tree eec22ab76dfa524c2796e76304252c12a075d930
parent 62d1a080e69e3c5e98840e000135afa7c688a77b
author Simon Pilgrim <llvm-dev@redking.me.uk> 1762960838 +0000
committer GitHub <noreply@github.com> 1762960838 +0000
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJpFKXGCRC1aQ7uu5UhlAAA+I8QADGYUia+5Pt8uHCTAhTPh5l9
 Kb2I1gRtFn8HQXWIcE7Ivw1sejslyKoiQeGEbkAl9PF+mlsT979FWUmiwFv/1eth
 13DEyYFHe/E8Y7+cXZg1gkqn5FzmVZ4Q8qQPz/6x7ALWbBes3eoKfZPpO1iIX8X3
 Od6nLdMVnkmr8zmR2iYSw7ybUhNnHAdsUT4+2luvm67SLsJEFyKPBk+LBHq+iiju
 MkZYGciclA95YdSfAFcsSy6VYwwnHkjz2SUcC/+RZk+GFAAnyVDMv8dkQ4XZ6HB7
 Ac6AT7Nnj51GYdaHo1P8tI+8M1Vm8iNecCAIndUCKoQc/z67TvvFdR82Ft8KoQnG
 QcEIt+LpU361CcVe1TkdbkT3E+L8G+nGcOBt/mdNwFdjilXF2M6of0MSXa+iScBg
 F2qHzYbyDiud6zUNMCAvYxMGRMPPNuYcHqbmOl8Mby/aJn/LI+luzzcwdKocUEdp
 q4pzn+GNHQWYOcBENTmX0XqRLAwC0h4QrYX8JhhBu5+tHq9esx5KFM1zMpxyfrVy
 3n3jd+9IuwEQKH9zPiXY4/5Bh78i6TdZc3ww5EUgeeyEibjMXiVTOkEgi+pXeUg3
 TnxmtmgotJ8HjH58pR5ljxGzWdZppomRpFoSxBmGOZvZC7Ua443kjw7chZq3JaHE
 uVC835xCkFIepKG+YqZm
 =HqLN
 -----END PGP SIGNATURE-----
 

[X86] AVX512 optimised CTLZ/CTTZ implementations for i256/i512 scalars (#164671)

Make use of AVX512 VPLZCNT/VPOPCNT to perform the big integer bit counts per vector element and then use VPCOMPRESS to extract the first non-zero element result.

There's more we can do here (widen/split other vector widths etc.) - but this is a good starting point.