[pooma-dev] KCC versus icc

[Jeffrey Oldham]

Paul A. Renard wrote:
> Hope I'm asking the correct crowd...
> 
> Given the following:
> 
>  const int N=128;
>  Array<2,complex<float> > u(N,N);
>  Iota<2>::Iota_t ij(iota(u.domain());
>  Iota<2>::Index_t I(ij.comp(0));
>  Iota<2>::Index_t J(ij.comp(1));
>  Array<1,complex<float> > cx(N), cy(N);
> 
>  // Values for u, cx, cy are filled elsewhere.
> 
>  // Then the following is called:
>  void compute(){
>   u *= cx(I)*cy(J);    // runs 4X slower with icc than KCC
>  }
> 
>  When I time this routine, I find that it runs about 4X slower when 
> compiled with Intel's icc (Version 7, -O3 -DNOPAssert -DNOCTASSERT) than 
> with KCC (version 4.0f, +K3 -DNOPAssert, -DNOCTAssert).  As expected, 
> the KCC version runs as fast as hand-written loops.
> 
> Do others observe this same sluggish behavior with icc?  Am I missing 
> some obvious compile flag? 
> 
> thanks
> Paul

This is the first such report on icc's bad behavior.  Perhaps someone 
else will have some idea.

Arch Robison (robison at kai.com) moved to work on icc.  He would probably 
be interested in the smallest test case you can construct.  If you send 
him information, would you please consider ccing me?

Thanks,
Jeffrey D. Oldham
oldham at codesourcery.com