1. c83ef3b Refactor F32 MINMAX parameters for WAsm SIMD by Marat Dukhan · 2 years, 9 months ago
  2. 0bf8afa Leverage f32x4.pmin and f32x4.pmax WAsm SIMD instructions by Marat Dukhan · 3 years ago
  3. 4810905 Leverage v128.const WAsm SIMD instruction by Marat Dukhan · 3 years, 1 month ago
  4. ee029b2 Replace deprecated wasm_simd128.h intrinsics with new versions by Marat Dukhan · 3 years, 3 months ago
  5. 5b86c43 NEON versions of non-blocked F32 SpMM microkernels by Marat Dukhan · 3 years, 10 months ago
  6. e8bfcc8 Add output_stride argument in SpMM microkernels by Marat Dukhan · 3 years, 10 months ago
  7. e278a55 Pre-scale batch_size by element size in SpMM microkernels by Marat Dukhan · 3 years, 10 months ago
  8. 1717075 Check output_channels argument in SpMM microkernels by Marat Dukhan · 3 years, 10 months ago
  9. ee2df51 Use size_t in SpMM arguments by Marat Dukhan · 3 years, 10 months ago
  10. 2da0de8 SpMM move prefetch to fetch next input instead of after the current input. by Frank Barchard · 3 years, 11 months ago
  11. f673b2c SpMM microkernels advance output by byte stride by Frank Barchard · 3 years, 11 months ago
  12. a19cff3 Neon prefetch for MR >= 16 allowing 32xNR to also prefetch by Frank Barchard · 3 years, 11 months ago
  13. 8ef44cd Pipelined Web Assembly Sparse Matrix Multiply by Frank Barchard · 3 years, 11 months ago
  14. beca652 Rename unroll to x for SpMM microkernels with unrolled loop by Frank Barchard · 3 years, 11 months ago
  15. 846c0c6 Add 32x1 32x2 32x4 SPMM microkernels and remove 4x1 4x2 4x4 for WASMSIMD, Neon and SSE by Frank Barchard · 4 years ago
  16. fea2680 WAsm SpMM microkernel assign vzero vector once by Frank Barchard · 4 years ago
  17. c451e8a WAsm SpMM microkernels unrolled by 2 and 4. by Frank Barchard · 4 years ago
  18. 9e05340 Replace PSIMD SpMM microkernels with WAsm SIMD. by Frank Barchard · 4 years ago
  19. 1530116 Use more descriptive names in SpMM microkernels by Marat Dukhan · 4 years, 2 months ago
  20. 6e80fdc Add 16x1 SSE f32-SpMM kernels, which is faster than the existing 8x1 kernel. by Erich Elsen · 4 years, 4 months ago
  21. f196d01 Support CMake build with MSVC by Marat Dukhan · 4 years, 5 months ago
  22. 8ac2b3a Include immintrin.h in sources using _mm_undefined_ps by Marat Dukhan · 4 years, 5 months ago
  23. 355ab43 Rename SpMM micro-kernels by Marat Dukhan · 4 years, 6 months ago
  24. eb09a6b Rename F32/U8 output params to minmax params by Marat Dukhan · 4 years, 6 months ago
  25. f32ae34 Unify the value of $ABC variable across all templates by Marat Dukhan · 4 years, 7 months ago
  26. 40a672f Move generated micro-kernels into a subdirectory by Marat Dukhan · 4 years, 10 months ago
  27. c452eb1 Re-generate SpMM micro-kernels by Marat Dukhan · 5 years ago
  28. c6afd9b Add blocked scalar spmm kernels. by Erich Elsen · 5 years ago
  29. fcfdc0e Automated g4 rollback of changelist 274728310. by Frank Barchard · 5 years ago
  30. 9cdade3 Add prefetch instructions to 16x1, 16x2, 16x4 kernels. by Erich Elsen · 5 years ago
  31. a5ca10e Neon intrinsics clamping - Replace 2 LD1R with 1 LD2R by Frank Barchard · 5 years ago
  32. b455b12 Initial open-source release by XNNPACK Team · 5 years ago