Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 354cbc614dcda5c01d060fa43731285464ba0ac5
  1. 354cbc6 QU8 MUL8 variant of DWCONV by Frank Barchard · 2 years, 9 months ago
  2. 1b1b032 Avoid backward references in Bazel targets by Marat Dukhan · 2 years, 9 months ago
  3. 79c76ab F16->F32 conversion microkernels in AVX512-SKX implementation by Marat Dukhan · 2 years, 9 months ago
  4. f1a6ed3 F16->F32 conversion microkernels in F16C implementation by Marat Dukhan · 2 years, 9 months ago
  5. 694d252 Fix incorrect initialization of QC8 GEMM/IGEMM parameters on AArch32+NEONDOT by Marat Dukhan · 2 years, 9 months ago
  6. 0bf8afa Leverage f32x4.pmin and f32x4.pmax WAsm SIMD instructions by Marat Dukhan · 2 years, 9 months ago
  7. a4ad988 X8 LUT microkernels for WAsm SIMD by Marat Dukhan · 2 years, 9 months ago
  8. aea2d55 Fix test failure in quantized Leaky ReLU NC test under ASan by Marat Dukhan · 2 years, 9 months ago
  9. 2aa2e2a q8 dwconv add channel tiles of 24 and 32 for mul16 rndnu microkernels by Frank Barchard · 2 years, 9 months ago
  10. 5cc31e3 Replace _mm512_(loadu/storeu)_epi8 with _mm512_(loadu/storeu)_si512 by Marat Dukhan · 2 years, 9 months ago
  11. 37c3077 Avoid _mm512_(loadu/storeu)_epi32 in _mm512_(loadu/storeu)_epi8 polyfills by Marat Dukhan · 2 years, 10 months ago
  12. 2ea9075 Script to sort file names in BUILD and CMakeLists.txt by Frank Barchard · 2 years, 10 months ago
  13. d0bf04c Fully qualify std::signbit in ELUOperatorTester by Marat Dukhan · 2 years, 10 months ago
  14. b54871d Polyfill _mm512_loadu_epi8 & _mm512_storeu_epi8 for pre GCC-11 by Marat Dukhan · 2 years, 10 months ago
  15. 67492b0 Expose quantized ELU operator in Subgraph API by Marat Dukhan · 2 years, 10 months ago
  16. eec0052 QS8 ELU operator by Marat Dukhan · 2 years, 10 months ago
  17. e4118ef Polyfill vld1q_u8_x4 for older AArch64 gcc versions by Marat Dukhan · 2 years, 10 months ago
  18. 55bad94 Change QS8 to QU8 in dwconv test by Frank Barchard · 2 years, 10 months ago
  19. 2366290 Add qu8_gemm_4x16__aarch64_neon_mlal_lane_cortex_a75 benchmark to E2E by Frank Barchard · 2 years, 10 months ago
  20. 98e054b Enable vectorized X8 LUT microkernels by Marat Dukhan · 2 years, 10 months ago
  21. 2b3c410 AVX512BW implementations of X8 LUT microkernels by Marat Dukhan · 2 years, 10 months ago
  22. 7c478e3 SSSE3, AVX, and AVX2 X8 LUT microkernels by Marat Dukhan · 2 years, 10 months ago
  23. 5de7bc0 QS8/QU8 Tanh operator using LUT microkernels by Marat Dukhan · 2 years, 10 months ago
  24. f718232 X8 LUT NEON microkernels by Marat Dukhan · 2 years, 10 months ago
  25. 548542c Fix CMake build by Marat Dukhan · 2 years, 10 months ago
  26. a4ba5d4 Expose quantized Sigmoid operator in Subgraph API by Marat Dukhan · 2 years, 10 months ago
  27. 71a9bb1 QS8 Sigmoid operator by Marat Dukhan · 2 years, 10 months ago
  28. f6c991e Implement generic LUT-based elementwise operator by Marat Dukhan · 2 years, 10 months ago
  29. 5407437 Benchmark for X8 LUT microkernels by Marat Dukhan · 2 years, 10 months ago
  30. d67539d Auto-generate X8 LUT microkernels and tests by Marat Dukhan · 2 years, 10 months ago
  31. 2df7542 Add qu8_4x8__neon_mlal_lane benchmark by Frank Barchard · 2 years, 10 months ago
  32. cdf59a5 Add QU8 NR=32 microkernels by Frank Barchard · 2 years, 10 months ago
  33. d460d0b Neon IGEMM do remainder with reversed MR for shifts by Frank Barchard · 2 years, 10 months ago
  34. dfe763f Expose quantized Subtract operator in Subgraph API by Marat Dukhan · 2 years, 10 months ago
