Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / refs/heads/main
  1. f5053f7 Update logic in the OpenMP scheduler to exclude LITTLE cores by Omar Al Khatib · 9 days ago main
  2. 8710385 Fix linking error to fp16_run_dequantization_core() by Ramy Elgammal · 26 hours ago
  3. c0e0128 Fix nightly build error by Pablo Marquez Tello · 2 days ago release_candidate
  4. d3d2e9b Refactor Dequantize to enable FP16 kernel in v8a multi_isa builds by Ramy Elgammal · 3 days ago
  5. 1d8936d Fix nightly build error by Pablo Marquez Tello · 3 days ago
  6. b4b61a6 Rework CpuQuantizeKernel to enable FP16 in multi_isa builds by Ramy Elgammal · 4 days ago
  7. 2217f1e Refactor arm_gemm to enable FP16 in all multi_isa builds by Pablo Marquez Tello · 4 days ago
  8. 21fb2ad Fix ReductionLayer FP16 for armv8a multi_isa builds by Ramy Elgammal · 5 days ago
  9. 4c3f716 Improve CPU extension detection on macos by Viet-Hoa Do · 8 days ago
  10. 05269f0 ScatterND fix for scalar cases by Gunes Bayir · 9 days ago
  11. 48f120c Make quantization rounding consistent by Jonathan Deakin · 10 days ago
  12. c1575b2 Add SME2 implementation of Softmax for QASYMM8 and QASYMM8_SIGNED. by Omar Al Khatib · 4 weeks ago
  13. 2fea135 Add batched indices support to Scatter GPU Implementation by Mohammed Suhail Munshi · 3 weeks ago
  14. c22e126 arm_gemm: fix SVE check on fast mode kernels. by David Mansell · 2 weeks ago
  15. 0c5ba9e Change reorder implementation to be vector length agnostic for OHWIo8 reorder by Radu Salavat · 5 weeks ago
  16. 5c76742 New SME2 heuristics. by David Mansell · 9 weeks ago
  17. 301e33f Add fp16 and integer data type support for ScatterNd in Gpu by Gunes Bayir · 3 weeks ago
  18. e5ef8c1 Disable SME2 Gemmlowp s8f32 kernel selection in case results needs to be accumulated by Gunes Bayir · 3 weeks ago
  19. 499b5bc Disable SME2 Gemm kernel selection in case results needs to be accumulated by Gunes Bayir · 3 weeks ago
  20. ada3200 Add update/index/output (m+1)/2d/(m+n) support for CLScatter by Gunes Bayir · 3 weeks ago
  21. 62d600f Move s32 to f32 conversion in reference layers from quantization to dequantization by Radu Salavat · 5 weeks ago
  22. 2481e95 Add memory stress tests for per channel quantized convolution by Gunes Bayir · 3 weeks ago
  23. 0fa28be Add padding to the shift and multipliers buffers by Pablo Marquez Tello · 3 weeks ago
  24. 575c5f1 Fix compiler error in the validation tests by Pablo Marquez Tello · 4 weeks ago
  25. 0e21236 Multi-Dimensional and Batched Scatter Reference and Dataset Implementation. by Mohammed Suhail Munshi · 6 weeks ago
  26. 7377107 Scatter GPU Kernel Implementation for 1D tensors. by Mohammed Suhail Munshi · 8 weeks ago
  27. 5057ce9 Update documentation for 24.04 release by Michael Kozlov · 4 weeks ago
  28. 83ca105 Fix v7 test failure when core matmul result is dequantized into fp32 by Gunes Bayir · 5 weeks ago
  29. 6ac82a4 fix compilation errors on linux with gcc12 by Sunita Nadampalli · 6 weeks ago
  30. a668f9f Add s8f32 kernels and dynamic QuantizationInfo by Jonathan Deakin · 4 months ago
  31. 34bdffb Add guarding for accumulation validation test in aarch32 by Radu Salavat · 5 weeks ago
  32. 64f2300 Runtime checks for bf16 fixed format tests by David Svantesson-Yeung · 7 weeks ago
