Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / f3dfa279d536906dac3e618244b2c1d33e5ff28a / src / runtime
  1. f3dfa27 COMPMID-632 Assembly: Integrate gemmlowp assembly version by Michalis Spyrou · 7 years ago
  2. b7b3153 COMPMID-464 Implement Depthwise separable convolution on NEON by Michalis Spyrou · 7 years ago
  3. 02bf80d COMPMID-661: Fix scale border issue (#38) by Daniil Efremov · 7 years ago
  4. ee8be2d COMPMID-556: Set CLSoftmaxLayer temp buffers to resizable. by Georgios Pinitas · 7 years ago
  5. 4d55e0a COMPMID-677: Integrate HGEMM assembly kernel (generic CPUs) by Pablo Tello · 7 years ago
  6. a3b1b46 COMPMID-667: Add validation static method to NEON GEMMlowp by Georgios Pinitas · 7 years ago
  7. 37908d9 COMPMID-560 - Validation mismatches Gaussian Pyramid Half Scale by Gian Marco · 7 years ago
  8. 6b77e91 COMPMID-665 - NEON: Add QASYMM8 in place Activation layer by Gian Marco · 7 years ago
  9. 30902ed COMPMID-617: Add validation methods to ML CL functions. by Georgios Pinitas · 7 years ago
  10. 3e80c7f COMPMID-661: Optimize FC layer with 2 new Bifrost kernels and LWS tuning (#33) by Anton Lokhmotov · 7 years ago
  11. d7295b7 COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3x3 kernel (#28) by Dmitry Savenko · 7 years ago
  12. 181e651 COMPMID-675: NEGEMMLowp Assembly Integration by Pablo Tello · 7 years ago
  13. 82afedf COMPMID-678 Align Convolution Interfaces by Giorgio Arena · 7 years ago
  14. 6681d24 COMPMID-675 - Fixed mismatches in GEMMLowpMatrixMultiplyKernel dotproduct path by Pablo Tello · 7 years ago
  15. e75a02b COMPMID-675 - Reworked NEGEMMLowp interface/function by Gian Marco · 7 years ago
  16. 84b51ad COMPMID-666: Adds the ability to import backing memory in a Tensor(CPU). by Georgios Pinitas · 7 years ago
  17. f450caa COMPMID-661: softmax-uint8 implementation (#16) by Chunosov · 7 years ago
  18. 7068f99 COMPMID-631: Merge branches/gles_compute branch by Anthony Barbier · 7 years ago
  19. af6204c COMPMID-661: Add avgpool-uint8 support. Optimize avgpool-fp32 for Bifrost. (#13) by Anton Lokhmotov · 7 years ago
  20. f9d3a0a COMPMID-617: Add validation functions. by Georgios Pinitas · 7 years ago
  21. d6afedc COMPMID-661: softmax-fp32 optimisation (#14) by Chunosov · 7 years ago
  22. 6ff12a0 COMPMID-662: Integrated the new a64_s8_gemm_12x8 + dot product kernel into ACL. by Pablo Tello · 7 years ago
  23. 3faea25 COMPMID-617: Adds validation to CLPoolingLayer by Georgios Pinitas · 7 years ago
  24. ab18212 COMPMID-616 - Optimizing GEMMLowp on NEON intrinsics by Gian Marco Iodice · 7 years ago
  25. 7362f0d COMPMID-464 Implement Depthwise convolution 3x3 on NEON by Michalis Spyrou · 7 years ago
  26. 3c5f949 COMPMID-575: Port Magnitude to new validation by John Richardson · 7 years ago
  27. 0063380 IVGCVSW-619: Support for Cl u8 bounded Relu by Michel Iwaniec · 7 years ago
  28. 63e5041 COMPMID-576: Port Phase to new validation by John Richardson · 7 years ago
  29. 5cbd20f COMPMID-556: Autoconfigure support in CLDepthwiseConvolution. by Georgios Pinitas · 7 years ago
  30. 33fd07b COMPMID-634: Enable clang with libc++ to compile for Android (32 and 64 bits) by Ioan-Cristian Szabo · 7 years ago
  31. 81a26ad COMPMID-643: Add bias to CLDepthwiseConvolution. by Georgios Pinitas · 7 years ago
  32. 511347a COMPMID-485: Offset-based memory manager support. by Georgios Pinitas · 7 years ago
  33. 96880cf COMPMID-640: FullyConnectedLayer failures on both NEON/CL by Georgios Pinitas · 7 years ago