  35. b8cbcb5 Fuse rounding term into bias in QS8 & QU8 VADD[C] microkernels by Marat Dukhan · 2 years, 10 months ago
  36. 031ff4b Template bug fix in stores for remainder of 8 in Neon QS8 microkernels by Frank Barchard · 2 years, 10 months ago
  37. 8e2fd20 QS8 and QU8 Subtract ND operators by Marat Dukhan · 2 years, 10 months ago
  38. ec5c129 Template bug fix in stores for remainder of 8. by Frank Barchard · 2 years, 10 months ago
  39. 6428725 Rename ADD quantization parameters to ADDSUB by Marat Dukhan · 2 years, 10 months ago
  40. 1f83cf9 Code generator scripts check if file changed and skip write if it is the same. by Frank Barchard · 2 years, 10 months ago
  41. 8ae1a53 Remove duplicate prototypes by Frank Barchard · 2 years, 10 months ago
  42. 4c49494 Fix crash on AArch32 in scalar quantized microkernels by Marat Dukhan · 2 years, 10 months ago
  43. 2fee611 Fix compilation warnings in QU8 GEMM/IGEMM NEONDOT microkernels by Marat Dukhan · 2 years, 10 months ago
  44. 1ce78ab Leverage Load-Zero WAsm SIMD instructions in Chrome M88 microkernels by Marat Dukhan · 2 years, 10 months ago
  45. 189c1d0 Support specifying the version of WAsm SIMD instructions by Marat Dukhan · 2 years, 10 months ago
  46. df8e604 4x8 QU8 Neon Dotproduct microkernel rename from ld64 to ld128 by Frank Barchard · 2 years, 10 months ago
  47. 90cd7df Fix rewind params for qs8 4x16c4 by Frank Barchard · 2 years, 10 months ago
  48. 33b4f75 VRND microkernels using native WAsm SIMD instructions by Marat Dukhan · 2 years, 10 months ago
  49. bd5b027 4x8 QU8 microkernel use 16 byte UDOT to save 4 UDOT by Frank Barchard · 2 years, 10 months ago
  50. b7a7c30 NEON GEMM/IGEMM microkernels change store/dup to 2 of each by Frank Barchard · 2 years, 10 months ago
  51. 132774e QU8 microkernels change stores to non-lane STR by Frank Barchard · 2 years, 10 months ago
  52. 42a17dd Switch scalar gemmlowp to rndnu for benchmarks by Frank Barchard · 2 years, 10 months ago
  53. 29833fd Change stores to non-lane STR by Frank Barchard · 2 years, 10 months ago
  54. c37b8da Enable little core microkernel on Big/Little CPUs by Frank Barchard · 2 years, 10 months ago
  55. efc3ccf Add 4x16c4 cortex_a55 microkernels to GEMM and E2E benchmarks by Frank Barchard · 2 years, 10 months ago
  56. 1c70764 4x16c4 cortex_a55 microkernel tuning by Frank Barchard · 2 years, 10 months ago
  57. e7e001f Fix bug in QC8/QS8/QU8 IGEMM DOT16x2 LD128 WAsm SIMD microkernels by Marat Dukhan · 2 years, 10 months ago
  58. a49e41f QU8 4x16C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 2 years, 10 months ago
  59. 8589ecd QS8 IGEMM use x11 for params, x10 for a3 and x0 for cn_stride by Frank Barchard · 2 years, 10 months ago
  60. 4810905 Leverage v128.const WAsm SIMD instruction by Marat Dukhan · 2 years, 10 months ago
  61. 8dc106e QC8/QS8/QU8 GEMM/IGEMM WAsm SIMD microkernels using i32x4.dot_i16x8_s instruction by Marat Dukhan · 2 years, 10 months ago
  62. feee77f Leverage f32x4.nearest, f32x4.floor, f32x4.ceil, f32x4.trunc WAsm SIMD instructions by Marat Dukhan · 2 years, 10 months ago
  63. 5d27a7b Leverage f32x4.nearest, f32x4.floor, f32x4.ceil, f32x4.trunc WAsm SIMD instructions by Marat Dukhan · 2 years, 10 months ago
  64. 0a3093c QU8 vadd neon use x32 instead of x8 by Frank Barchard · 2 years, 10 months ago
  65. 7da8b02 Q8 dwconv switch from 8x25 to 16x25 by Frank Barchard · 2 years, 10 months ago
  66. e252f92 End-to-end benchmarks on QC8 MobileNet v1/v2 models by Marat Dukhan · 2 years, 10 months ago
