[LLVMdev] Enable changing UnsafeFPMath on a per-function basis

[Sanjay Patel]

On Wed, Jan 14, 2015 at 1:53 PM, Chandler Carruth <chandlerc at google.com>
wrote:

>
> On Wed, Jan 14, 2015 at 12:28 PM, Akira Hatanaka <ahatanak at gmail.com>
> wrote:
>
>> If modeling the flags at per-instruction level is the right thing to do
>
>
> Long term, I definitely think this is the right way to go. It lets us
> optimize code which has been inlined from an unsafe fp math function into a
> normal function.
>

Instruction-level FMF has potential benefits beyond just inlined code. A
couple of recent examples posted here:
http://lists.cs.uiuc.edu/pipermail/llvmdev/2015-January/080364.html
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20150114/158388b1/attachment.html>