Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 6ea2a42bfe2bcc8745d2fcc567f9b9bd7c593834
  1. 6ea2a42 COMPMID-2939 Keep benchmark_examples and validate_examples by SiCong Li · 4 years, 7 months ago
  2. 3e84bb6 COMPMID-2920: NEInstanceNormalization fails on NHWC validations by Manuel Bottini · 4 years, 8 months ago
  3. 5f7dda6 COMPMID-2929: Resolve segfault at end of benchmark suite execution. by Georgios Pinitas · 4 years, 7 months ago
  4. c16b30c COMPMID-2916 19.11 Release checklist by SiCong Li · 4 years, 7 months ago
  5. 09471fa COMPMID-2853: Fix VGG16 for fp16. by Georgios Pinitas · 4 years, 8 months ago
  6. 002cbd3 COMPMID-2919 add error message for zero stride values by Sang-Hoon Park · 4 years, 8 months ago
  7. f49b8eb COMPMID-2924:Remove proprietary header by Giuseppe Rossini · 4 years, 8 months ago
  8. 951b8a4 COMPMID-2309 : CLConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters by Vidhya Sudhan Loganathan · 4 years, 8 months ago
  9. cd4e9ab COMPMID-2452: Add mnist example by Isabella Gottardi · 4 years, 8 months ago
  10. ee8cf32 COMPMID-2905: Fixed benchmark graph segfault. by Pablo Tello · 4 years, 8 months ago
  11. 7a669a8 COMPMID-2921 Performance regression on NEON Int8 by Giorgio Arena · 4 years, 8 months ago
  12. 2dab2e9 COMPMID-2139: Update documentation about memory manager by Michalis Spyrou · 4 years, 8 months ago
  13. af724e7 COMPMID-2897 CL LogSoftmax QASYMM8 pre-commit tests are intermittently failing by Giorgio Arena · 4 years, 8 months ago
  14. 7b12bfb COMPMID-1730: Document best practices by Michele Di Giorgio · 4 years, 8 months ago
  15. 8217c8e COMPMID-2895: Remove QASYMM8_PER_CHANNEL data type by Georgios Pinitas · 4 years, 8 months ago
  16. 94e0cf9 COMPMID-2690 Extend Doxygen documents to include GEMM Tuner by SiCong Li · 4 years, 8 months ago
  17. 5dea19e COMPMID-2579: Fuse batch normalization with convolution and depthwise convolution at graph level on NEON by Gian Marco Iodice · 4 years, 8 months ago
  18. eaa01ab COMPMID-2671 use Signed32 for default output data type of ArgMinMax by Sang-Hoon Park · 4 years, 8 months ago
  19. 75041a1 COMPMID-2563 Change how the best overall GEMM configuration is selected by SiCong Li · 4 years, 8 months ago
  20. 77d4252 COMPMID-2853: VGG16 regression for fp32 by Georgios Pinitas · 4 years, 8 months ago
  21. 9aaf09e COMPMID-2452: Fix meta-data override issue in DynamicTensor test by Georgios Pinitas · 4 years, 8 months ago
  22. 11b0b8a COMPMID-2672: add comments for GEMM helper macros by Sang-Hoon Park · 4 years, 8 months ago
  23. 63d4dbd COMPMID-2452: Fix 32-bit per-channel convolution for NEON. by Georgios Pinitas · 4 years, 8 months ago
  24. 15396ff COMPMID-2892: [CL] use int accumulator for quantized MxN DWC by Sang-Hoon Park · 4 years, 8 months ago
  25. 5264b7d COMPMID-2576: Fuse activation in Winograd output transform. by Pablo Tello · 4 years, 8 months ago
  26. 68adf44 COMPMID-2893: Bare-metal build failures by Georgios Pinitas · 4 years, 8 months ago
  27. dbdea0d COMPMID-2308: NEConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters by Georgios Pinitas · 4 years, 8 months ago
  28. 75d4733 COMPMID-2138: Create safe math integer functions by Michalis Spyrou · 4 years, 8 months ago
  29. 3252795 COMPMID-2106: Extend get_input_accessor() to run input images through QASYMM8 networks by Manuel Bottini · 4 years, 8 months ago
  30. 0fc2d7a COMPMID-2862: remove forward declaration of ReductionOperation by Sang-Hoon Park · 4 years, 8 months ago
  31. 7ae80a9 COMPMID-2549: Add GLES Runtime Context interfaces. by Georgios Pinitas · 4 years, 8 months ago
  32. bfd75d6 COMPMID-2672: add comments for OpenCL helper macros by Sang-Hoon Park · 4 years, 8 months ago
  33. 62eeb53 COMPMID-2266: [CL] add support for Log Softmax by Sang-Hoon Park · 4 years, 8 months ago
  34. 44bfc3f COMPMID-1671: Allow fp mixed precision in CLFCLayer. by Georgios Pinitas · 4 years, 8 months ago
