Very important about my USL program...
I will ad something very important:
I have wrote this:
"And you can type at the command prompt: usl data.csv -d 0.2 10
the -d option will give you the derivative of the USL equation at
delta(y)/delta(x)=0.2 (it must be between 0 and 1) with a step
delta(x)=10 that will output a number and derivative of a
secant or a derivative delta(y)/delta(x) to better optimize the
criterion of the cost for a better QoS."
I have added this, because if the data is fixed/constant, such as
on my Scalable Parallel C++ Conjugate Gradient Linear System Solver
so then you can predict scalability and optimize the criterion of the
cost for a better QoS like i have explained to you.
USL methodology doesn't predict scalability because scalability
is dependant on the nature of data also but if the data is constant
so you can predict. And when you fix the data and test with USL
methodology , you can quantify the level of Contention (with strength α)
due to waiting or queueing for shared resources and the level of
Coherency (with strength β) due to the delay for data to become
consistent (or coherent) by virtue of point-to-point exchange,
and by forecasting on a fixed data you can have a better idea
of how your parallel system scales, so it is a powerful tool
Also i have easy the job for you by compiling my Universal Scalability
Law for Delphi and FreePascal programs to windows 32bit and 64bit
executables, they are really fantastic and powerful, they are GUI and
command line, please read about them and download them from here:
Amine Moulay Ramdane.