Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 7c478e31bbc7a1b61199222110efd190fd1b9d13
  1. 7c478e3 SSSE3, AVX, and AVX2 X8 LUT microkernels by Marat Dukhan · 3 years, 2 months ago
  2. 5de7bc0 QS8/QU8 Tanh operator using LUT microkernels by Marat Dukhan · 3 years, 2 months ago
  3. f718232 X8 LUT NEON microkernels by Marat Dukhan · 3 years, 2 months ago
  4. 548542c Fix CMake build by Marat Dukhan · 3 years, 2 months ago
  5. a4ba5d4 Expose quantized Sigmoid operator in Subgraph API by Marat Dukhan · 3 years, 2 months ago
  6. 71a9bb1 QS8 Sigmoid operator by Marat Dukhan · 3 years, 2 months ago
  7. f6c991e Implement generic LUT-based elementwise operator by Marat Dukhan · 3 years, 2 months ago
  8. 5407437 Benchmark for X8 LUT microkernels by Marat Dukhan · 3 years, 2 months ago
  9. d67539d Auto-generate X8 LUT microkernels and tests by Marat Dukhan · 3 years, 2 months ago
  10. 2df7542 Add qu8_4x8__neon_mlal_lane benchmark by Frank Barchard · 3 years, 2 months ago
  11. cdf59a5 Add QU8 NR=32 microkernels by Frank Barchard · 3 years, 2 months ago
  12. d460d0b Neon IGEMM do remainder with reversed MR for shifts by Frank Barchard · 3 years, 2 months ago
  13. dfe763f Expose quantized Subtract operator in Subgraph API by Marat Dukhan · 3 years, 2 months ago
  14. b8cbcb5 Fuse rounding term into bias in QS8 & QU8 VADD[C] microkernels by Marat Dukhan · 3 years, 2 months ago
  15. 031ff4b Template bug fix in stores for remainder of 8 in Neon QS8 microkernels by Frank Barchard · 3 years, 2 months ago
  16. 8e2fd20 QS8 and QU8 Subtract ND operators by Marat Dukhan · 3 years, 2 months ago
  17. ec5c129 Template bug fix in stores for remainder of 8. by Frank Barchard · 3 years, 2 months ago
  18. 6428725 Rename ADD quantization parameters to ADDSUB by Marat Dukhan · 3 years, 2 months ago
  19. 1f83cf9 Code generator scripts check if file changed and skip write if it is the same. by Frank Barchard · 3 years, 2 months ago
  20. 8ae1a53 Remove duplicate prototypes by Frank Barchard · 3 years, 2 months ago
  21. 4c49494 Fix crash on AArch32 in scalar quantized microkernels by Marat Dukhan · 3 years, 2 months ago
  22. 2fee611 Fix compilation warnings in QU8 GEMM/IGEMM NEONDOT microkernels by Marat Dukhan · 3 years, 2 months ago
  23. 1ce78ab Leverage Load-Zero WAsm SIMD instructions in Chrome M88 microkernels by Marat Dukhan · 3 years, 2 months ago
  24. 189c1d0 Support specifying the version of WAsm SIMD instructions by Marat Dukhan · 3 years, 2 months ago
  25. df8e604 4x8 QU8 Neon Dotproduct microkernel rename from ld64 to ld128 by Frank Barchard · 3 years, 2 months ago
  26. 90cd7df Fix rewind params for qs8 4x16c4 by Frank Barchard · 3 years, 2 months ago
  27. 33b4f75 VRND microkernels using native WAsm SIMD instructions by Marat Dukhan · 3 years, 2 months ago
  28. bd5b027 4x8 QU8 microkernel use 16 byte UDOT to save 4 UDOT by Frank Barchard · 3 years, 2 months ago
  29. b7a7c30 NEON GEMM/IGEMM microkernels change store/dup to 2 of each by Frank Barchard · 3 years, 2 months ago
  30. 132774e QU8 microkernels change stores to non-lane STR by Frank Barchard · 3 years, 2 months ago
  31. 42a17dd Switch scalar gemmlowp to rndnu for benchmarks by Frank Barchard · 3 years, 2 months ago
  32. 29833fd Change stores to non-lane STR by Frank Barchard · 3 years, 2 months ago
  33. c37b8da Enable little core microkernel on Big/Little CPUs by Frank Barchard · 3 years, 2 months ago
  34. efc3ccf Add 4x16c4 cortex_a55 microkernels to GEMM and E2E benchmarks by Frank Barchard · 3 years, 2 months ago
