Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / a5cb79f18685292bf5b63a0c484a58945320823d / src
  1. a5cb79f Update the ClConv2d heuristic by Gian Marco Iodice · 1 year, 6 months ago
  2. 8a2d7ce Extend Transposed Conv. for tiles with N0>1 by Gunes Bayir · 1 year, 6 months ago
  3. 939b21a Use CPU quantized addition kernel for quantized subtraction by Omar Al Khatib · 1 year, 7 months ago
  4. bb1ab05 Fix company name on copyright notice by Viet-Hoa Do · 1 year, 6 months ago
  5. 81f796b Fix various compilation errors by Viet-Hoa Do · 1 year, 6 months ago
  6. aecb5d9 Implement Logits1DMaxShiftExpSum kernel component in dynamic fusion by Gunes Bayir · 1 year, 7 months ago
  7. 8ae5714 Add Resize/Scale operator to Dynamic Fusion interface by Jakub Sujak · 1 year, 7 months ago
  8. 8468371 Make CLReshape kernel window based on dst instead of src by Ramy Elgammal · 1 year, 7 months ago
  9. 04f4620 Add multiple output support for dynamic fusion by Viet-Hoa Do · 1 year, 7 months ago
  10. 81fdadd Add is_supported_op interface by SiCong Li · 1 year, 8 months ago
  11. e317baf Optimize MeanReduce by integer acc. and removing upfront dequant. by Omar Al Khatib · 1 year, 7 months ago
  12. 85260d8 Update direct conv2d kernel in dynamic fusion by Gian Marco Iodice · 1 year, 7 months ago
  13. 24c87f0 Optimize SVE natural exponential function by Viet-Hoa Do · 1 year, 7 months ago
  14. 9d7b690 Fixed various mismatches in CpuCastKernel by Pablo Marquez Tello · 1 year, 7 months ago
  15. b84e253 Add output operator for dynamic fusion by Viet-Hoa Do · 1 year, 7 months ago
  16. a0ae8d2 Optimize Transposed Convolution for CL backend (Quantized) by Gunes Bayir · 1 year, 7 months ago
  17. 3274172 Add CLAMP operator to Dynamic Fusion interface by Jakub Sujak · 1 year, 7 months ago
  18. 21a0a4e Fix build error resulting from incorrect header path by Jakub Sujak · 1 year, 7 months ago
  19. 1dc6ff1 Implement Cast operator in dynamic fusion by Gunes Bayir · 1 year, 7 months ago
  20. df6a3b0 Use heuristics for setting dynamic fusion direct conv2d tile sizes by Ramy Elgammal · 1 year, 7 months ago
  21. 86689cd Optimize CPU base-e exponential function on FP32 by Viet-Hoa Do · 1 year, 8 months ago
  22. 76335eb Implement the OpenCL kernel to compute the indirect convolution by Gian Marco Iodice · 1 year, 8 months ago
  23. f16973b Fix build error for unused variables in data type specific builds by Gunes Bayir · 1 year, 7 months ago
  24. 404462a Adding GpuAdd to dynamic fusion operators by Ramy Elgammal · 1 year, 8 months ago
  25. 03b2971 Integrate SME2 kernels by Viet-Hoa Do · 2 years, 1 month ago
  26. 7dc0234 Implement FP32/16 Depthwise Conv2d operator in dynamic fusion by Gunes Bayir · 1 year, 8 months ago
  27. 5d01681 Implement address precalculation for indirect conv2d - OpenCL by Gian Marco Iodice · 1 year, 8 months ago
  28. e112ef1 ONCPUML-1072: Remove double definition of get_mws for Mul kernel by fadara01 · 1 year, 8 months ago
  29. 31df05a Remove dynamic fusion prototype with tests and examples by SiCong Li · 1 year, 8 months ago
  30. 73bb6b7 ONCPUML-1072: Tuned MWS values (for N1, V1) for binary operators used by oneDNN by Fadi Arafeh · 1 year, 9 months ago
  31. d2475c7 Add num_threads_to_use to OMPScheduler based on workload size by cfRod · 1 year, 8 months ago
  32. 8307ecf Fix regression caused by mws in ActivationLayer by Mohammed Suhail Munshi · 1 year, 8 months ago
