[PATCH] D56011: [x86] lower extracted fadd/fsub to horizontal vector math
Sanjay Patel via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu Jan 3 10:12:00 PST 2019
spatel marked an inline comment as done.
spatel added inline comments.
================
Comment at: test/CodeGen/X86/haddsub.ll:1034
; 512-bit vectors, float/double, fadd/fsub
----------------
This wasn't clear from the patch update comment: we have 512-bit tests and AVX512 RUN lines. However, the output is identical to regular AVX1 because we're just extracting the low 128-bits.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D56011/new/
https://reviews.llvm.org/D56011
More information about the llvm-commits
mailing list