  33. cdce25b Accumulation in Cpu Gemm kernels is not supported for quantized kernels in aarch32. This patch guards the relevant tests. by Radu Salavat · 5 weeks ago
  34. cfca87b Add SME2 implementation of softmax for FP16 by Gunes Bayir · 6 weeks ago
  35. f1f1f87 Add in place summation to CPU GEMM kernels by Radu Salavat · 3 months ago
  36. 1322065 Specify absolute tolerance by Sangwon Ha · 6 weeks ago
  37. 553e241 Fix compiler error by Pablo Marquez Tello · 6 weeks ago
  38. 1e91d71 Parallelise im2col along dimensions with higher number of iterations by Milos Puzovic · 7 weeks ago
  39. 77bbe2e Add SME2 implementation of softmax for FP32 by Viet-Hoa Do · 5 months ago
  40. 905786e Added new NEON fixed format fast math mode hybrid kernel with maximum height of 6 for accumulation and updated heuristics by Milos Puzovic · 8 weeks ago
  41. 37d8445 Fix graph examples for WoA by Pablo Marquez Tello · 8 weeks ago
  42. 473b829 Adds Tests and reference implementation for scatter operator with 1D tensors. by Mohammed Suhail Munshi · 9 weeks ago
  43. 4908981 [ONCPUML-1451] Guard bf16 to bf16 tests with ARM_COMPUTE_ENABLE_FIXED_FORMAT_KERNELS by Renato Arantes · 8 weeks ago
  44. 7b3adf2 Fix for nightly build failures for android by Mohammed Suhail Munshi · 8 weeks ago
  45. 6a82787 Workaround to enable cross-compiling from macOS® to Android™ by Jakub Sujak · 8 weeks ago
  46. 8609ca0 Add skeleton for CLScatter op, reference and tests by Mohammed Suhail Munshi · 3 months ago
  47. 36a75da [ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorch® autocast() function by Renato Arantes · 4 months ago
  48. d219115 Make Cpu/Gpu/Ref scalar/vectoral S32 division consistent by Gunes Bayir · 9 weeks ago
  49. 1618e95 Increase tolerance_num of Cpu RNNLayer tests by Gunes Bayir · 9 weeks ago
  50. 43ba0dd Increase MatMul and DilatedConv test Q8 thresholds to 1 by Gunes Bayir · 9 weeks ago
  51. c00a82b Fix overflow in NEMeanStdDevNormalizationKernel by Pablo Marquez Tello · 9 weeks ago
  52. 3e4b193 Fix quant. gemv kernel driver by adding set_quantized_bias() by Gunes Bayir · 9 weeks ago
  53. 5a67733 arm_gemm: Fix bias handling for sme2 FP16 GEMV. by David Mansell · 9 weeks ago
  54. 3ac0b87 Fix validation in pool2d assembly wrapper by Pablo Marquez Tello · 9 weeks ago
  55. 93e743f Optimize CpuSoftmaxKernel for axis != 0 and neon kernels by Omar Al Khatib · 5 months ago
  56. d0611c1 Update documentation for 24.02.1 release by Felix Thomasmathibalan · 2 months ago
  57. 57a8852 Fix WoA nightly failure by Pablo Marquez Tello · 10 weeks ago
  58. 9167c9c Prefer indirect Gemm vs. Direct convolution if supported by Gunes Bayir · 2 months ago
  59. e77736f Set int8 test tolerance in FullyConnected to int8 by Gunes Bayir · 2 months ago
  60. 40af090 Disable FP16 on 32 bit by Pablo Marquez Tello · 2 months ago
  61. bf05373 Fix performance regression in fixed-format kernels by Gunes Bayir · 2 months ago
  62. 6fe9eaf Set Neon™ as present for WoA by Pablo Marquez Tello · 3 months ago
  63. 2676424 Fix segfault in DWC in WoA by Pablo Marquez Tello · 3 months ago
  64. c1787f0 Fix OpenBSD® build failure caused by patch 11144 by Gunes Bayir · 3 months ago
