[ODE] Some SSE in Quick step

[Daniel Moser Tralamazza]

Quoting Nguyen Binh <ngbinh at glassegg.com>:

> Hi ,
> 
>    As recommend by Russ, I SIMDize some part of QuickStep.
>    I expect some performance gain but have not profiled it yet.
> 
>    I remember the list have a person who provide many performance
>    comparison. Now please re-run the tests... ;)
> 
>    Ah, finally, here is the link :
>    http://www.coderfarm.com/pubs/Physics/quickstep.cpp
> 
>    just dl it and overwrite old file.
> 
> -- 
> Best regards,
> 
> ---------------------------------------------------------------------
>    Nguyen Binh
>    Software Engineer
>    Glass Egg Digital Media
>    
>    E.Town Building  
>    7th Floor, 364 CongHoa Street
>    Tan Binh District,
>    HoChiMinh City,
>    VietNam,
> 
>    Phone : +84 8 8109018
>    Fax   : +84 8 8109013
> 
>      www.glassegg.com
> ---------------------------------------------------------------------
> 
> _______________________________________________
> ODE mailing list
> ODE at q12.org
> http://q12.org/mailman/listinfo/ode
> 

Hi there,

Just saw the quickstep, really great!
I was doing (no time left anymore) some 3dnow optimization, hope someone likes:
http://www.inf.furb.br/~tylenol/files/ode/

best regards,

ps: I only profiled dDot routine on my Athlon, its works :) and faster :D
Oh, and I tested an AMD memcpy implementation, I dont know if its open src, but
it's fast.

Daniel Tralamazza

"The process of preparing programs for a digital computer is especially
attractive, not only because it can be economically and scientifically
rewarding, but also because it can be an aesthetic experience much like
composing poetry or music."
Donald Knuth - The Art of Computer Programming