  35. 2697fd8 COMPMID-2707: add keep_dims parameter to Reduction Operation by Sang-Hoon Park · 4 years, 9 months ago
  36. df4cf57 COMPMID-2306: CLDepthwiseConvolution: support for QUANT8_PER_CHANNEL_SYMM by Michele Di Giorgio · 4 years, 9 months ago
  37. 8b72199 COMPMID-1889: Fuse bias addition and output stage in CLFCLayer. by Georgios Pinitas · 4 years, 8 months ago
  38. fde0914 MLCE-146: VTS failures A55 by Pablo Tello · 4 years, 8 months ago
  39. d985378 COMPMID-2588: Optimize the output detection kernel required by MobileNet-SSD (~27% improvement) by Giuseppe Rossini · 4 years, 8 months ago
  40. 279814b COMPMID-2481: Add InputQuantizationInfo!=OutputQuantization Info tests for DeconvolutionLayer by Manuel Bottini · 4 years, 8 months ago
  41. 7736389 COMPMID-2452: (3RDPARTY_UPDATE) Internal benchmark fixes by Georgios Pinitas · 4 years, 8 months ago
  42. 0726398 COMPMID-2501: Support multiplier > 1 during QASYMM8 requantization for Quantized LSTM by Manuel Bottini · 4 years, 8 months ago
  43. 05069f0 COMPMID-2515: Merge optimized depthwise convolution to the generic depthwise convolution function by Manuel Bottini · 4 years, 9 months ago
  44. e36b526 COMPMID-2567: Create a python script to parse the CLGEMM benchmarks and by SiCong Li · 4 years, 9 months ago
  45. 48b3ef8 COMPMID-2577: Fuse bias addition and activation in gemm assembly kernels by Georgios Pinitas · 4 years, 9 months ago
  46. 1dce310 COMPMID-2452: Fix CLDepthwiseConvolutionLayerNativeKernel by Michele Di Giorgio · 4 years, 8 months ago
  47. 314598f COMPMID-2486: Fix bare arm64-v8.2-a builds by Michalis Spyrou · 4 years, 8 months ago
  48. d93e263 COMPMID-2708 NEDepthwiseConvolution Generic: support for QUANT8_PER_CHANNEL_SYMM by Giorgio Arena · 4 years, 9 months ago
  49. ab5b1a2 COMPMID-2744 [CL] add support for 9x9 quantized direct convolution by Sang-Hoon Park · 4 years, 9 months ago
  50. 422da26 COMPMID-2452: Update documentation for Weights Manager by Michalis Spyrou · 4 years, 8 months ago
  51. 45ce566 COMPMID-2209: Update documentation for RuntimeContext. by Georgios Pinitas · 4 years, 8 months ago
  52. 84dca2d COMPMID-2486: Fix bare metal builds by Michalis Spyrou · 4 years, 8 months ago
  53. 34f88dd Revert "COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAX" by Manuel Bottini · 4 years, 8 months ago
  54. 662e5a4 Revert "COMPMID-2742: [CL] ArgMinMax clCreateKernel error" by Manuel Bottini · 4 years, 8 months ago
  55. fae513c COMPMID-2486: Remove/add disabled compiler warnings by Michalis Spyrou · 4 years, 8 months ago
  56. ebaddb6 COMPMID-2452: fixed linker error when cppscheduler=0 by Pablo Tello · 4 years, 8 months ago
  57. 3f8cc58 COMPMID-2813: Update the heuristic in CLDepthWiseConvolutionLayer by Gian Marco Iodice · 4 years, 9 months ago
  58. 1af089c COMPMID-2452: NEInstanceNormalization test tolerance fix by Manuel Bottini · 4 years, 8 months ago
  59. c69371a COMPMID-2452: Change names for internal benchmarks by Georgios Pinitas · 4 years, 9 months ago
  60. d24affe COMPMID-2265 add support for Log Softmax to NEON by Sang-Hoon Park · 4 years, 9 months ago
  61. 7c60c99 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  62. a07ce15 COMPMID-2741: [CL] GEMMMatrixMultiplyReshaped clCreateKernel Error by Georgios Pinitas · 4 years, 9 months ago
  63. db8485a COMPMID-2205: CL runtime context. by Pablo Tello · 4 years, 9 months ago
  64. a046e16 COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM8 NHWC by Michele Di Giorgio · 4 years, 9 months ago
  65. 76c996f COMPMID-2742: [CL] ArgMinMax clCreateKernel error by Manuel Bottini · 4 years, 9 months ago
  66. ee0f6cc COMPMID-2743: Mark 9x9 quantized direct convolutions as unsupported in CL by Georgios Pinitas · 4 years, 9 months ago
  67. 3d426c5 COMPMID-2697: Dynamic Tensors Type2 test case by Georgios Pinitas · 4 years, 9 months ago
