[PATCH] D99565: [X86] Support replacing aligned vector moves with unaligned moves when avx is enabled.

[Craig Topper via Phabricator via llvm-commits]

craig.topper added inline comments.


================
Comment at: clang/lib/Driver/ToolChains/CommonArgs.cpp:1723
+  if (Args.hasArg(options::OPT_fuse_unaligned_vector_move))
+    addArg(Twine("-x86-enable-unaligned-vector-move=true"));
+  else if (Args.hasArg(options::OPT_fno_use_unaligned_vector_move))
----------------
Could you just put this in target features in the IR and not have to deal with LTO specially? Similar to what we do with retpoline, speculative loading hardening, etc.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D99565/new/

https://reviews.llvm.org/D99565