[lnkForumImage]
TotalShareware - Download Free Software
Confronta i prezzi di migliaia di prodotti.
Asp Forum
 Home | Login | Register | Search 


 

Forums >

comp.programming

Here is my solution and my new intuitive proof about the USL methodology...

Ramine

4/17/2016 2:06:00 AM

Hello,

You have seen me thinking and writing yesterday about the USL
methodology...

Here is my solution and my new intuitive proof about the USL methodology...

USL methodology that uses nonlinear regression or poylynomial regression
is a methodology that is based on probability, i explain:

When the serial part of the overall parallel program is
more bigger, so the chance to score better on the contention and the
crosstalk is higher and this will constitute a useful approximation
of the Alpha and Beta coefficient of USL, because when the chance is
higher in probability the contention and the crosstalk of the predicted
scalability will be a better approximation, but when the serial part
of the overall parallel program is more and more smaller so the chance
to score better on the contention and the crosstalk is more and more
lower, so the result of this new and more intuitive proof constitute a
good approximation that enable the forecasting of the scalability much
farther.. this is what make the USL methodology really amazing and
successful , so i think that my USL programs are great and important
tools that predict scalability.


So i think that USL methodology is a great tool.

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.