[PATCH] Flag to enable IEEE-754 friendly FP optimizations

[Hal Finkel via llvm-commits]

----- Original Message -----
> From: "Sergey Dmitrouk" <sdmitrouk at accesssoftek.com>
> To: "Stephen Canon" <scanon at apple.com>
> Cc: "Hal Finkel" <hfinkel at anl.gov>, "llvm-commits" <llvm-commits at lists.llvm.org>, "Owen Anderson" <owen at apple.com>,
> "Mehdi Amini" <mehdi.amini at apple.com>
> Sent: Wednesday, September 23, 2015 11:40:58 AM
> Subject: Re: [PATCH] Flag to enable IEEE-754 friendly FP optimizations
> 
> (Updated mailing list address.)
> 
> Hi Steve,
> 
> > Did this stuff ever land?
> 
> No, it was relatively close, but an issue with reordering became
> visible and changed the disposition.

Is there a reason that we should not land the constant-folding patches first, and then move on to the problems of preventing reordering?

> 
> > If not, what do we need to do to make it happen?
> 
> That reordering issue is quite hard to address, the latest update I
> sent is
> here:
> 
> http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20150914/299491.html

Looks like you're waiting for a reply from me on this; I'll do that...

 -Hal

> 
> I'm afraid getting such changes in will take a lot of time too...
>  And
> that patch is far from being complete as it's missing new
> instructions and thus
> changes for all the targets (I'm getting there, or at least I think
> so).
> 
> Regards,
> Sergey
> 
> On Wed, Sep 23, 2015 at 07:55:16AM -0700, Stephen Canon wrote:
> >    Hi all
> >
> >    Did this stuff ever land?  If not, what do we need to do to make
> >    it
> >    happen?
> >
> >    Steve
> 

-- 
Hal Finkel
Assistant Computational Scientist
Leadership Computing Facility
Argonne National Laboratory