Re: Patch to fix _mm_sqrt_sd intrinsic

[Daniel Berlin <dberlin at dberlin dot org>]

On Thu, 25 Aug 2005, Kelley Cook wrote:

> > On Wed, 2005-08-24 at 20:13 -0700, Richard Henderson wrote:
> > > On Wed, Aug 24, 2005 at 05:45:20PM -0700, Fariborz Jahanian wrote:
> > > > The Intel reference manuals say it shall be this:
> > > >
> > > >      __m128d _mm_sqrt_sd( __m128d );
> > >
> > > Not the one I'm looking at, it doesn't.
> > >
> > >   __m128d __mm_sqrt_sd (__m128d a, __m128d)
> > >
> > >   Computes the square root of the lower DP FP value of b.
> > >   The upper DP FP value is passed through from a.
> > >
> > >     r0 := sqrt(b0)
> > >     r1 := a1
> >
> > same here for 9.0 (the latest):
>
> On the other hand, both my hardcopy of the Intel Instruction Set reference 
> and the current ftp://download.intel.com/design/Pentium4/manuals/25366716.pdf 
> version
> has exactly as Fariborz has proposed:
Okay, but the intrinsic they actually have in emmintrin.h and friends, 
matches the compiler reference manual.

So i'd guess that people either haven't been programming with mm_sqrt_sd, 
or have been using the form the intel compilers accept.
What does MSVC (or any other compile accepting the intrinsics) have in the 
header files for mm_sqrt_sd?