Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / refs/heads/branches/arm_compute_24_04 / src / runtime
  1. 473b829 Adds Tests and reference implementation for scatter operator with 1D tensors. by Mohammed Suhail Munshi · 4 months ago
  2. 8609ca0 Add skeleton for CLScatter op, reference and tests by Mohammed Suhail Munshi · 5 months ago
  3. 5d7a93a Fix compilation error on GCC 13.2 by Jakub Sujak · 7 months ago
  4. 85cafff Add Mali™-G720 and Mali™-G620 as GpuTargets by Gunes Bayir · 7 months ago
  5. 4737094 Optimize CPU depth-to-space by Viet-Hoa Do · 9 months ago
  6. 17e116e Revert "thread_local _custom_scheduler" by Pablo Marquez Tello · 8 months ago
  7. fadc9b1 Optimize CpuSoftmaxKernel for axis=0 by Gunes Bayir · 9 months ago
  8. ded5b18 thread_local _custom_scheduler by David Svantesson · 12 months ago
  9. d4650e9 Fix various coverity issues by SiCong Li · 9 months ago
  10. 4a9dbed Update heuristic for MatMul Native U8 by Gian Marco Iodice · 9 months ago
  11. 704c22f [GPU] Update Reverse layer to allow negative axis and reversed axis order by Adnan AlSinan · 9 months ago
  12. 72b7471 Add check to disable dynamic bias with quantized datatypes in Conv2D layer by Mohammed Suhail Munshi · 10 months ago
  13. c1204c7 Connect MatMul MMUL kernels to ClMatMul operator by Gunes Bayir · 10 months ago
  14. 0b72aa4 Optimize NEStackLayer by Gunes Bayir · 10 months ago
  15. 1434155 Change heuristics for FP16 Deconv by Sangwon Ha · 10 months ago
  16. 745153b NEDeconvolutionLayer validation fix by Pablo Marquez Tello · 10 months ago
  17. afd38f0 Apply clang-format on repository by Felix Thomasmathibalan · 10 months ago
  18. bdcb4c1 Implement tflite compliant reverse for CPU by Adnan AlSinan · 10 months ago
  19. 729099c Enable job-chaining with incremental job_chaining_size. by Anitha Raj · 10 months ago
  20. 0d27b2e Remove legacy PostOps code by Jakub Sujak · 11 months ago
  21. 7d91c61 Fix out-of-scope CLBufferMemoryRegion's buffer still in queue issue by SiCong Li · 12 months ago
  22. 29e27b0 Add support for S64 output in NEArgMinMaxLayer by Pablo Marquez Tello · 12 months ago
  23. 4f76a00 Fix ReduceMean validate issue by Viet-Hoa Do · 12 months ago
  24. 9129549 Retain back-compatibility for arm_compute/core/Types.h by SiCong Li · 1 year ago
  25. 0a59e69 Fix problem with exception handling in CPPScheduler by Matthew Bentham · 1 year ago
  26. 8dfb882 Enable S64 output in CLArgMinMax by Pablo Marquez Tello · 1 year, 1 month ago
  27. 314d3e2 Break up core/Utils.h to reduce unused code being included everywhere by Matthew Bentham · 1 year, 1 month ago
  28. a359ee9 Fix excessive calls to clReleaseCommandQueue by SiCong Li · 1 year, 3 months ago
  29. 8e2dede Add Bias to MatMul Kernels and add support for use in Fully Connected Layer by Mohammed Suhail Munshi · 1 year, 1 month ago
  30. 1d06204 Do not include headers necessary for logging when logging is disabled by Matthew Bentham · 1 year, 1 month ago
  31. 019a7d9 Enable transpose convolution with non-square kernels by Viet-Hoa Do · 1 year, 1 month ago
  32. 9b392d7 Rewrote CLArgMinMax for axis 0 by Pablo Marquez Tello · 1 year, 1 month ago
  33. a2bb80e Use MatMul in fully connected layer with dynamic weights when supported by Mohammed Suhail Munshi · 1 year, 1 month ago
  34. 94abde4 Add Fused Activation to OpenCL MatMul by Mohammed Suhail Munshi · 1 year, 2 months ago
