Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 0797eb17d3a9b30ec447e8ee4ac6e02c300730d8 / bench
  1. 0797eb1 Rename QS8 assembly GEMM kernels to ld64 by Frank Barchard · 3 years, 9 months ago
  2. f1fd89e 1x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 9 months ago
  3. 31bb45b 4x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 9 months ago
  4. a48848f 4x8, 6x8 and 8x16 Neon dot product GEMM microkernels by Frank Barchard · 3 years, 10 months ago
  5. d9ca7e6 AVX512F versions of Sigmoid microkernel by Marat Dukhan · 3 years, 10 months ago
  6. 2fa1745 6x16 QS8 GEMM for Neon dot product by Frank Barchard · 3 years, 10 months ago
  7. d243c1a LUT-based SSE Sigmoid microkernels by Marat Dukhan · 3 years, 10 months ago
  8. fc2844e FP16 hardswish operator benchmark by Frank Barchard · 3 years, 10 months ago
  9. 66f3ccd End-to-end FP16 MobileNet v3 benchmarks by Marat Dukhan · 3 years, 10 months ago
  10. ef4ce31 Remove trailing whitespace by Marat Dukhan · 3 years, 10 months ago
  11. 70a9618 End-to-end QS8 MobileNet v2 benchmark by Marat Dukhan · 3 years, 11 months ago
  12. 37297a6 F32-RELU unrolled more for improved performance on Web Assembly by Frank Barchard · 3 years, 11 months ago
  13. 9f5ccb3 f32 relu microkernel WASM assembly x2 and x4 unrolled loops by Frank Barchard · 4 years ago
  14. a964473 Add xnn_qs8_gemm_minmax_ukernel_${MR}x${NR}c4__neondot (ARMv8.2+dotprod). by Benoit Jacob · 4 years ago
  15. d91624e f32 relu microkernel WASM assembly optimized implementation by Frank Barchard · 4 years ago
  16. bb00b1d AVX512 variants of QS8 GEMM and IGEMM microkernels by Marat Dukhan · 4 years ago
  17. 9e0b539 QS8 variant of NWC Global Average Pooling operator by Marat Dukhan · 4 years ago
  18. ab67142 Benchmark ARM NEON versions of QS8 GEMM microkernels by Marat Dukhan · 4 years ago
  19. 27203da WAsm SIMD versions of QS8 GEMM and IGEMM microkernels by Marat Dukhan · 4 years ago
  20. b1cbbba Add ADE20k parameters to Softmax benchmark by Marat Dukhan · 4 years ago
  21. 0743cdf Hardcoded end-to-end benchmark on MobileNet v1 in QS8 format by Marat Dukhan · 4 years ago
  22. 16f1e1a QS8 version of NHWC Convolution operator by Marat Dukhan · 4 years ago
  23. 22de5e7 WAsm SIMD implementation of QU8 Q31 requantization by Marat Dukhan · 4 years ago
  24. ecd8311 Rename s8rng/s32rng -> i8rng/i32rng by Marat Dukhan · 4 years ago
  25. dfcaa3c Include scalar QU8 requantization in the benchmark by Marat Dukhan · 4 years ago
  26. 3e07b91 Reoptimize QS8 implementatation of Q31 requantization schema in WAsm SIMD by Marat Dukhan · 4 years ago
  27. 56bdd4a QS8 requantization benchmark by Marat Dukhan · 4 years ago
  28. 683fab3 XW (eXtended Weights) optimization for QS8 GEMM microkernel by Marat Dukhan · 4 years ago
  29. e7edc80 Add 3x4c8 variants of SSE2/SSSE3/SSE4.1/XOP GEMM/IGEMM microkernels by Marat Dukhan · 4 years ago
  30. 1280952 AVX2 version of QS8 GEMM and IGEMM microkernels by Marat Dukhan · 4 years ago
  31. 1566fee XOP versions of QS8 GEMM/IGEMM microkernels by Marat Dukhan · 4 years ago
  32. 44f0ca7 Bind RNG by reference in microbenchmarks by Marat Dukhan · 4 years ago
