Displaying 3 results from an estimated 3 matches for "pr17758".
2013 Nov 10
2
[LLVMdev] [RFC] How to fix sqrt vs llvm.sqrt optimization asymmetry
Hello everyone,
The particular motivation for this e-mail is my desire for feedback on how to fix PR17758; but there is a core design issue here, so I'd like a wide audience.
The underlying issue is that, because the semantics of llvm.sqrt are purposefully defined to be different from libm sqrt (unlike all of the other llvm.<libm function> intrinsics) (*), and because autovectorization relie...
2013 Nov 11
0
[LLVMdev] [RFC] How to fix sqrt vs llvm.sqrt optimization asymmetry
..., and with the libm result, which is
NaN for x < 0:
http://pubs.opengroup.org/onlinepubs/007904975/functions/sqrt.html
Cheers,
Nick
On 10/11/2013 3:36 p.m., Hal Finkel wrote:
> Hello everyone,
>
> The particular motivation for this e-mail is my desire for feedback on how to fix PR17758; but there is a core design issue here, so I'd like a wide audience.
>
> The underlying issue is that, because the semantics of llvm.sqrt are purposefully defined to be different from libm sqrt (unlike all of the other llvm.<libm function> intrinsics) (*), and because autovectorizat...
2013 Nov 12
3
[LLVMdev] [RFC] How to fix sqrt vs llvm.sqrt optimization asymmetry
...:
> http://pubs.opengroup.org/onlinepubs/007904975/functions/sqrt.html
>
> Cheers,
> Nick
>
> On 10/11/2013 3:36 p.m., Hal Finkel wrote:
> > Hello everyone,
> >
> > The particular motivation for this e-mail is my desire for feedback
> > on how to fix PR17758; but there is a core design issue here, so
> > I'd like a wide audience.
> >
> > The underlying issue is that, because the semantics of llvm.sqrt
> > are purposefully defined to be different from libm sqrt (unlike
> > all of the other llvm.<libm function> int...