  34. 960ccc4 COMPMID-556: Disable GEMMLowp tests until we've got the intrinsics version merged by Anthony Barbier · 7 years ago
  35. a1ed41f IVGCVSW-601: support for asymetric padding in cl conv and depthwise conv by Jaroslaw Rzepecki · 7 years ago
  36. 48a60f9 IVGCVSW-632 CL support for Softmax beta parameter by Pablo Palmier · 7 years ago
  37. bf2fb95 COMPMID-481: Add gemmlowp_aarch64_v8p4 kernel. by Pablo Tello · 7 years ago
  38. f5f34bb COMPMID-470: Neon Deconvolution. by Pablo Tello · 7 years ago
  39. 4bd9fda COMPMID-603: Fix OMPScheduler. by Georgios Pinitas · 7 years ago
  40. ece307b COMPMID-556 - Fix ConvolutionLayer test by Gian Marco Iodice · 7 years ago
  41. 1682430 COMPMID-463 - Extended Pooling Layer on NEON to support Global Pooling by Gian Marco Iodice · 7 years ago
  42. 7ce53c6 COMPMID-546 Add auto config to depth concatenate by steniu01 · 7 years ago
  43. b2881fc COMPMID-417 Updated build system to not combined objects of the different levels of library by Anthony Barbier · 7 years ago
  44. 490bf2e COMPMID-417 Fix bare metal build for armv7a by Michalis Spyrou · 7 years ago
  45. 3c2c433 COMPMID-417 - Added NEFlattenLayer function by Gian Marco Iodice · 7 years ago
  46. 1b2e2e5 COMPMID-417: Fix memory manager in NEConvolution. by Georgios Pinitas · 7 years ago
  47. 77497d7 COMPMID-417 - Fix for the config_id default string by Gian Marco Iodice · 7 years ago
  48. 80373f6 COMPMID-481: Add AArch32 GEMM by Moritz Pflanzer · 7 years ago
  49. beabe3b COMPMID-481: Add AArch64 GEMM by Moritz Pflanzer · 7 years ago
  50. de691f0 COMPMID-524 - Implemented CLTuner object by Gian Marco · 7 years ago
  51. 4726fdf COMPMID-541: Fix padding in CLMinMaxLocationKernel by Moritz Pflanzer · 7 years ago
  52. 2fd5d95 COMPMID-417: Fix CPPScheduler for empty windows by Moritz Pflanzer · 7 years ago
  53. 6a3e976 COMPMID-417: Fix memory manager in NEDirectConvolution. by Georgios Pinitas · 7 years ago
  54. d9e5b19 COMPMID-417: Fix in BlobMemoryPool and BlobLifetimeManager by Georgios Pinitas · 7 years ago
  55. 5701e2a COMPMID-534: Port MemoryManager to CL functions (Images) by Georgios Pinitas · 7 years ago
  56. 9fe4144 COMPMID-452 CL Generic Depthwise Convolution implementation. by Giorgio Arena · 7 years ago
  57. bf17955 COMPMID-522 - Added support for GlobalPooling in CLPoolingLayer and CLFlattening for 3D tensor by Gian Marco Iodice · 7 years ago
  58. 583137c COMPMID-417: Add support for floats in scale. by Georgios Pinitas · 7 years ago
  59. 3021edf COMPMID-417: Fix NEGaussianPyramidOrb. by Georgios Pinitas · 7 years ago
  60. d910ffa COMPMID-534: Port MemoryManager to NEON functions (Images) by Georgios Pinitas · 7 years ago
  61. aec513c COMPMID-417: Fix potential memory leak in CLReduction Kernel. by Georgios Pinitas · 7 years ago
  62. 8a94e7c COMPMID-534: Add MemoryManager support in OpenCL functions by Georgios Pinitas · 7 years ago
  63. 658039b COMPMID-534: Add MemoryManager support in NEON functions by Georgios Pinitas · 7 years ago
  64. 51db22c COMPMID-417: Remove unused include by Moritz Pflanzer · 7 years ago
  65. ff06f20 COMPMID-417: Cleanup CPPScheduler by Moritz Pflanzer · 7 years ago
  66. 5ee66ea COMPMID-462: Implement TensorReshape for NEON and CL. by Georgios Pinitas · 7 years ago
  67. 56dd726 COMPMID-448: Implement CL Quantization/Dequantization Layer. by Michele Di Giorgio · 7 years ago