  35. f1aeab9 Break up arm_compute/core/Types.h a bit by Matthew Bentham · 1 year, 2 months ago
  36. 54b41a3 Reorder destructor in src by David Svantesson · 1 year, 2 months ago
  37. 56fabba Fix performance regression in FP16 Deconvolution by Jakub Sujak · 1 year, 3 months ago
  38. ed9eb30 Remove check for bias in CPU Depthwise Convolution by Jakub Sujak · 1 year, 3 months ago
  39. 318782b Remove inclusion of NEReorderKernel header from NEReorderLayer by Ramy Elgammal · 1 year, 3 months ago
  40. a8db612 Re-enable dyanmic weights in Neon™ depthwise convolution by Ramy Elgammal · 1 year, 3 months ago
  41. edafe7f Disable dynamic weights in unsupported operators by Viet-Hoa Do · 1 year, 3 months ago
  42. 76e7b63 Make NECast::validate take args by const pointer by Matthew Bentham · 1 year, 3 months ago
  43. 352c07d Implement OpenCL MatMul heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 3 months ago
  44. cd8b40d Guards to make NEReorder aarch64 only by David Svantesson · 1 year, 3 months ago
  45. 7a0f1bd Add fp16 GeMM heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 3 months ago
  46. f0ff76d Add Reorder to changelog by David Svantesson · 1 year, 3 months ago
  47. 3b162e5 Reorder added by David Svantesson · 1 year, 4 months ago
  48. eaae899 Fix OMPScheduler run_workloads single thread issue by SiCong Li · 1 year, 3 months ago
  49. f16eed9 Change fp16 GeMM heuristic for Arm® Mali™-G77 by Gian Marco Iodice · 1 year, 3 months ago
  50. dba672c Integrate multi-threaded pretranspose_B_array by SiCong Li · 1 year, 4 months ago
  51. 9b0a6b4 Fix dynamic weights for CPU connected layer by Viet-Hoa Do · 1 year, 4 months ago
  52. a1b1e41 Implement MatMul Function and Operator with Floating Point support for CPU by Mohammed Suhail Munshi · 1 year, 4 months ago
  53. 617ed50 Support dynamic weights for Fully Connected layers on GPU by Jakub Sujak · 1 year, 4 months ago
  54. f26ea2f Implement MatMul Function by Ramy Elgammal · 1 year, 4 months ago
  55. fff9a4c Add Cropping to CLBatchToSpace by Omar Al Khatib · 1 year, 4 months ago
  56. 8893e45 Add cropping support to NEBatchToSpace by SiCong Li · 1 year, 4 months ago
  57. a3e57c2 Add dynamic weights for CPU fully connected layer by Viet-Hoa Do · 1 year, 5 months ago
  58. 4ceb453 Add CropInfo to BatchToSpace reference and fixture by SiCong Li · 1 year, 5 months ago
  59. 47f177e Fix LWS search space used by CLTuner by SiCong Li · 1 year, 5 months ago
  60. adfcacc Add weights_info as optional input for NEDeconvolutionLayer by Annop Wongwathanarat · 1 year, 5 months ago
  61. c4ed2fd Extend skip upsampling for deconvolution for non-1x1 kernels by Annop Wongwathanarat · 1 year, 6 months ago
  62. 5dc732e Fix performance regression in Transposed Convolution by Gunes Bayir · 1 year, 6 months ago
  63. ae72a46 Add new operator AddMulAdd for Neon™ backend for Float/Quantized types by Gunes Bayir · 1 year, 6 months ago
  64. 464ed20 Remove fixed format strides hack by Jonathan Deakin · 1 year, 7 months ago
  65. b609c93 Skip upsampling for deconvolution when not needed by Annop Wongwathanarat · 1 year, 6 months ago
  66. a6a1538 Fix performance regression when stride equal to kernel size by Gunes Bayir · 1 year, 6 months ago
  67. 11f7d7e Add enable_fast_math for NEDeconvolutionLayer by Annop Wongwathanarat · 1 year, 7 months ago
  68. a68df8d Revert "Update the heuristic for CLDepthwiseConvolutionNative kernel" by Gian Marco Iodice · 1 year, 6 months ago
