1. a93765f Add MR=1 versions of QS8 gemm benchmarks by Frank Barchard · 3 years, 4 months ago
  2. 85b1e24 Merge pull request #1273 from powderluv:fix-compile by XNNPACK Team · 3 years, 4 months ago
  3. 6d490f7 Change isfinite() to std::isfinite() by Anush Elangovan · 3 years, 4 months ago
  4. 2202c81 Implement bilinear upsampling (CHW layout) for ARM architecture by Artsiom Ablavatski · 3 years, 4 months ago
  5. 2302ffd QS8 Neon GEMM microkernel with 8 bit multiply and vpadal to accumulate by Frank Barchard · 3 years, 4 months ago
  6. cadd422 Numerically sort microkernel filenames in BUILD files. by Frank Barchard · 3 years, 4 months ago
  7. ec0bf14 QS8 GEMM and IGEMM 3x8 3x16 and IGEMM 4x8 and 4x16 by Frank Barchard · 3 years, 4 months ago
  8. 4ecae2e QS8 Neon GEMM microkernel with 8 bit multiply by Frank Barchard · 3 years, 4 months ago
  9. b94e34b QS8 GEMM select 2x16 for Neon MLAL. by Frank Barchard · 3 years, 4 months ago
  10. cfbc849 Add 4x8 and 4x16 qs8 gemm microkernels by Frank Barchard · 3 years, 5 months ago
  11. 48d70eb Upgrade XNNPACK to db2475b8af7e129b722167c3579ea743735fd733 by Haibo Huang · 3 years, 5 months ago
  12. db2475b Include <memory> for `std::addressof` after libc++ commit 7ad49aec125b3c1205b164331d0aa954d773f890. by XNNPACK Team · 3 years, 5 months ago
  13. abb547c Merge pull request #1257 from skyline75489:patch-3 by XNNPACK Team · 3 years, 5 months ago
  14. 5c29c64 Restore support for older armv7 devices by Chester Liu · 3 years, 5 months ago
  15. 25bab07 Improve architecture detection for Apple devices by Chester Liu · 3 years, 5 months ago
  16. c5704bf WebAssembly DWConv2D 3x3 stride 2 loadsplat by Frank Barchard · 3 years, 5 months ago
  17. e1ffe15 Merge pull request #1254 from malfet:enable-osx-cross-compilation by XNNPACK Team · 3 years, 5 months ago
  18. b126f9c Update cpuinfo checkout hash by Nikita Shulga · 3 years, 5 months ago
  19. 30dbea6 Add support for CMAKE_OSX_ARCHITECTURES by Nikita Shulga · 3 years, 5 months ago
  20. c6889b3 WebAssembly DWConv2D 5x5 stride 2 loadsplat by Frank Barchard · 3 years, 5 months ago
  21. e683659 Merge pull request #1252 from skyline75489:patch-1 by XNNPACK Team · 3 years, 5 months ago
  22. 4510c4a Exclude aarch32 & aarch64 ASM code accroding to XNNPACK_ENABLE_ASSEMBLY flag by Chester Liu · 3 years, 5 months ago
  23. 02bb429 WebAssembly DWConv2D 3x3p1 adapted from NEON by Frank Barchard · 3 years, 5 months ago
  24. b20dcd6 WASMSIMD dwconv2d 5x5p2 use loadsplat by Frank Barchard · 3 years, 5 months ago
  25. f7291fc Accuracy verification test for EXP evaluation stubs by Marat Dukhan · 3 years, 5 months ago
  26. 1a3db36 Fix CMake build by Marat Dukhan · 3 years, 5 months ago
  27. d28a5a2 Accuracy verification test for EXPMINUS evaluation stubs by Marat Dukhan · 3 years, 5 months ago
  28. c30f310 WASMSIMD dwconv2d chw 3x3p1 replace loadsplat with vector load and shuffle by Frank Barchard · 3 years, 5 months ago
  29. e332dd6 Fix bug in EXPM1MINUS and ELU implementation by Marat Dukhan · 3 years, 5 months ago
  30. f44f022 Accuracy verification test for EXPM1MINUS evaluation stubs by Marat Dukhan · 3 years, 5 months ago
  31. cf67ec6 Separate naming for accuracy evaluation benchmarks by Marat Dukhan · 3 years, 5 months ago
  32. 63ec750 Document support for Apple Silicon Macs by Marat Dukhan · 3 years, 5 months ago
  33. 51dd6eb Update Google Test dependency by Marat Dukhan · 3 years, 5 months ago
