comp.programming

kenobi

4/17/2016 6:39:00 AM

W dniu niedziela, 17 kwietnia 2016 04:00:53 UTC+2 uzytkownik Ramine napisal:
> Hello,
>
>
> I am not crazy, please follow my proof...
>
>
> I explain better my previous proof...
>
> For a bigger part of the serial part of the Amdahl's law,
> here is my proof:
>
> If the serial part of the Amdahl's law is more bigger, so the
> chance to get contention with the USL methodology with fewer
> cores and fewer threads is bigger, so this will allow the USL
> methodology to have a better approximation of the predicted
> scalability and to forecast farther.
>
> But i will be clear on the smaller parts of the Amdahl's law:
>
> But if the serial part of the Amdahl's law is smaller , so the
> chance to get contention with the USL methodology with fewer
> cores and fewer threads will get smaller, so this will allow
> the USL methodology to forecast farther with fewer cores and
> fewer threads.
>
> But since when the serial part of the Amdahl's law is bigger
> you will hit probabilistically more the contention and this will
> make the USL methodology work, and since the chance probabilistically
> that the bigger parts that causes contention and the smaller serial
> parts that are much farther from the serial part that causes contention
> is much higher, so this this prooves mathematically that USL
> methodology is successful and is an amazing great tool that can predict
> scalability and forecast scalability much farther.
>
> This is my mathematical proof using probability.
>
>
> So now you undertand that USL methodology is a really an amazing great
> tool !
>
> And my USL programs are a really amazing great tools !
>
>
> You can download my USL programs version 3.0 with the source code from:
>
> https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-...
>
>
> Thank you,
> Amine Moulay Ramdane.

better listen to celine dijon goat, let her destroy your crappy mind to the bone, shitmakin crap floder