  33. b230a1f Fixed Arm NN unit test failure caused by quantised multiplication patch. by Omar Al Khatib · 1 year, 8 months ago
  34. ec0113d Optimize Transposed Convolution for CL backend (FP32/16) by Gunes Bayir · 1 year, 8 months ago
  35. 96fb194 Optimize T_QUANTIZE8_ASYMMETRIC for Mali™ G52 by Pablo Marquez Tello · 1 year, 8 months ago
  36. fd76611 Fix compiler warnings in dynamic fusion by SiCong Li · 1 year, 8 months ago
  37. d4a9cc0 Fix CPU multiplication layer threading overhead by Viet-Hoa Do · 1 year, 8 months ago
  38. d158609 SVE Hard-Swish via Lookup table for quantized input by Pablo Marquez Tello · 2 years, 1 month ago
  39. 605a928 Optimize CPU mul layer on quantized data by Omar Al Khatib · 1 year, 8 months ago
  40. a2b131b Fix compiler warnings in dynamic fusion by SiCong Li · 1 year, 8 months ago
  41. 635013a Fix activation block in gemm.cl by Gian Marco Iodice · 1 year, 8 months ago
  42. 01934e9 Partially Revert "Add threshold for floating-point SOFT_RELU activation" by Gunes Bayir · 1 year, 8 months ago
  43. 0ae31d1 Fix fixed-point quantized addition by Viet-Hoa Do · 1 year, 8 months ago
  44. a7077e9 Updateable weights in depthwise convolution by Milos Puzovic · 1 year, 8 months ago
  45. 199982f Add threshold for floating-point SOFT_RELU activation by Milos Puzovic · 1 year, 8 months ago
  46. 4b5f6ef Add check for Batch Matmul in GemmAssemblyDispatch by Mohammed Suhail Munshi · 1 year, 9 months ago
  47. f44bbc5 Rewrite dynamic fusion by SiCong Li · 1 year, 10 months ago
  48. 3394f3e Rework direct convolution heuristic on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
  49. 910e3f9 Fix fixed-point quantized addition by Viet-Hoa Do · 1 year, 9 months ago
  50. 2bc8cfe Add FP16 tanh based on rational approximation by Jonathan Deakin · 1 year, 9 months ago
  51. 9fc0b5c Update reinterpret tensor as 1D for CPU add by Viet-Hoa Do · 1 year, 9 months ago
  52. 6782452 Add test in GEMMLowp for batch matmul by Mohammed Suhail Munshi · 1 year, 9 months ago
  53. 0a36f58 Fix FFTConvolutionLayer test by Viet-Hoa Do · 1 year, 9 months ago
  54. fa79fda Optimize Neon™ Logistic Activation by Mohammed Suhail Munshi · 1 year, 10 months ago
  55. c8cc024 Adding documentation section explaining how BF16 is used by Ramy Elgammal · 1 year, 9 months ago
  56. 6670413 Fix LUT-based activation layer by Viet-Hoa Do · 1 year, 9 months ago
  57. 2ffab6d Workaround CL compiler issue on FP16 by Viet-Hoa Do · 1 year, 9 months ago
  58. 842ad21 Optimize Neon™ SUB operator by squashing execution window by Jakub Sujak · 1 year, 10 months ago
  59. ad9a7ed Rework DepthwiseConvolution heuristic on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
  60. 3bedd2f Improve start-up time in gemmlowp reshaped rhs only. by Adnan AlSinan · 1 year, 10 months ago
  61. db14af6 Update GEMM reshaped rhs only heuristic by Gian Marco Iodice · 1 year, 9 months ago
  62. b5368fb Force CL kernel compilation with 64 registers by Viet-Hoa Do · 1 year, 10 months ago
  63. 304dfdb Fix Batch Matmul nightly failure by Adnan AlSinan · 1 year, 10 months ago
  64. 40b4419 Optimize CPU add layer on quantized data by Viet-Hoa Do · 1 year, 10 months ago
  65. ff81de5 Fix overflow in NEActivationLayer for FP16 type by Pablo Marquez Tello · 1 year, 9 months ago
  66. d6b8a71 Add FP32 Neon™ swish activation by Jonathan Deakin · 1 year, 11 months ago