  34. dfe47b9 Use iOS microkernels for Apple Silicon Macs by Marat Dukhan · 3 years, 5 months ago
  35. 0fff1bd Update cpuinfo dependency by Marat Dukhan · 3 years, 5 months ago
  36. ced880d Add missing <memory> include in accuracy evaluation benchmarks by Marat Dukhan · 3 years, 6 months ago
  37. 4eddb9c Fix incompatibility with Apple Clang in Subgraph tester by Marat Dukhan · 3 years, 6 months ago
  38. 802fcae Additional SSE/SSE2 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 6 months ago
  39. 412e2f4 Rename WASMSIMD dwconv2d functions to splat or loadsplat by Frank Barchard · 3 years, 6 months ago
  40. 3de5dfa Remove PSIMD dependency by Marat Dukhan · 3 years, 6 months ago
  41. 094e692 Support sparse rewriting for clusters with ELU operator by Marat Dukhan · 3 years, 6 months ago
  42. c1aa297 Inroduce `timeout` parameter into `xnnpack_unit_test` by Artsiom Ablavatski · 3 years, 6 months ago
  43. b36582b Enable sparse inference by default by Marat Dukhan · 3 years, 6 months ago
  44. cfbed0a Disable sparse graph rewriting on x86 with AVX+ by Marat Dukhan · 3 years, 6 months ago
  45. c10585f Minor refactoring of SubgraphTester by Marat Dukhan · 3 years, 6 months ago
  46. 54b2d54 Disable sparse graph rewriting for clusters with <= 2/3 zeroes by Marat Dukhan · 3 years, 6 months ago
  47. 4f936de Merge "Update Android.bp following XNNPACK rebase" am: aeaa208971 am: 86b9f05b32 am: c4c7805b0a by Treehugger Robot · 3 years, 6 months ago
  48. 8b238e1 Upgrade XNNPACK to de390d4b6fd1ca0b82bba3640fbd3cc9bbc5c4ef am: b2aed94f42 am: 38758c6c49 am: b863c08481 by Haibo Huang · 3 years, 6 months ago
  49. c4c7805 Merge "Update Android.bp following XNNPACK rebase" am: aeaa208971 am: 86b9f05b32 by Treehugger Robot · 3 years, 6 months ago
  50. b863c08 Upgrade XNNPACK to de390d4b6fd1ca0b82bba3640fbd3cc9bbc5c4ef am: b2aed94f42 am: 38758c6c49 by Haibo Huang · 3 years, 6 months ago
  51. 6f7d4a2 Remove unused input_width_tile from dwconv2d_chw_parameters by Marat Dukhan · 3 years, 6 months ago
  52. 86b9f05 Merge "Update Android.bp following XNNPACK rebase" am: aeaa208971 by Treehugger Robot · 3 years, 6 months ago
  53. 38758c6 Upgrade XNNPACK to de390d4b6fd1ca0b82bba3640fbd3cc9bbc5c4ef am: b2aed94f42 by Haibo Huang · 3 years, 6 months ago
  54. 4ddfab4 Optimize CHW microkernel selection for pre-NEON AArch32 by Marat Dukhan · 3 years, 6 months ago
  55. aeaa208 Merge "Update Android.bp following XNNPACK rebase" by Treehugger Robot · 3 years, 6 months ago
  56. c763488 CONV2D HWC2CHW microkernel for ARM NEON by Marat Dukhan · 3 years, 6 months ago
  57. 3e91338 Initialize pointers to NEON CHW microkernels by Marat Dukhan · 3 years, 6 months ago
  58. c8bbe70 Benchmarks for NEON versions of DWCONV2D CHW microkernels by Marat Dukhan · 3 years, 6 months ago
  59. 3b32261 Simplify constant expressions in WAsm SIMD DWConv CHW by Frank Barchard · 3 years, 6 months ago
  60. 0725b8d Rename WebAssembly SIMD source files and functions with x86 or arm suffix after wasmsimd by Frank Barchard · 3 years, 6 months ago
  61. 5eea831 Update Android.bp following XNNPACK rebase by Miao Wang · 3 years, 6 months ago
  62. 5d7ca1a Remove duplicate WASMSIMD dwconv2d 5x5s2 tests by Frank Barchard · 3 years, 6 months ago
  63. c12dcda Fix typo in sparse rewriting by Marat Dukhan · 3 years, 6 months ago
  64. 7332e83 Add Runtime flag to indicate sparse inference preference by Marat Dukhan · 3 years, 6 months ago
  65. 1631e3e Refactor SpMM benchmarks by Marat Dukhan · 3 years, 6 months ago
