Asp Forum - I have come to an interesting subject...

Ramine

4/15/2016 4:09:00 AM

Hello,

I have come to an interesting subject...

I will now give my critics of the methodology of USL that is
using Dr. Gunther the author of USL..

Here is his methodology of USL represented in an R package:

https://cran.r-project.org/web/pac...

And read Dr. Gunther about USL here:

http://www.perfdynamics.com/Manifesto/USLscalab...

I have just thought about his methodology of using Parallel
systems as a black box using mathematical regression to quantify
and predict scalability, and i think he is wrong doing it so..

Because when the serial part is for example 1/8 of the parallel part,
you can probalistically get much more scalability with less parallel
threads and less cores than when testing with more and more cores,
because with more and more cores you will get more and more contention
on the serial part , so the Dr. Gunther methodology fails , because
it is testing the system with less cores and less threads, so it will
not get and predict the right or a better approximation of the
scalability, so i say that Dr. Gunther methodology of USL fails and is
not the right tool, and more than that , as i said before it is not
suited for critical systems that demand and require us to know
the worst-case performance.

Thank you,
Amine Moulay Ramdane.

3 Answers

kenobi

4/15/2016 7:48:00 AM

W dniu piatek, 15 kwietnia 2016 03:07:38 UTC+2 uzytkownik Ramine napisal:
> Hello,
>
>
> I have come to an interesting subject...
>
> I will now give my critics of the methodology of USL that is
> using Dr. Gunther the author of USL..
>
> Here is his methodology of USL represented in an R package:
>
> https://cran.r-project.org/web/pac...
>
> And read Dr. Gunther about USL here:
>
> http://www.perfdynamics.com/Manifesto/USLscalab...
>
>
> I have just thought about his methodology of using Parallel
> systems as a black box using mathematical regression to quantify
> and predict scalability, and i think he is wrong doing it so..
>
> Because when the serial part is for example 1/8 of the parallel part,
> you can probalistically get much more scalability with less parallel
> threads and less cores than when testing with more and more cores,
> because with more and more cores you will get more and more contention
> on the serial part , so the Dr. Gunther methodology fails , because
> it is testing the system with less cores and less threads, so it will
> not get and predict the right or a better approximation of the
> scalability, so i say that Dr. Gunther methodology of USL fails and is
> not the right tool, and more than that , as i said before it is not
> suited for critical systems that demand and require us to know
> the worst-case performance.
>
>
>
> Thank you,
> Amine Moulay Ramdane.

see you still dont getting wiser, belier
You should be aware Ram-craper that if you are treating people as an air ignoring all "dont spam here" and trash groups they can treat you adequate maneer crapmaker - your debt is already very high ^^

Ramine

4/15/2016 4:57:00 PM

On 4/14/2016 9:08 PM, Ramine wrote:
> Hello,
>
>
> I have come to an interesting subject...
>
> I will now give my critics of the methodology of USL that is
> using Dr. Gunther the author of USL..
>
> Here is his methodology of USL represented in an R package:
>
> https://cran.r-project.org/web/pac...
>
> And read Dr. Gunther about USL here:
>
> http://www.perfdynamics.com/Manifesto/USLscalab...
>
>
> I have just thought about his methodology of using Parallel
> systems as a black box using mathematical regression to quantify
> and predict scalability, and i think he is wrong doing it so..
>
> Because when the serial part is for example 1/8 of the parallel part,
> you can probalistically get much more scalability with less parallel

I mean: probabilistically, not probalistically.

> threads and less cores than when testing with more and more cores,
> because with more and more cores you will get more and more contention
> on the serial part , so the Dr. Gunther methodology fails , because
> it is testing the system with less cores and less threads, so it will
> not get and predict the right or a better approximation of the
> scalability, so i say that Dr. Gunther methodology of USL fails and is
> not the right tool, and more than that , as i said before it is not
> suited for critical systems that demand and require us to know
> the worst-case performance.
>
>
>
> Thank you,
> Amine Moulay Ramdane.
>
>
>
>
>
>
>
>
>
>
>
>
>

kenobi

4/15/2016 8:48:00 PM

W dniu piatek, 15 kwietnia 2016 15:54:48 UTC+2 uzytkownik Ramine napisal:
> On 4/14/2016 9:08 PM, Ramine wrote:
> > Hello,
> >
> >
> > I have come to an interesting subject...
> >
> > I will now give my critics of the methodology of USL that is
> > using Dr. Gunther the author of USL..
> >
> > Here is his methodology of USL represented in an R package:
> >
> > https://cran.r-project.org/web/pac...
> >
> > And read Dr. Gunther about USL here:
> >
> > http://www.perfdynamics.com/Manifesto/USLscalab...
> >
> >
> > I have just thought about his methodology of using Parallel
> > systems as a black box using mathematical regression to quantify
> > and predict scalability, and i think he is wrong doing it so..
> >
> > Because when the serial part is for example 1/8 of the parallel part,
> > you can probalistically get much more scalability with less parallel
>
> I mean: probabilistically, not probalistically.
>
dont say crapmaker.. better listen to celine dijon dork idiot brianlackin abuser

>
> > threads and less cores than when testing with more and more cores,
> > because with more and more cores you will get more and more contention
> > on the serial part , so the Dr. Gunther methodology fails , because
> > it is testing the system with less cores and less threads, so it will
> > not get and predict the right or a better approximation of the
> > scalability, so i say that Dr. Gunther methodology of USL fails and is
> > not the right tool, and more than that , as i said before it is not
> > suited for critical systems that demand and require us to know
> > the worst-case performance.
> >
> >
> >
> > Thank you,
> > Amine Moulay Ramdane.
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >

comp.programming

I have come to an interesting subject...

Ramine

kenobi

Ramine

kenobi

x Login to ForumsZone