  35. 1c70764 4x16c4 cortex_a55 microkernel tuning by Frank Barchard · 3 years, 2 months ago
  36. e7e001f Fix bug in QC8/QS8/QU8 IGEMM DOT16x2 LD128 WAsm SIMD microkernels by Marat Dukhan · 3 years, 2 months ago
  37. a49e41f QU8 4x16C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 3 years, 2 months ago
  38. 8589ecd QS8 IGEMM use x11 for params, x10 for a3 and x0 for cn_stride by Frank Barchard · 3 years, 2 months ago
  39. 4810905 Leverage v128.const WAsm SIMD instruction by Marat Dukhan · 3 years, 2 months ago
  40. 8dc106e QC8/QS8/QU8 GEMM/IGEMM WAsm SIMD microkernels using i32x4.dot_i16x8_s instruction by Marat Dukhan · 3 years, 2 months ago
  41. feee77f Leverage f32x4.nearest, f32x4.floor, f32x4.ceil, f32x4.trunc WAsm SIMD instructions by Marat Dukhan · 3 years, 2 months ago
  42. 5d27a7b Leverage f32x4.nearest, f32x4.floor, f32x4.ceil, f32x4.trunc WAsm SIMD instructions by Marat Dukhan · 3 years, 2 months ago
  43. 0a3093c QU8 vadd neon use x32 instead of x8 by Frank Barchard · 3 years, 3 months ago
  44. 7da8b02 Q8 dwconv switch from 8x25 to 16x25 by Frank Barchard · 3 years, 3 months ago
  45. e252f92 End-to-end benchmarks on QC8 MobileNet v1/v2 models by Marat Dukhan · 3 years, 3 months ago
  46. 0d06573 dwconv Q8 switch from 8x9 to 16x9 tile. by Frank Barchard · 3 years, 3 months ago
  47. aae722a Run template generators in parallel by Frank Barchard · 3 years, 3 months ago
  48. 1215c9a QS8 NEON GEMM microkernels use rewind instead of reload by Frank Barchard · 3 years, 3 months ago
  49. 6b30b73 Remainder branch move before label. by Frank Barchard · 3 years, 3 months ago
  50. fec7363 QU8 C4 4x8 rename registers to avoid 3 push/pops. by Frank Barchard · 3 years, 3 months ago
  51. 8b69802 Enable QU8 C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 3 years, 3 months ago
  52. ca4c68e QU8 C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 3 years, 3 months ago
  53. 2d33a9b Document WebAssembly SIMD as non-experimental platform by Marat Dukhan · 3 years, 3 months ago
  54. 56f157c Relabel branches for quantized assembly ARM microkernels by Frank Barchard · 3 years, 3 months ago
  55. 0c76422 QU8 NEON Assembly remove channel wise by Frank Barchard · 3 years, 3 months ago
  56. 408f153 Enable QU8 4x16 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 3 years, 3 months ago
  57. 4066898 QU8 4x16 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 3 years, 3 months ago
  58. 3b9b4bc Fix VCLAMP parameter initialization functions on pre-NEON ARM by Marat Dukhan · 3 years, 3 months ago
  59. a38bf33 QU8 4x8c4 rewind params with SUB by Frank Barchard · 3 years, 3 months ago
  60. b48f367 QU8 4x8 C4 NEON reload params during subtract by Frank Barchard · 3 years, 3 months ago
  61. 073185e QU8 4x8 C4 NEON Assembly Dot Product use partial sums on zero point by Frank Barchard · 3 years, 3 months ago
  62. 0049e89 QU8 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 3 years, 3 months ago
  63. a29b57e QU8 e2e benchmark remove rndnu from benchmark names. by Frank Barchard · 3 years, 3 months ago
  64. 889ed10 QS8 gemm benchmarks switch from GEMMLOWP to RNDNU for AARCH64 assembly by Frank Barchard · 3 years, 3 months ago
  65. 52e4443 Rename linux_aarch64 to linux_arm64 by Marat Dukhan · 3 years, 3 months ago
  66. 6fe565e QU8 neondot use C2 partial sum for zero point accumulators. by Frank Barchard · 3 years, 3 months ago
  67. 3f2074f QU8 neondot use uint32x2 for zero point and accumulators by Frank Barchard · 3 years, 3 months ago
