Georgios Pinitas · 3 years ago
  45. a0efe69 Reintroduce implementation of NEConvolutionLayer::get_convolution_method by Michele Di Giorgio · 3 years ago
  46. 9a1e28b Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1 by Gian Marco Iodice · 3 years ago
  47. a76e403 Fix A55 performance constant for fp16 hybrid gemm kernel by Georgios Pinitas · 3 years ago
  48. b55f8e8 Port NEConvolutionLayer by Michalis Spyrou · 3 years ago
  49. 8e2f64f Create custom flags for enabling fp16 support by Georgios Pinitas · 3 years ago
  50. a86433a Reduce binary footprint of CpuConvertFullyConnectedWeightsKernel by Michele Di Giorgio · 3 years ago
  51. 120c87b Fix bare metal build issues by Freddie Liardet · 3 years ago
  52. bb5d42c Fix cpu GEMM fp16 issue by Freddie Liardet · 3 years ago
  53. f81f51c Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago
  54. 97426a7 Remove generated kernels that overlap hand-written ones by Georgios Pinitas · 3 years ago
  55. 9805583 Fix memory lifetime issue by Georgios Pinitas · 3 years ago
  56. d87aded Port CLGEMMConvolutionLayer by Manuel Bottini · 3 years ago
  57. 4718706 Dispatch Conv2d using the Direct method when necessary by Georgios Pinitas · 3 years ago
  58. 387f80e Update GEMM assembly performance parameters by Georgios Pinitas · 3 years ago
  59. 5e61cb0 Add missing limits include by Freddie Liardet · 3 years ago
  60. e92c23e Fix allocation of prepare tensor on ClWinogradConv2d by Georgios Pinitas · 3 years ago
  61. 7075fe2 Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago
  62. 22f5ed5 Avoid allocation of auxiliary memory in CpuGemmConvolution by Georgios Pinitas · 3 years ago
  63. 8bd2556 Fix vector_length identification mechanism for SVE by Georgios Pinitas · 3 years ago
  64. d9cdf14 Port NEFullyConnectedLayer to memory injecting interface by Michele Di Giorgio · 3 years ago
  65. a8297fb Pass fast math flag for correct GEMM3D validation support by Georgios Pinitas · 3 years ago
  66. e7012a6 Fix bare metal build error by Freddie Liardet · 3 years ago
  67. 69a9ac4 Expose fast_math mode for GEMM through BFloat16 by Georgios Pinitas · 3 years ago
  68. 1fa27ad Inject temporary tensors to pack in they don't exist in CpuSoftmax by Georgios Pinitas · 3 years ago
  69. f4e84fb Port ClGemmLowp to new API by Georgios Pinitas · 3 years 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 ago
  73. 0f033df Include limits header to fix errors reported by GCC11 by Michele Di Giorgio · 3 years ago
  74. 2b147ee Avoid multiple Rhs matrix transformation on ClGemm by Georgios Pinitas · 3 years ago
  75. d844c08 Port CLIm2ColKernel to ClIm2ColKernel by Manuel Bottini · 3 years ago
  76. 0b27133 Disabled DirectConv method for NCHW and kernel > 15 by Pablo Marquez Tello · 3 years ago
  77. 29599d0 Port NEGEMMConvolutionLayer by Manuel Bottini · 3 years ago
  78. 13ef176 Improve filelist for GPU by Georgios Pinitas · 3 years ago
  79. 7b23732 Port CLCol2ImKernel to ClCol2ImKernel by Manuel Bottini · 3 years ago
  80. c38ca38 Fix CL kernel compilation failure by Michalis Spyrou · 3 years ago
  81. a387e27 Add in-place calculation support for CL elementwise arithmetic kernels by Sheri Zhang · 3 years ago
  82. 96f977e Port NEWinogradConvolutionLayer by Michalis Spyrou · 3 years ago
  83. 04b39e8 Limit the LOOP_UNROLLING on the kernel height by Gian Marco Iodice · 3 years ago
  84. 24b8920 Port NECol2ImKernel by Manuel Bottini · 3 years ago
  85. da81675 Remove redundant implementations of Add/Sub operators by Georgios Pinitas · 3 years ago
  86. 4411e1f Change CLConvolution selection to run Direct approach on large kernels by Georgios Pinitas · 3 years ago
  87. dd23f2a Add LayerData to all nodes by Freddie Liardet · 3 years ago
  88. cfac51c Port NEGEMMLowp Part 2 by Manuel Bottini · 3 years ago
  89. 06ac6e4 Add basic Operator interface by Georgios Pinitas · 3 years ago
  90. 4587594 Validate unsupported data types with runtime information by Georgios Pinitas · 3 years ago
  91. 5e28181 Fix manual LOOP_UNROLLING by Gian Marco Iodice · 3 years ago
  92. 9002899 Port NEIm2ColKernel by Manuel Bottini · 3 years ago
  93. 5ee0d95 Improve implementation selection speed of CpuElementwiseUnary by Georgios Pinitas · 3 years ago
  94. 8155c02 Rework OpenCL Depthwise Convolution by Gian Marco Iodice · 3 years, 3 months ago
  95. 2eb5d16 Align kernel/operator header layout by Georgios Pinitas · 3 years ago
  96. 4dfc553 Port NEGEMM to memory injecting interface (Part 3) by Michele Di Giorgio · 3 years ago
  97. bc4e311 Implement FP GPU depthwise convolution 1x1 kernel for in-place computation by SiCongLi · 3 years ago
  98. 6683165 Add quantization helper functions for OpenCL by Georgios Pinitas · 3 years ago
  99. 2ef59b9 Reduce binary size footprint of CpuGemmInterleave4x4Kernel by Michele Di Giorgio · 3 years ago
  100. f7f6450 Adjust minimum DDK version for manual unroll by Giorgio Arena · 3 years ago