  68. baf174e COMPMID-485: Memory Manager by Georgios Pinitas · 7 years ago
  69. 06b184a COMPMID-439 - Refactored NEQuantizationLayer and NEQuantizationLayer in order to support 3D input tensors by Gian Marco Iodice · 7 years ago
  70. ba0f8dd COMPMID-417: Fix thread allocation in CPPScheduler by Moritz Pflanzer · 7 years ago
  71. c186b57 COMPMID-481: Add thread info parameter by Moritz Pflanzer · 7 years ago
  72. f4af76e COMPMID-417: Fix clang tidy after renaming by Moritz Pflanzer · 7 years ago
  73. 04f089c COMPMID-476 L2 Normalization for CL by Michalis Spyrou · 7 years ago
  74. 3e36369 COMPMID-358 Implement OpenCL ROI Pooling by SiCong Li · 7 years ago
  75. edfa9f4 COMPMID-477 - Optimized batched case in CLConvolutionLayer by Gian Marco Iodice · 7 years ago
  76. 32982d8 COMPMID-439: Implement NEON Dequantization Layer. by Michele Di Giorgio · 7 years ago
  77. 93a690e COMPMID-452 CL Depthwise Separable Convolution Layer kernel implementation, validation and benchmarking for 3x3xC depthwise filter and DataType::F32. by Giorgio Arena · 7 years ago
  78. d60a6b9 COMPMID-477 - Optimized CLNormalizationLayer by Gian Marco Iodice · 7 years ago
  79. 4e09b38 COMPMID-439: Implement NEON Quantization Layer. by Michele Di Giorgio · 7 years ago
  80. 484e7b3 COMPMID-417: Cleanup NEON FullyConnectedLayer by Moritz Pflanzer · 7 years ago
  81. 768e9f1 COMPMID-417: Cleanup CL FullyConnectedLayer by Moritz Pflanzer · 7 years ago
  82. 1246b63 COMPMID-477 - Optimized Direct Convolution 3x3 and 5x5 (f32) for Bifrost. by Gian Marco Iodice · 7 years ago
  83. 409ee0a COMPMID-417: Add in-place support for batch-normalization. by Georgios Pinitas · 7 years ago
  84. fc2817d COMPMID-424 NEON/CL Harris Corners validation tests. by Giorgio Arena · 7 years ago
  85. 5cb4d6a COMPMID-477 - Optimizing CLDirectConvolution 3x3 on OpenCL and added the auto configuration by Gian Marco Iodice · 7 years ago
  86. 559d771 COMPMID-417 - Fixed auto-config in NEConvolutionLayer and in CLConvolutionLayer by Gian Marco Iodice · 7 years ago
  87. d976958 COMPMID-: Implement L2NormalizationLayer. by Georgios Pinitas · 7 years ago
  88. d8e765b COMPMID-472 : Implement Floor for CL and NEON. by Georgios Pinitas · 7 years ago
  89. a261181 COMPMID-417 NEON/CL MeanStdDev bugfix using FillBorderKernel by Giorgio Arena · 7 years ago
  90. ef4b4ae COMPMID-438: Add support for floating point Min-Max Location layer. by Michele Di Giorgio · 7 years ago
  91. f87cc7f COMPMID-417: Port NEDirectConvolution 1x1 to QS16. by Pablo Tello · 7 years ago
  92. 6c92834 COMPMID-413: Add support for QS8 and QS16 CLNormalizationLayer. by Michele Di Giorgio · 7 years ago
  93. 27b386c COMPMID-355 Implement 3x3 CL direct convolution by steniu01 · 7 years ago
  94. b49a715 COMPMID-421: Added FP16 support to Softmax. by Pablo Tello · 7 years ago
  95. 0d17614 COMPMID-421: Added FP16 support to the NEON Direct Convolution function. by Pablo Tello · 7 years ago
  96. d929b9c COMPMID-417: Enable CPU target selection by Moritz Pflanzer · 7 years ago
  97. e222941 COMPMID-401: Implement FixedPointPosition conversion for NEON. by Georgios Pinitas · 7 years ago
  98. ac4e873 COMPMID-417: Port DepthConcatenate to QS8/QS16 for NEON/CL. by Georgios Pinitas · 7 years ago
  99. 3470247 COMPMID-417 Checking CL non uniform support at runtime. by steniu01 · 7 years ago
  100. 9247c92 COMPMID-428: Port NESoftmaxLayer to 16-bit fixed point. by Georgios Pinitas · 7 years ago