Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 7e4ca400606755cfb86c594bc489c5fec3c2cf26 / src
  1. 7e4ca40 3x3s2c3 CONV NEONFMA microkernel with 0+1 padding by Marat Dukhan · 4 years, 3 months ago
  2. b9a9958 Simplify q8 dwconv to remove unrolled aarch64 code by Frank Barchard · 4 years, 3 months ago
  3. 8bd4cba Fix ARM/gcc build or ROUNDZ evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  4. ffbf96a Benchmark for ROUND evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  5. b389f35 Rename pooling_2d.input_padding_* into pooling_2d.padding_* by Marat Dukhan · 4 years, 3 months ago
  6. 6ddfc60 Implement "Greedy by size planner" memory optimization by Chao Mei · 4 years, 3 months ago
  7. c9852ba ROUNDU and ROUNDD evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  8. 737a3a1 IGEMM 4x8 a53/a55 - Replace STP x19, x19 with STR by Frank Barchard · 4 years, 3 months ago
  9. 942b576 Increase size of explicit zero vector in NCHW Convolution by Marat Dukhan · 4 years, 3 months ago
  10. b339045 Comment change rename clamp params to params by Frank Barchard · 4 years, 3 months ago
  11. 1fd91c8 Further optimize NEON ROUND Add+Sub-based evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  12. 03723f5 Further optimize NEON & SSE2 conversion-based rounding stubs by Marat Dukhan · 4 years, 3 months ago
  13. 2dbb944 ROUNDZ evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  14. f1d2da4 Fix typo in xnn_math_f32_roundne__scalar description by Marat Dukhan · 4 years, 3 months ago
  15. 075088a Refactor function names for ROUNDNE evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  16. b196659 FP16 hswish, clamp and prelu microkernels by Frank Barchard · 4 years, 3 months ago
  17. af846e0 FP16 vbinary microkernels use a_ptr, b_ptr, y_ptr void * by Frank Barchard · 4 years, 3 months ago
  18. 1019dcd Force SNaN->QNaN conversion in PSIMD ROUND-NE evaluation stub by Marat Dukhan · 4 years, 3 months ago
  19. 3e19790 Force SNaN->QNaN conversion in scalar ROUND-NE evaluation stub by Marat Dukhan · 4 years, 3 months ago
  20. 8d50380 Force SNaN->QNaN conversion in NEON ROUND-NE evaluation stub by Marat Dukhan · 4 years, 3 months ago
  21. c3d8fb3 Force SNaN->QNaN conversion in SSE ROUND-NE evaluation stub by Marat Dukhan · 4 years, 3 months ago
  22. bcdb1c1 Remove xnn_q8_dwconv_minmax_ukernel_up8x9__aarch32_neon by Frank Barchard · 4 years, 3 months ago
  23. eda9c11 Update CHW DWCONV to pass in input_height and not output_height. by Erich Elsen · 4 years, 3 months ago
  24. 3b745a4 Initialize micro-kernels for pre-NEON ARM in non-mobile builds by Marat Dukhan · 4 years, 3 months ago
  25. d793f6c FP16 vbinary ops by Frank Barchard · 4 years, 3 months ago
  26. 5592e62 Fix math_nonsign_mask_f32 on MSVC by Marat Dukhan · 4 years, 3 months ago
  27. 8853b82 Round-to-nearest-even evaluation stubs by Marat Dukhan · 4 years, 3 months ago
  28. d57dd61 Few fixes in CHW DWCONV by Marat Dukhan · 4 years, 3 months ago
  29. 4e5db3d CHW DWCONV with implicit padding by Erich Elsen · 4 years, 3 months ago
  30. 0dc8f47 Fix a typo by Chao Mei · 4 years, 3 months ago
  31. 3f9f99f Nx16 FP16 intrinsic GEMM and IGEMM ukernels by Frank Barchard · 4 years, 3 months ago
  32. 5d761c4 Fix NR > 8 for FP16 intrinsic GEMM and IGEMM ukernels by Frank Barchard · 4 years, 3 months ago