  68. df2c721 COMPMID-2452: Remove unnecessary checks from CLWinogradOutputTransformKernel by Michele Di Giorgio · 4 years, 9 months ago
  69. 633d30b COMPMID-2306: CLDepthwiseConvolution: support for QUANT8_PER_CHANNEL_SYMM - Reference by Michele Di Giorgio · 4 years, 9 months ago
  70. f882901 COMPMID-2452: Change names for internal benchmarks by Georgios Pinitas · 4 years, 9 months ago
  71. 6bff195 COMPMID-2486: Remove disabled compiler warnings by Michalis Spyrou · 4 years, 9 months ago
  72. 6665f82 COMPMID-2452: Mismatches FP16 in CL InstanceNormalization by Manuel Bottini · 4 years, 9 months ago
  73. cce2ea6 COMPMID-2687: Update doc for thread-safety by Georgios Pinitas · 4 years, 9 months ago
  74. 0d54804 COMPMID-2572: Update the heuristic in CLGEMM for FP16 by Gian Marco Iodice · 4 years, 9 months ago
  75. bd18811 COMPMID-2103: Use substreams for sharing weights in the DeepSpeech example by Michalis Spyrou · 4 years, 9 months ago
  76. 36debd4 COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAX by Manuel Bottini · 5 years ago
  77. b27e13a COMPMID-2685: [CL] Use Weights manager by Michalis Spyrou · 4 years, 9 months ago
  78. 2ff0009 COMPMID-2661: Implement complex function dynamic tensor support. by Georgios Pinitas · 4 years, 9 months ago
  79. 58c71ef COMPMID-2257: Add support for QASYMM8 in NEGenerateProposals by Michele Di Giorgio · 4 years, 9 months ago
  80. d64a46c COMPMID-2699: Add support for QASYMM16 in NEQuantizationLayer by Michele Di Giorgio · 4 years, 9 months ago
  81. 79f88e6 COMPMID-2313: Implement CL INSTANCE_NORMALIZATION function by Manuel Bottini · 4 years, 9 months ago
  82. 20c2b50 COMPMID-2693 Weights manager to mark the initial weights as unsued by Michalis Spyrou · 4 years, 9 months ago
  83. b94c368 COMPMID-2645: Detection Post-Process fixes by Georgios Pinitas · 4 years, 9 months ago
  84. 3d8fe49 INFPRF-609:Performance Issue of the Latest ArmCL by giuros01 · 4 years, 9 months ago
  85. 2aa7fd0 COMPMID-2601 [CL] add mixed precision support to PoolingLayer by Sang-Hoon Park · 4 years, 9 months ago
  86. 5c4a8e9 COMPMID-2592 Create a new kernel for CLPad with SYMMETRIC and REFLECT mode by Giorgio Arena · 4 years, 10 months ago
  87. 04ea4e8 COMPMID-2581: Fuse batch normalization with convolution and depthwise convolution at graph level for OpenCL - FP16 by giuros01 · 4 years, 9 months ago
  88. ae0fc86 COMPMID-2452: Dot product optimizations on merge/transforms by Georgios Pinitas · 4 years, 9 months ago
  89. 9637b2e COMPMID-2671: Change ArgMinMax NEON/CL output type to Signed32 by Michele Di Giorgio · 4 years, 9 months ago
  90. cecb0a7 COMPMID-2637 [CL] fix broadcast pixel-wise multiplication with 5D tensors by Sang-Hoon Park · 4 years, 9 months ago
  91. 879d131 COMPMID-2452: Fix compilation issues on armclang by Georgios Pinitas · 4 years, 9 months ago
  92. ea80348 COMPMID-2564 - Add CLGEMMNative example by SiCong Li · 4 years, 9 months ago
  93. 0c17aa2 COMPMID-2571: Add mixed-precision support in CLGEMMReshaped for FP16 by Gian Marco Iodice · 4 years, 9 months ago
  94. 40958ad COMPMID-2663: Interface to unbound mappings. by Georgios Pinitas · 4 years, 9 months ago
  95. bc166d5 COMPMID-2565 - Add CLGEMMReshaped example by SiCong Li · 4 years, 9 months ago
  96. 6b612f5 COMPMID-2310: CLGenerateProposalsLayer: support for QASYMM8 by Michele Di Giorgio · 4 years, 10 months ago
  97. 240b79d COMPMID-2692 Use existing command line infrastructure for CLGEMMReshapedOnlyRHS by SiCong Li · 4 years, 9 months ago
  98. bc88c62 COMPMID-2452: Replace DOT assemble macro with the corresponding word directives. by Georgios Pinitas · 4 years, 9 months ago
  99. dc200dc COMPMID-2452 Fix precommit tests by Michalis Spyrou · 4 years, 9 months ago
  100. 05639f6 COMPMID-2571: Add support for FP16 in CLGEMMReshaped - part 1 by Gian Marco Iodice · 4 years, 9 months ago