  67. 0d06573 dwconv Q8 switch from 8x9 to 16x9 tile. by Frank Barchard · 2 years, 10 months ago
  68. aae722a Run template generators in parallel by Frank Barchard · 2 years, 10 months ago
  69. 1215c9a QS8 NEON GEMM microkernels use rewind instead of reload by Frank Barchard · 2 years, 10 months ago
  70. 6b30b73 Remainder branch move before label. by Frank Barchard · 2 years, 10 months ago
  71. fec7363 QU8 C4 4x8 rename registers to avoid 3 push/pops. by Frank Barchard · 2 years, 10 months ago
  72. 8b69802 Enable QU8 C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 2 years, 10 months ago
  73. ca4c68e QU8 C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 2 years, 10 months ago
  74. 2d33a9b Document WebAssembly SIMD as non-experimental platform by Marat Dukhan · 2 years, 10 months ago
  75. 56f157c Relabel branches for quantized assembly ARM microkernels by Frank Barchard · 2 years, 10 months ago
  76. 0c76422 QU8 NEON Assembly remove channel wise by Frank Barchard · 2 years, 10 months ago
  77. 408f153 Enable QU8 4x16 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  78. 4066898 QU8 4x16 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  79. 3b9b4bc Fix VCLAMP parameter initialization functions on pre-NEON ARM by Marat Dukhan · 2 years, 10 months ago
  80. a38bf33 QU8 4x8c4 rewind params with SUB by Frank Barchard · 2 years, 10 months ago
  81. b48f367 QU8 4x8 C4 NEON reload params during subtract by Frank Barchard · 2 years, 10 months ago
  82. 073185e QU8 4x8 C4 NEON Assembly Dot Product use partial sums on zero point by Frank Barchard · 2 years, 10 months ago
  83. 0049e89 QU8 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  84. a29b57e QU8 e2e benchmark remove rndnu from benchmark names. by Frank Barchard · 2 years, 10 months ago
  85. 889ed10 QS8 gemm benchmarks switch from GEMMLOWP to RNDNU for AARCH64 assembly by Frank Barchard · 2 years, 10 months ago
  86. 52e4443 Rename linux_aarch64 to linux_arm64 by Marat Dukhan · 2 years, 10 months ago
  87. 6fe565e QU8 neondot use C2 partial sum for zero point accumulators. by Frank Barchard · 2 years, 10 months ago
  88. 3f2074f QU8 neondot use uint32x2 for zero point and accumulators by Frank Barchard · 2 years, 10 months ago
  89. 6507b17 Enable quantized inference by default on the Web platform by Marat Dukhan · 2 years, 10 months ago
  90. 7a8dd87 Work around generating v128.storeXX_lane for quantized WAsm SIMD microkernels by Marat Dukhan · 2 years, 10 months ago
  91. fb53a8c Enable quantized inference by default on the Web platform by XNNPACK Team · 2 years, 10 months ago
  92. 0f66135 Enable quantized inference by default on the Web platform by Marat Dukhan · 2 years, 10 months ago
  93. de9c64a Enable 4x16 QU8 dot production microkernels by Frank Barchard · 2 years, 10 months ago
  94. 9cedb59 Accumulate in 16 bits once in WAsm SIMD MUL16 QS8/QC8 DWCONV before extending to 32 bits by Marat Dukhan · 2 years, 10 months ago
  95. a74310a Remove UDOT by zero point along the N axis by Frank Barchard · 2 years, 10 months ago
  96. 41f8f7c Merge pull request #1826 from peterjc123:clang_windows_fixes by XNNPACK Team · 2 years, 10 months ago
  97. 65692c7 Fix build for Clang on Windows by peter · 2 years, 10 months ago
  98. 0d00baa Support quantized Clamp and Max Pooling operators in Subgraph API by Marat Dukhan · 2 years, 11 months ago
  99. 61c0c9e Clamp NC operator for S8 data type by Marat Dukhan · 2 years, 11 months ago
  100. 9491279 Refactor parameter initialization for VCLAMP microkernels by Marat Dukhan · 2 years, 11 months ago