  33. 5cb16e7 ArgMax Pooling 2D and UnPooling 2D nodes in Subgraph API by Marat Dukhan · 4 years, 3 months ago
  34. e4b8e57 Support TF SAME padding in Argmax Pooling operator by Marat Dukhan · 4 years, 3 months ago
  35. b0e4fae FP16 IGEMM microkernels by Frank Barchard · 4 years, 3 months ago
  36. 99003a8 Add xnn_init_f16_scaleminmax_params helper by Frank Barchard · 4 years, 3 months ago
  37. e92f859 Rename xnn_f16_gemm_ukernel_function to xnn_f16_gemm_minmax_ukernel_function by Frank Barchard · 4 years, 3 months ago
  38. e70dbeb Rename minmax_params to params for variables. by Frank Barchard · 4 years, 3 months ago
  39. 142268b F16 pack functions by Frank Barchard · 4 years, 3 months ago
  40. e826543 Move operator implementations in src/operators/ by Marat Dukhan · 4 years, 3 months ago
  41. 5871703 Support TF-SAME padding in Deconvolution by Marat Dukhan · 4 years, 3 months ago
  42. 8aaf186 Disable TSan in potentially in-place micro-kernels with OOB reads by Marat Dukhan · 4 years, 3 months ago
  43. 0184901 Simplify x86 detection in WAsm builds by Marat Dukhan · 4 years, 3 months ago
  44. f587084 Support Deconvolution in Subgraph API by Marat Dukhan · 4 years, 3 months ago
  45. 78583c7 Enable Cygwin and MSYS build in CMake by Marat Dukhan · 4 years, 3 months ago
  46. fc563f5 Replace LDP with 2 LDR for loads. by Frank Barchard · 4 years, 3 months ago
  47. f5425ea Additional NEON/NEONFMA DWCONV microkernels by Marat Dukhan · 4 years, 3 months ago
  48. 38c07ec Fully Connected node in Subgraph API by Marat Dukhan · 4 years, 3 months ago
  49. 9709e59 Aligned memory incorrectly being deallocated by free() by Tijmen Verhulsdonck · 4 years, 3 months ago
  50. 05b9830 Refactor inputs and outputs representation in a subgraph by Marat Dukhan · 4 years, 3 months ago
  51. 83ea939 FP16 intrinsics generate minmax names and GEMMINC by Frank Barchard · 4 years, 3 months ago
  52. 3b8e566 F16 8x8 GEMM ld64 microkernels by Frank Barchard · 4 years, 3 months ago
  53. 9b885f7 Remove PRFM from F16 GEMM microkernels by Frank Barchard · 4 years, 3 months ago
  54. f5cc7e7 GEMM aarch64 microkernels use LDP to fetch param and cn_stride by Frank Barchard · 4 years, 3 months ago
  55. c4668ed Comment fix for mr <= 4 by Frank Barchard · 4 years, 3 months ago
  56. 875be77 Change xnn_f16_output_params to xnn_f16_scaleminmax_params by Frank Barchard · 4 years, 4 months ago
  57. fd1c759 Suppress warnings about implicit type narrowing in Runtime by Marat Dukhan · 4 years, 4 months ago
  58. 0c864be Fix narrowing type casts in Fully Connected operator by Marat Dukhan · 4 years, 4 months ago
  59. 0b10b9f Fix implicit type cast warnings in NHWC Convolution by Marat Dukhan · 4 years, 4 months ago
  60. 5c9e889 Comment change for params from static to XNN_MIN_ELEMENTS by Frank Barchard · 4 years, 4 months ago
  61. 9913f9c Suppress warning about narrowing type conversion in NCHW Convolution by Marat Dukhan · 4 years, 4 months ago
  62. 1e0410e Remove dead code in NCHW Convolution by Marat Dukhan · 4 years, 4 months ago
  63. e8085f7 Comment change from clamping_params to params by Frank Barchard · 4 years, 4 months ago
  64. bddfbcd FP16 4x8, 6x8 and 1x8 GEMM ld64 microkernels by Frank Barchard · 4 years, 4 months ago
  65. f196d01 Support CMake build with MSVC by Marat Dukhan · 4 years, 4 months ago
  66. 13a93fa 1x12 Cortex A64 F32 GEMM use 2 sets of accumulators by Frank Barchard · 4 years, 4 months ago