  69. bc67208 Update the heuristic for CLDepthwiseConvolutionNative kernel by Gian Marco Iodice · 1 year, 7 months ago
  70. 9d3bd41 Move DWC native heuristic into the heuristic folder by Gian Marco Iodice · 1 year, 7 months ago
  71. a5cb79f Update the ClConv2d heuristic by Gian Marco Iodice · 1 year, 7 months ago
  72. e317baf Optimize MeanReduce by integer acc. and removing upfront dequant. by Omar Al Khatib · 1 year, 8 months ago
  73. a0ae8d2 Optimize Transposed Convolution for CL backend (Quantized) by Gunes Bayir · 1 year, 8 months ago
  74. df6a3b0 Use heuristics for setting dynamic fusion direct conv2d tile sizes by Ramy Elgammal · 1 year, 8 months ago
  75. 76335eb Implement the OpenCL kernel to compute the indirect convolution by Gian Marco Iodice · 1 year, 8 months ago
  76. 31df05a Remove dynamic fusion prototype with tests and examples by SiCong Li · 1 year, 9 months ago
  77. d2475c7 Add num_threads_to_use to OMPScheduler based on workload size by cfRod · 1 year, 9 months ago
  78. ec0113d Optimize Transposed Convolution for CL backend (FP32/16) by Gunes Bayir · 1 year, 9 months ago
  79. ad9a7ed Rework DepthwiseConvolution heuristic on OpenCL by Gian Marco Iodice · 1 year, 11 months ago
  80. c4f2743 Optimize Quantized/Integer Bilinear Scale for Neon™ by Gunes Bayir · 1 year, 11 months ago
  81. 0eed305 Optimize FP32/16 Bilinear Scale Kernel for Neon™ by Gunes Bayir · 1 year, 11 months ago
  82. 211a55d Optimize depthwise convolution on OpenCL by Gian Marco Iodice · 1 year, 11 months ago
  83. cd083cf Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer repeatedly when mapping multiple children of the same parent. by Murray Kornelsen · 2 years, 1 month ago
  84. 8bab588 Fix validation problem in CLQLSTMLayer by Pablo Marquez Tello · 2 years ago
  85. 52695f5 Fix CTS/SLTS failure related to Depthwise Convolution by Gunes Bayir · 2 years ago
  86. 13b623e [ONCPUML-968] Fixed format kernel support in additional APIs by Milos Puzovic · 2 years ago
  87. 385dad2 Fix for OpenMP scheduler work breakdown by Milos Puzovic · 2 years ago
  88. 9178002 Fix for inclusion of "arm_gemm" from src into "Types.h" from core by Ramy Elgammal · 2 years ago
  89. 553f695 [ONCPUML-951] Variable weight support for Convolution. by Francesco Petrogalli · 2 years, 1 month ago
  90. a1f7851 Integrate new winograd APIs from MLTech by ramelg01 · 2 years, 1 month ago
  91. 4bfc70e Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16 by Gunes Bayir · 2 years, 8 months ago
  92. 22dd8b9 Add missing flag when building cl graph examples and fix by Michalis Spyrou · 2 years, 1 month ago
  93. f28abef Fix compilation error in 32-bit with logging build by Viet-Hoa Do · 2 years, 2 months ago
  94. b63b119 Integrate Dynamic Fusion patches by SiCong Li · 2 years, 6 months ago
  95. 5873358 QLSTM add support for different qinfo by Mike Kelly · 2 years, 3 months ago
  96. 1bae0f9 NEQLSTM: perform type conversion in prepare method. by Pablo Marquez Tello · 2 years, 3 months ago
  97. 0a486cf Enable dynamic cl tuning for dynamically fused kernels by SiCong Li · 2 years, 4 months ago
  98. 16c5697 Add DirectConvolution2D kernel component for dynamic fusion by Gunes Bayir · 2 years, 4 months ago
  99. 171fc3d Add CPU Pool3d FP16/32 implementation by Adnan AlSinan · 2 years, 5 months ago
  100. a5d61bf NEQLSTM: Add support for QASYMM8_SIGNED for input_to_forget_weights by Pablo Marquez Tello · 2 years, 4 months ago