- cmsg cancel <nd6362$r7c$2@dont-email.me> - 6 Updates
- USL for Delphi and FreePascal version 1.1 - 1 Update
- Yet about USL - 2 Updates
- About USL version 1.0 - 1 Update
- Universal Scalability Law (USL) version 1.0 - 2 Updates
| bleachbot <bleachbot@httrack.com>: Mar 26 02:38PM +0100 |
| bleachbot <bleachbot@httrack.com>: Mar 26 02:43PM +0100 |
| bleachbot <bleachbot@httrack.com>: Mar 26 03:08PM +0100 |
| bleachbot <bleachbot@httrack.com>: Mar 26 04:05PM +0100 |
| bleachbot <bleachbot@httrack.com>: Mar 26 04:12PM +0100 |
| bleachbot <bleachbot@httrack.com>: Mar 26 07:34PM +0100 |
| Ramine <ramine@1.1>: Mar 26 02:37PM -0700 Hello... USL for Delphi and FreePascal version 1.1 I have updated USL for Delphi and FreePascal to version 1.1, now you can pass a second parameter that is a number to predict its scalability, for example by typing at the command prompt this: usl data.csv 20 Here it will predict the scalability of 20 cores. Here is the output: Peak number is: 449.188 Predicted scalability peak is: 18.434 Predicted scalability for number 20.00 is: 10.245 Coefficient of determination R-squared is: 0.995 Here in the output, the peak number is the peak number of cores (look inside the csv file) that will give the Predicted scalability peak that is: 18.434X and Predicted scalability for number 20.00(that means 20 cores) is: 10.245X You can download the new version 1.1 from: https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Mar 26 11:09AM -0700 Hello, Hope you have read my previous post about USL... I have played with the USL ported to the R language here: http://www.inside-r.org/packages/cran/usl/docs But when i have used the non-linear regression by passing "nlxb" as a method , it didn't work on the data.csv performance data file, because it reported that: Number of cores peak scalability is: Inf And that's incorrect, because it must be 449, so i have used polynomial regression and other appromations on my USL program ported to Delphi and FreePascal and it has worked correctly. Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Mar 26 11:16AM -0700 I correct, read again... Hello.... Hope you have read my previous post about USL... I have played with the USL ported to the R language here: http://www.inside-r.org/packages/cran/usl/docs But when i have used the non-linear regression by passing "nlxb" as a method , it didn't work on the data.csv performance data file, because it reported that: Number of cores peak scalability is: Inf And that's incorrect, because it must be 449, so i have used polynomial regression and other approximations on my USL program ported to Delphi and FreePascal and it has worked correctly. Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Mar 26 10:12AM -0700 Hello, Hope you have read my previous post about my USL for Delphi and FreePascal. Please take a look at the source code in the zip file: When you compile the usl.pas , please type this in the command prompt: usl data.csv Here is the output of my program: Peak number is: 449.188 Predicted scalability peak is: 18.434 Coefficient of determination R-squared is: 0.995 The peak number is the peak number of cores (look inside the csv file) that will give the Predicted scalability peak that is: 18.434X I have used a polynomial regression and i have done other approximations to find the predicted scalability peak when the derivative must equal an approximation of 0 and this when the USL coefficient beta equal 0. This is all about mathematics. You can download my USL program from: https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Mar 26 09:44AM -0700 Hello, I have just implemented a very powerful tool called USL using mathematics, please read about it here: http://www.perfdynamics.com/Manifesto/USLscalability.html Here it is: Universal Scalability Law (USL) for Delphi and FreePascal version 1.0 Author: Amine Moulay Ramdane. Email: aminer@videotron.ca Description: This program analyzes system performance data with the Universal Scalability Law (USL), and it compiles with Delphi XE versions and FreePascal. You have to supply the performance data as a csv file format, please take a look at the supplied csv file called "data.csv", the first line of the names of the colomuns of the csv file must be commented by "#" character. Just compile the usl.pas program and run it by executing it on the command prompt like this: usl data.csv The Universal Scalability Law (USL) was developed by Dr. Neil J. Gunther. It can be used to analyze system performance data in order to learn more about the scalability limitations of the system. Details are presented in the book *Guerrilla Capacity Planning*. Authors of Universal Scalability Law website: http://www.perfdynamics.com/ - Platform: Win32 ,Win64,Linux,OSX Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Mar 26 09:50AM -0700 Hello, You can download it from here: https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-freepascal Thank you, Amine Moulay Ramdane. |
| You received this digest because you're subscribed to updates for this group. You can change your settings on the group membership page. To unsubscribe from this group and stop receiving emails from it send an email to comp.programming.threads+unsubscribe@googlegroups.com. |
No comments:
Post a Comment