  66. 3a30521 Refactor accuracy evaluation benchmarks by Marat Dukhan · 3 years, 6 months ago
  67. 5b86c43 NEON versions of non-blocked F32 SpMM microkernels by Marat Dukhan · 3 years, 6 months ago
  68. 2fa7a0c Build and test non-blocked NEONFMA SpMM microkernels on AArch32 by Marat Dukhan · 3 years, 6 months ago
  69. f56b4bb Fix classification of Depth-to-Space operator in Sparse rewriting by Marat Dukhan · 3 years, 6 months ago
  70. 102e9ea Revert "Remove PSIMD dependency" by Marat Dukhan · 3 years, 6 months ago
  71. c11e654 Document Alibaba HALO and Samsung ONE as XNNPACK users by Marat Dukhan · 3 years, 6 months ago
  72. cee4e95 Remove PSIMD dependency by Marat Dukhan · 3 years, 6 months ago
  73. 6eaa152 Update pthreadpool dependency by Marat Dukhan · 3 years, 6 months ago
  74. 892310c Simplify parallelization in elementwise binary and Padding operators by Marat Dukhan · 3 years, 6 months ago
  75. e7223ee WASMSIMD dwconv2d 5x5s2 tests and benchmark by Frank Barchard · 3 years, 6 months ago
  76. 4e89587 Guard microbenchmarks against running microkernels on incompatible CPUs by Marat Dukhan · 3 years, 6 months ago
  77. d713e8a Refactor microbenchmarks by Marat Dukhan · 3 years, 6 months ago
  78. ff0624e Add WebAssembly dwconv2d_chw_3x3s2p1 benchmark by Frank Barchard · 3 years, 6 months ago
  79. b88d011 WebAssembly SIMD DWConv2D 3x3 stride-2 adapted from NEON by Frank Barchard · 3 years, 6 months ago
  80. 729f07b WebAssembly SIMD DWConv2D 5x5 stride 2 adapted from NEON by Frank Barchard · 3 years, 6 months ago
  81. 710612f dwconv2d_chw_ukernel_5x5p2__wasmsimd simplify shuffle expressions to a constant. by Frank Barchard · 3 years, 6 months ago
  82. 6b1629a Remove code generator for old 5x5p2 by Frank Barchard · 3 years, 6 months ago
  83. 401d97b Refactor Sigmoid operator benchmark by Marat Dukhan · 3 years, 6 months ago
  84. 1a803b6 Improve compatibility with legacy compilers by Marat Dukhan · 3 years, 6 months ago
  85. ef7c30a Fix CMake build by Marat Dukhan · 3 years, 6 months ago
  86. a160020 Support ELU operator in Subgraph API by Marat Dukhan · 3 years, 6 months ago
  87. b6bd4bc Implement ELU operator by Marat Dukhan · 3 years, 6 months ago
  88. 8f8c739 Document Depth-to-Space operator in README by Marat Dukhan · 3 years, 6 months ago
  89. ed6baaf Vector ELU microkernels by Marat Dukhan · 3 years, 6 months ago
  90. 20a0741 Web Assemble DWConv2D f32_dwconv2d_chw_ukernel_5x5p2__wasmsimd adapted from Neon by Frank Barchard · 3 years, 6 months ago
  91. b2aed94 Upgrade XNNPACK to de390d4b6fd1ca0b82bba3640fbd3cc9bbc5c4ef by Haibo Huang · 3 years, 6 months ago
  92. de390d4 EXPM1MINUS evaluation stubs by Marat Dukhan · 3 years, 6 months ago
  93. 79fd730 Fix CMake build by Marat Dukhan · 3 years, 6 months ago
  94. ffedf80 Refactor IBILINEAR CHW microkernels by Marat Dukhan · 3 years, 6 months ago
  95. 0a9c120 Enable NCHW Depth-To-Space in Subgraph API by Marat Dukhan · 3 years, 6 months ago
  96. 0e52117 NHWC version of Depth-To-Space operator by Marat Dukhan · 3 years, 6 months ago
  97. 1810c6e Limit range of fp16 test data to avoid denormals by Frank Barchard · 3 years, 6 months ago
  98. 188d104 Refactor Depth To Space NCHW2NHWC operator test by Marat Dukhan · 3 years, 6 months ago
  99. 322b21e Remove no longer used input2_pixel_stride in xnn_operator by Marat Dukhan · 3 years, 6 months ago
  100. 9cbaa63 Unify parameters of DepthToSpace NCHW->NHWC operator with other operators by Marat Dukhan · 3 years, 6 months ago