  67. 24d9a03 Disable TSan in MaxPool micro-kernels with SIMD by Marat Dukhan · 4 years, 4 months ago
  68. 29c6b26 Exlude PSIMD micro-kernels from the MSVC/ICC build by Marat Dukhan · 4 years, 4 months ago
  69. 45c7fd8 Avoid realloc for packed weights in ResizeBilinear operator by Marat Dukhan · 4 years, 4 months ago
  70. 787978d Eliminate __builtin_prefetch calls by Marat Dukhan · 4 years, 4 months ago
  71. 9c6c09b Use normal (unaligned) allocation for subconvolution buffer by Marat Dukhan · 4 years, 4 months ago
  72. f214916 Add a dummy variable in xnn_f32_default_params by Marat Dukhan · 4 years, 4 months ago
  73. 1b4b69d Specify "C" linkage for xnn_params structure by Marat Dukhan · 4 years, 4 months ago
  74. 02072e6 Avoid two more cases of arithmetics on void* by Marat Dukhan · 4 years, 4 months ago
  75. 57dccd8 NEON and SSE2 implementations of X32 UNPOOL micro-kernel by Marat Dukhan · 4 years, 4 months ago
  76. d0cf9bd Replace VLAs with direct alloca calls by Marat Dukhan · 4 years, 4 months ago
  77. 1f4e461 F16 1x8 GEMM ld64 microkernel by Frank Barchard · 4 years, 4 months ago
  78. c2cfb97 Port AlignedAllocator to Windows by Marat Dukhan · 4 years, 4 months ago
  79. 8fc8776 Suppress type narrowing warning in X8-ZIP SSE2 micro-kernel by Marat Dukhan · 4 years, 4 months ago
  80. bdc8099 Avoid arithmetics on void* in indirection buffer setup by Marat Dukhan · 4 years, 4 months ago
  81. ef3e7dc Replace __builtin_lrintf with lrintf by Marat Dukhan · 4 years, 4 months ago
  82. 504f594 Port xnn_aligned_deallocate to Windows by Marat Dukhan · 4 years, 4 months ago
  83. 57133c0 Port xnn_initialize to Windows by Marat Dukhan · 4 years, 4 months ago
  84. 2acf108 Avoid arithetics on void* in NCHW Convolution by Marat Dukhan · 4 years, 4 months ago
  85. 8ac2b3a Include immintrin.h in sources using _mm_undefined_ps by Marat Dukhan · 4 years, 4 months ago
  86. 9fe932e Partial port to Windows and MSVC by Marat Dukhan · 4 years, 4 months ago
  87. 9993660 Add MINMAX suffix to remaining micro-kernels by Marat Dukhan · 4 years, 4 months ago
  88. 36b76b6 1x16 LD32 F16 GEMM by Frank Barchard · 4 years, 4 months ago
  89. 3cb54f9 1x8 LD64 F32 GEMM by Frank Barchard · 4 years, 4 months ago
  90. 683f559 FP16 4x16 and 6x16 GEMM ld32 microkernels by Frank Barchard · 4 years, 4 months ago
  91. 91cd2b7 Rename binary operation micro-kernels by Marat Dukhan · 4 years, 4 months ago
  92. 355ab43 Rename SpMM micro-kernels by Marat Dukhan · 4 years, 4 months ago
  93. 869c62d Auto-switch to LINEAR GEMM/IGEMM/DWCONV micro-kernels by Marat Dukhan · 4 years, 4 months ago
  94. aefaef3 Prepare xnn_params for variations in fused activations by Marat Dukhan · 4 years, 4 months ago
  95. 163a7e6 Scalar & WAsm GEMM/IGEMM/DWCONV micro-kernels without activation by Marat Dukhan · 4 years, 4 months ago
  96. de06f49 Add MINMAX suffix to GEMM/IGEMM/DWCONV/PPMM micro-kernel names by Marat Dukhan · 4 years, 4 months ago
  97. 8452ff5 Refactor AVGPOOL micro-kernel parameters by Marat Dukhan · 4 years, 4 months ago
  98. 1c58711 Add MINMAX suffix to filenames of GEMM/IGEMM/PPMM/DWCONV micro-kernels by Marat Dukhan · 4 years, 4 months ago
  99. eb09a6b Rename F32/U8 output params to minmax params by Marat Dukhan · 4 years, 4 months ago
  100. a51cf48 Unify layout of min/max parameters by Marat Dukhan · 4 years, 4 months ago