On Fri, Mar 29, 2019 at 5:51 PM Arsenault, Matthew via llvm-dev < llvm-dev at lists.llvm.org> wrote:> A few things I’ve been thinking about: > > - Is anyone working on finishing the migration to using the new fneg > instruction? > > What did you have in mind? I was not aware that there is work pending.> - Controls for allowing and/or mandating denormal flushing > - Making denormal-fp-math attribute per FP type > - FTZ flag > > This would be useful to us too.> - Dealing with constrained and unconstrained versions of target FP > intrinsics > > That's really interesting and not something that I had anticipated. Itneeds to be discussed... -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20190401/cf1b6d5f/attachment.html>
> On Apr 1, 2019, at 11:30 AM, Cameron McInally via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > What did you have in mind? I was not aware that there is work pending. >As far as I know, fneg isn’t constant folded. The tests haven’t been migrated, and clang is still emitting fsub -0.0, x. I’m not sure what the state of the rest of the optimizations is, but I just remember the initial instruction getting added. -Matt -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20190401/8f3c351f/attachment.html>
On Mon, Apr 1, 2019 at 11:52 AM Matt Arsenault <arsenm2 at gmail.com> wrote:> > > On Apr 1, 2019, at 11:30 AM, Cameron McInally via llvm-dev < > llvm-dev at lists.llvm.org> wrote: > > What did you have in mind? I was not aware that there is work pending. > > > As far as I know, fneg isn’t constant folded. >Ah, yes. I did know that, but forgot. It's now on my todo list...> The tests haven’t been migrated, and clang is still emitting fsub -0.0, x. > I’m not sure what the state of the rest of the optimizations is, but I just > remember the initial instruction getting added. >Huh, I did not know this. I thought I did a visual inspection and saw that FNeg IR was being generated by Clang, but I'm probably wrong. Also on my todo list now. Thanks, Matt! -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20190401/d1050232/attachment.html>