[PATCH] D124741: [Clang] Add integer add reduction builtin
Florian Hahn via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Sun May 1 13:04:52 PDT 2022
fhahn accepted this revision.
fhahn added a comment.
This revision is now accepted and ready to land.
> For other reductions, we've tried to share builtins for float/integer vectors, but the fadd reduction builtins also take a starting value argument. Technically I could support float by using default values, but we're probably better off with specific fadd reduction builtins for both arguments.
I think them main issue for fadd reductions is that the `fadd` intrinsic can either do unordered or serialized, but not reduction-trees as specified for the builtins in Clang.
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
More information about the cfe-commits