  67. ce79ac6 CPU GEMM: Fix overreads in SVE merges. by David Mansell · 1 year, 10 months ago
  68. ead4d11 Fix unresolved symbol for target armv7a + Android by Pablo Marquez Tello · 1 year, 10 months ago
  69. 047e5d0 Fix validation in validate_image2d_support_on_rhs by Gian Marco Iodice · 1 year, 10 months ago
  70. 622b8ad Fix bug in QASYMM8_SIGNED to F32 cast layer by Viet-Hoa Do · 1 year, 10 months ago
  71. c4f2743 Optimize Quantized/Integer Bilinear Scale for Neon™ by Gunes Bayir · 1 year, 10 months ago
  72. 0d05b66 Interpreting tensor as 1D for CPU multiplication by Viet-Hoa Do · 1 year, 10 months ago
  73. 5687e55 Fix invalid memory access for dynamically fused Cl Elementwise kernels by SiCong Li · 1 year, 11 months ago
  74. 926f502 Adding GELU activation by Murray Kornelsen · 2 years ago
  75. 6e09e14 INT8 Quantized MeanStdDevNorm (LayerNorm) by Murray Kornelsen · 2 years ago
  76. 26c9d1a Add test for NEGEMM to test a batched matrix multiplication with variable input tensors by Adnan AlSinan · 1 year, 10 months ago
  77. 4478e1c Rework heuristic in ClConv2d by Gian Marco Iodice · 1 year, 10 months ago
  78. 0eed305 Optimize FP32/16 Bilinear Scale Kernel for Neon™ by Gunes Bayir · 1 year, 10 months ago
  79. d11de98 Add a macro guard in all OpenCL kernels in gemmlowp.cl by Gian Marco Iodice · 1 year, 10 months ago
  80. e4e3b2e Disable Winograd on fp16 if fast-math = false by Ramy Elgammal · 1 year, 10 months ago
  81. 211a55d Optimize depthwise convolution on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
  82. 552fe4c F16 Specialization for MeanStdDevNorm by Murray Kornelsen · 2 years ago
  83. 1257131 Enable Winograd-based conv2d when IFM>=8 on Gpu by Gian Marco Iodice · 1 year, 10 months ago
  84. cd083cf Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer repeatedly when mapping multiple children of the same parent. by Murray Kornelsen · 2 years ago
  85. a331e48 Fix add for tensors with non-matching strides by Jonathan Deakin · 1 year, 11 months ago
  86. 8bab588 Fix validation problem in CLQLSTMLayer by Pablo Marquez Tello · 1 year, 11 months ago
  87. a81fc84 Fix macos build errors by Pablo Marquez Tello · 1 year, 11 months ago
  88. 53929b1 Use Neon™ kernels for FP Bilinear Resize for SVE by Gunes Bayir · 1 year, 11 months ago
  89. 9ee8a3e Revert "Fix performance regression in ClConv2D" by Ramy Elgammal · 1 year, 11 months ago
  90. 29db3d2 Add LUT for quantized sigmoid function by Viet-Hoa Do · 1 year, 11 months ago
  91. e54d8c0 Fix performance regression in ClConv2D by Gian Marco Iodice · 1 year, 11 months ago
  92. cec1af5 Fix performance regression in Conv2D on OpenCL by Adnan AlSinan · 1 year, 11 months ago
  93. cc03419 Disable unsafe FP optimizations in Winograd Output Transform by Gunes Bayir · 1 year, 11 months ago
  94. 52695f5 Fix CTS/SLTS failure related to Depthwise Convolution by Gunes Bayir · 1 year, 11 months ago
  95. 65c8db8 Fix for AI benchmark ResNet regression by Viet-Hoa Do · 1 year, 11 months ago
  96. 0105ce5 Fix LeNet-f16 convolution regression by Adnan AlSinan · 1 year, 11 months ago
  97. 93581a5 [ONCPUML-970] Fast math mode for fixed format kernels by Pablo Marquez Tello · 2 years ago
  98. f67903b Add Dynamic Fusion Tests with BugFixes by Mohammed Suhail Munshi · 2 years ago
  99. 13b623e [ONCPUML-968] Fixed format kernel support in additional APIs by Milos Puzovic · 2 years ago
  100. 3c4d085 Update the GPUTarget list by Gian Marco Iodice · 2 years ago