[PATCH] Don't generate 64-bit movd after cmpneqsd in 32-bit mode (PR19059)

Hans Wennborg hans at chromium.org
Mon Mar 10 18:14:42 PDT 2014

  On Mon, Mar 10, 2014 at 5:17 PM, Jim Grosbach <grosbach at apple.com> wrote:
  > While it does seem a bit roundabout, it does actually capture the semantics
  > of what’s happening more accurately, which is good, and without a
  > target-specific ISD node or a pseudo-instruction. I like the idea.
  > On Mar 10, 2014, at 5:11 PM, Craig Topper <craig.topper at gmail.com> wrote:
  > I was sort of wondering if we could scalar_to_vector this to a vector with
  > the right sized elements, bitcast that to an f32 vector, then extract
  > element on that. I'll admit its rather convoluted.

  That seems to work :) New patch uploaded.


More information about the llvm-commits mailing list