Re: REST impact paper

It was thus said that the Great Stephen D. Williams once stated:
> On 9/8/17 10:10 PM, Sean Conner wrote:
> > I was playing around with the x86 SIMD instructions.  I have code I
> > wrote in the early 90s (in x86 assembly) that matched (I thought) quote
> > well to a vectorized version.  The core was an interative application of
> > these two functions:
> >
> >	x1 = (A * y + B) * x * (1 - x)
> >	y1 = (C * x + D) * y * (1 - y)
> >
> >   I wrote a version using the vector instructions of the x86.  I could
> >easily beat clang (which uses LLVM), but try as I might, I could not beat
> >GCC.
> 
> Using inline-vector instructions?  

  The whole function was written in assembler.  Easier to do that than to
try to handle differences of inline assembly/intrinsics between GCC and
clang.

> That can help a little, but to really get serious impact, you need to
> write the whole loop / function in vectorized assembly.  The proper
> interleaving of vector and non-vector instructions is where you can start
> getting serious multipliers. 

  Hrm.  Unfortunately, there aren't many non-vectorized instructions in the
main loop.  I've tried reordering instructions to avoid successive
modifications to a register, but that didn't do anything to speed things up.

  -spc (It's not important as it was mostly for my own amusement anyway)
_______________________________________________
FoRK mailing list
http://xent.com/mailman/listinfo/fork