  68. 6507b17 Enable quantized inference by default on the Web platform by Marat Dukhan · 3 years, 3 months ago
  69. 7a8dd87 Work around generating v128.storeXX_lane for quantized WAsm SIMD microkernels by Marat Dukhan · 3 years, 3 months ago
  70. fb53a8c Enable quantized inference by default on the Web platform by XNNPACK Team · 3 years, 3 months ago
  71. 0f66135 Enable quantized inference by default on the Web platform by Marat Dukhan · 3 years, 3 months ago
  72. de9c64a Enable 4x16 QU8 dot production microkernels by Frank Barchard · 3 years, 3 months ago
  73. 9cedb59 Accumulate in 16 bits once in WAsm SIMD MUL16 QS8/QC8 DWCONV before extending to 32 bits by Marat Dukhan · 3 years, 3 months ago
  74. a74310a Remove UDOT by zero point along the N axis by Frank Barchard · 3 years, 3 months ago
  75. 41f8f7c Merge pull request #1826 from peterjc123:clang_windows_fixes by XNNPACK Team · 3 years, 3 months ago
  76. 65692c7 Fix build for Clang on Windows by peter · 3 years, 3 months ago
  77. 0d00baa Support quantized Clamp and Max Pooling operators in Subgraph API by Marat Dukhan · 3 years, 3 months ago
  78. 61c0c9e Clamp NC operator for S8 data type by Marat Dukhan · 3 years, 3 months ago
  79. 9491279 Refactor parameter initialization for VCLAMP microkernels by Marat Dukhan · 3 years, 3 months ago
  80. 4c3e5a9 GEMM benchmark assembly microkernels before intrinsics. by Frank Barchard · 3 years, 3 months ago
  81. e79acb7 S8 VCLAMP microkernels by Marat Dukhan · 3 years, 3 months ago
  82. 1f5b108 Refactor U8 CLAMP microkernels by Marat Dukhan · 3 years, 3 months ago
  83. 2ea50a0 Refactor U8 MAXPOOL microkernels similarly to S8 MAXPOOL by Marat Dukhan · 3 years, 3 months ago
  84. dc5c148 S8 Max Pooling operator by Marat Dukhan · 3 years, 3 months ago
  85. 2314753 S8 MAXPOOL microkernels for all architectures by Marat Dukhan · 3 years, 3 months ago
  86. f158942 WAsm SIMD implementation of U8 MAXPOOL microkernel by Marat Dukhan · 3 years, 3 months ago
  87. 91ae165 Refactor initialization of MAXPOOL microkernel parameters by Marat Dukhan · 3 years, 3 months ago
  88. ee69093 Enable shell and node environments for WAsm binaries by Marat Dukhan · 3 years, 3 months ago
  89. 9098aba E2E for QU8 GEMM microkernels by Frank Barchard · 3 years, 3 months ago
  90. e033126 Generate more tile sizes for QU8 gemm/igemm by Frank Barchard · 3 years, 3 months ago
  91. b1cd381 Enable dot production microkernels for QU8 on Cortex A55 by Frank Barchard · 3 years, 3 months ago
  92. 2025515 Enable dot production microkernels for QU8 on ARM by Frank Barchard · 3 years, 3 months ago
  93. 88e839c QU8 C4 NEON Dot Product GEMM/IGEMM microkernels by Frank Barchard · 3 years, 3 months ago
  94. cf557d4 Increase timeout for Multiply ND operator test by Marat Dukhan · 3 years, 3 months ago
  95. c67779e Fix flakiness in QS8/QC8 NHWC Deconvolution tests by Marat Dukhan · 3 years, 3 months ago
  96. e7991e7 Minor refactoring of RNG in Fully Connected tester by Marat Dukhan · 3 years, 3 months ago
  97. 57c7827 Fix flakiness in QS8/QC8 NHWC Convolution tests by Marat Dukhan · 3 years, 3 months ago
  98. b3faed3 Fix flakiness in QC8/QS8 GEMM/IGEMM/DWCONV microkernels by Marat Dukhan · 3 years, 3 months ago
  99. 0c2a31e Improve unpacking in SSE4+ QC8/QS8/QU8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 3 months ago
  100. d960231 Remove tests for WAsm SIMD QS8 DWCONV microkernels with GEMMLOWP requantization by Marat Dukhan · 3 years, 3 months ago