  65. ef63739 Integrate new pretranspose_b_array with extra fused transpose of B by Gunes Bayir · 3 months ago
  66. 0a48c4c Requantization cases for offset changes only by Mohammed Suhail Munshi · 4 months ago
  67. 9469058 Fix linker errors in validation suite for WoA by Pablo Marquez Tello · 3 months ago
  68. 8528134 Fix validation suite on WoA by Pablo Marquez Tello · 3 months ago
  69. e37a863 Fix escape character issues in format_code script by Gunes Bayir · 3 months ago
  70. 7976f08 Fix compiler errors in cl-clang by Pablo Marquez Tello · 3 months ago
  71. 0cba93f [QTest] Use dynamic output quantization in Depthwise Conv tests by Omar Al Khatib · 4 months ago
  72. 8614077 Disable some DirectConv2d tests in Dynamic Fusion by Gunes Bayir · 3 months ago
  73. d98e27e Update documentation for 24.02 release by Felix Thomasmathibalan · 3 months ago
  74. 0c85334 Fix parallel depthwise perf regression from 2db938c by Jonathan Deakin · 3 months ago
  75. 0e73498 Add support for QSYMM8 in ClCastKernel by Pablo Marquez Tello · 3 months ago
  76. 0ee13af Remove CKW prototype and Template Writer by Gunes Bayir · 3 months ago
  77. a3e1b50 Fix the bug in GpuTanh operator in dynamic fusion by Gunes Bayir · 3 months ago
  78. a5a81ae Mark GpuSoftmax and GpuReshape as not supported by Gunes Bayir · 3 months ago
  79. 2db938c Parallelize CPU depthwise over batch if only 1 row by Jonathan Deakin · 3 months ago
  80. e695579 arm_gemm: SME: Remove artificial single-thread constraint on quantized int8 kernels. by David Mansell · 4 months ago
  81. 1561d40 Build CKW by default by Gunes Bayir · 3 months ago
  82. 9d8f4ed Fix compilation issue in CKW due to unused variable by Gunes Bayir · 3 months ago
  83. 9e987b1 Fix path by Jakub Sujak · 3 months ago
  84. 8050d22 Disable FP16 tests compilation on Multi-Isa v8a by Mohammed Suhail Munshi · 3 months ago
  85. 0c17c4b Fix leftover cols in CpuGemmLowpMatrixBReductionKernel by Jonathan Deakin · 4 months ago
  86. 9b72a6c Add scripts to generate Doxygen documentation by Jakub Sujak · 6 months ago
  87. 2b9fa59 Use the stable CKW API in the GPU dynamic fusion backend by Gunes Bayir · 4 months ago
  88. 7ab7fca Fix logic in SConscript by Jakub Sujak · 4 months ago
  89. b5d6082 Add build options for Address and UndefinedBehavior sanitizers by Jakub Sujak · 4 months ago
  90. ec89b91 Fix multi_isa build for arch=arm64-v8a by Pablo Marquez Tello · 4 months ago
  91. fb92e22 arm_gemm: convolution: optimize convolver.hpp. by David Mansell · 6 months ago
  92. 2aec5f1 Fix tolerance issue in BF16 MatMul tests by Gunes Bayir · 4 months ago
  93. 277def4 Fix Debug mode in CMake by Jonathan Deakin · 4 months ago
  94. bde6e78 Fix for Logically dead code detected in Coverity checks by Anitha Raj · 4 months ago
  95. e8e016e Fix for unchecked return value detected in Coverity checks. by Anitha Raj · 4 months ago
  96. fdf56fb Make GpuWorkloadContext own all tensor info objects by Viet-Hoa Do · 4 months ago
  97. e812c0c Don't build CKW as part of Android.bp by Jakub Sujak · 4 months ago
  98. 3a704ae Update Documentation for 24.01 release by Felix Thomasmathibalan · 4 months ago
  99. c7f550d Improved documentation by Pablo Marquez Tello · 4 months ago
  100. 6829e02 Fix divide-by-zero compilation error by Viet-Hoa Do · 4 months ago