  33. dee732b LD128 versions of QS8 GEMM SSE2/SSSE3/SSE4.1 microkernels by Marat Dukhan · 4 years ago
  34. 14d3ce8 Add LD64 suffix in QS8 GEMM/IGEMM microkernels by Marat Dukhan · 4 years ago
  35. 733d0be QS8 GEMM MRx4c8 SSE2/SSSE3/SSE4.1 microkernels by Marat Dukhan · 4 years ago
  36. 595e170 QS8 GEMM microkernels and infrastructure by Marat Dukhan · 4 years ago
  37. 9199246 Remove redundant input_zero_point parameter from xnn_qu8_gemm_params by Marat Dukhan · 4 years ago
  38. 5b69f8b Rename requantization functions and filenames by Marat Dukhan · 4 years ago
  39. a199d49 Remove support for direct Asm.js builds by Marat Dukhan · 4 years ago
  40. 92162da Remove PSIMD versions of PPMM and PACKX microkernels by Marat Dukhan · 4 years ago
  41. 0d0d882 WAsm SIMD version of PPMM microkernel by Marat Dukhan · 4 years ago
  42. c664027 Use proper macros to guard code segment to prevent compilation errors. by Chao Mei · 4 years ago
  43. d187a5b LUT64-based SIGMOID microkernels for WAsm SIMD by Marat Dukhan · 4 years ago
  44. c201006 FP16 ReLU microkernel benchmark by Frank Barchard · 4 years ago
  45. 3c4a952 relu microkernel benchmark by Frank Barchard · 4 years ago
  46. 249cd6a Remove PSIMD variants of RADDSTOREEXPMINUSMAX microkernels by Marat Dukhan · 4 years ago
  47. 2f1b1ce Remove PSIMD versions of evaluation stubs by Marat Dukhan · 4 years ago
  48. 6eca86c Remove PSIMD variants of unary elementwise microkernels by Marat Dukhan · 4 years ago
  49. bbf7f3f Remove PSIMD variants of DWCONV microkernels by Marat Dukhan · 4 years ago
  50. 115d3e2 Remove PSIMD variants of GEMM and IGEMM microkernels by Marat Dukhan · 4 years ago
  51. 490febe Cortex A7 microkernel based on LD64 with PLD added. 3.2% faster in end to end mobilenet v2 by Frank Barchard · 4 years ago
  52. 52238f0 WAsm SIMD versions of RADDSTOREEXPMINUSMAX microkernels by Marat Dukhan · 4 years ago
  53. b3635ed Port SIGMOID microkernels to WAsm SIMD by Marat Dukhan · 4 years ago
  54. 08b7a97 Rename Q8 microkernels and operators to QU8 by Marat Dukhan · 4 years ago
  55. 55dde5b NEON F32 HSWISH microkernel unrolled by 16 by Marat Dukhan · 4 years ago
  56. 9df9dc6 Reoptimize HSWISH microkernels by Marat Dukhan · 4 years ago
  57. 8c41796 WAsm SIMD versions of F32 RMAX microkernel by Marat Dukhan · 4 years ago
  58. c8caea6 Generalize Convolution operator creation across data types by Marat Dukhan · 4 years ago
  59. bc08f31 Generalize Fully Connected operator creation across data types by Marat Dukhan · 4 years ago
  60. b42f866 Unify interface of weights packing functions by Marat Dukhan · 4 years ago
  61. 6804bbd Square Root operator by Marat Dukhan · 4 years, 1 month ago
  62. f4db2f3 Vector SQRT microkernels by Marat Dukhan · 4 years, 1 month ago
  63. 270a2c4 FP16 End-to-End benchmarks by Marat Dukhan · 4 years, 1 month ago
  64. 49b4dcc FP16 Convolution NHWC operator by Frank Barchard · 4 years, 1 month ago
  65. c303fe6 Optimize selection of HSWISH microkernels in WAsm SIMD by Marat Dukhan · 4 years, 1 month ago
  66. 1d89da8 Enable WAsm HSWISH microbenchmarks in WAsm SIMD build by Marat Dukhan · 4 years, 1 month ago
  67. a11ca34 Microbenchmarks for HSWISH microkernels by Marat Dukhan · 4 years, 1 month ago
  68. ad35260 HardSwish operator benchmark by Marat Dukhan · 4 years, 1 month ago
  69. 8772714 Benchmarks for rounding operators by Marat Dukhan · 4 years, 1 month ago
  70. d3f3d87 ROUND evaluation stubs in WAsm SIMD intrinsics by Marat Dukhan · 4 years, 1 month ago
  71. 0ccccf1 Group FP16 operators together in a section guarded by #ifndef XNN_NO_F16_OPERATORS by Frank Barchard · 4 years, 1 month ago
  72. 569561d Generate PLD variation of AARCH32 LD64 by Frank Barchard · 4 years, 1 month ago
  73. ac014d7 DWCONV microkernels in WAsm SIMD intrinsics by Marat Dukhan · 4 years, 1 month ago
  74. 1bbf96b GEMM/IGEMM implementations in WAsm SIMD intrinsics by Marat Dukhan · 4 years, 1 month ago
  75. d986004 Remove cpuinfo as dependency for operator benchmarks by Frank Barchard · 4 years, 1 month ago
  76. 7465a89 Add PSIMD DWCONV CHW 5X5S2P2 kernel. by Erich Elsen · 4 years, 1 month ago
  77. 0c84973 FP16 Global Average Pooling operator benchmark by Frank Barchard · 4 years, 1 month ago
  78. 0325244 FP32 Global Average Pooling operator benchmark by Frank Barchard · 4 years, 1 month ago
  79. 2892889 Add PSIMD DWCONV 5x5s2 kernel. by Erich Elsen · 4 years, 1 month ago
  80. 016e586 iOS use Cortex-A75 microkernel which avoids x18 register by Frank Barchard · 4 years, 1 month ago
  81. fd7a6e3 Add PSIMD DWCONV-CHW 3x3s2p1 kernel. by Erich Elsen · 4 years, 1 month ago
  82. e6214af Add PSIMD dwconv 3x3s1 kernel. by Erich Elsen · 4 years, 1 month ago
  83. 0a1970e PSIMD F32-CONV-HWC2CHW kernel by Erich Elsen · 4 years, 1 month ago
  84. 6e80fdc Add 16x1 SSE f32-SpMM kernels, which is faster than the existing 8x1 kernel. by Erich Elsen · 4 years, 1 month ago
  85. 290055c Requantization implementation in WAsm SIMD intrinsics by Marat Dukhan · 4 years, 1 month ago
  86. b123340 Add SSE versions of conv-hwc2chw by Erich Elsen · 4 years, 1 month ago
  87. 9c1a735 Include FP16 header for conversions by Frank Barchard · 4 years, 1 month ago
  88. 5a599a6 FP16 DWCONV microkernel by Frank Barchard · 4 years, 1 month ago
  89. 8fb51b6 Remove Add NC operator by Marat Dukhan · 4 years, 1 month ago
  90. d960714 FP16 IGEMM benchmark fix log2(sizeof uint16) = 1 by Frank Barchard · 4 years, 1 month ago
  91. 2b95ea1 f32_dwconv benchmark add missing neon microkernels by Frank Barchard · 4 years, 2 months ago
  92. 40f50e1 f16 benchmarks - add cpuinfo check for FP16 by Frank Barchard · 4 years, 2 months ago
  93. 56b10cd CONV-HWC NEONFMA micro-kernels with width tile 1 by Marat Dukhan · 4 years, 2 months ago
  94. d536072 DWCONV add input_offset and zero parameters by Frank Barchard · 4 years, 2 months ago
  95. 3b98f6b 4x4 LD64 GEMM+MINMAX microkernel in AArch32+VFP assembly by Marat Dukhan · 4 years, 2 months ago
  96. 1f29b80 Refactor CHW micro-kernels by Marat Dukhan · 4 years, 2 months ago
  97. ffbf96a Benchmark for ROUND evaluation stubs by Marat Dukhan · 4 years, 2 months ago
  98. eda9c11 Update CHW DWCONV to pass in input_height and not output_height. by Erich Elsen · 4 years, 2 months ago
  99. 4e5db3d CHW DWCONV with implicit padding by Erich Elsen · 4 years, 2 months ago
  100. 09a5df3 Thumb-1 compatibility for DisableDenormals assembly by Marat Dukhan · 4 years, 2 months ago