- cmsg cancel <nfm9ug$huq$2@dont-email.me> - 4 Updates
- About my USL programs... - 1 Update
- I have to set it more right and more precise.. - 1 Update
- I explain more the USL methodology of my USL programs... - 1 Update
- I correct, read again.... - 1 Update
- USL methodology is amazing and it works ! - 1 Update
| bleachbot <bleachbot@httrack.com>: Apr 26 01:44AM +0200 |
| bleachbot <bleachbot@httrack.com>: Apr 26 01:47AM +0200 |
| bleachbot <bleachbot@httrack.com>: Apr 26 02:06AM +0200 |
| bleachbot <bleachbot@httrack.com>: Apr 22 09:08PM +0200 |
| Ramine <ramine@1.1>: Apr 22 03:10PM -0700 Hello, A you have noticed i have given a proof that my USL programs can forecast scalability up to 10X the maximum number of cores and threads of the performance data measurements, this is useful, other than that, this 10X is the right number that optimizes the criterion of the cost, so when you want to buy bigger NUMA systems, make sure that you buy them with the right configuration that permit to add more processors and more memory, this way you will be able to test again the Computer NUMA system that you have bought empirically with my USL programs, to better forecast again farther the scalability and optimize more the criterion of the cost, so as you have noticed my USL programs are great tools and important tools ! I have included the 32 bit and 64 bit windows executables of my programs inside the zip file to easy the job for you. 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-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Apr 21 02:14PM -0700 Hello, I have to set it more right and more precise.. So here is my other proof again... If the serial part of the Amdahl's law is bigger, you have more chance to hit the contention, so there is more chance that USL will give a good approximation of the predicted scalability up to 10X the maximum number of cores and threads of the performance data measurements.., but let say the serial part of the Amdahl's law is bigger and is 1/4 the parallel part of the Amdahl's law, and let say the parallel part is variable and it makes the USL methodology escape the contention at fewer core and fewer threads, the USL methodology will have much more chance at fewer cores and fewer threads to give a good approximation up to 10X the maximum number of cores and threads of the performance data measurements.., you can feel and confirm it by statistically using more examples of the follwing above cases and calculating it.. But if the serial part is smaller , so there is more chance that USL methodology will escape contention at fewer core and fewer threads. so there is more chance that USL will give a good approximation of the predicted scalability up to 10X the maximum number of cores and threads of the performance data measurements.. So overall. the USL methodology will be able to forecast scalability with a better approximation up to 10X the maximum number of cores and threads of the performance data measurements.. This is a good news i think, and this makes USL methodology a good tool that is important and interesting to use. I have included the 32 bit and 64 bit windows executables of my programs inside the zip file to easy the job for you. 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-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Apr 25 08:07PM -0700 Hello.... I explain more the USL methodology of my USL programs... the USL's law is a rational function that is equal to: C(N) = N/(1 + α (N − 1) + β N (N − 1)) I have made mistake in my previous proof, but now i have undertood completely the USL methodology, the α is the contention and β is the crosstalk.. but when you have a parallel program that have a locked region using locks , if you empirically benchmark the scalability of this parallel program , the graph of the empirical scalability will look like the rational function above with a corresponding parameters α and β, and this behavior of the empirical world of parallel programs permit us to predict scalability using nonlinear regression or polynomial regression, this is why my USL programs are great because they permit us to predict scalability and they don't have any limitation because they give a good approximation. I have just updated my USL programs that works great to version 3.1... I have included the 32 bit and 64 bit windows executables of my programs inside the zip file to easy the job for you. You can download my USL programs version 3.1 with the source code from: https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Apr 25 07:48PM -0700 Hello...... USL methodology is amazing and it works ! My previous proof was not correct... I will explain why USL methodology is amazing and it works ! The Amdahl's law is a rational function... and when in a parallel program you have a locked region using for example locks, when you will draw the scalability graph of this parallel program , you will notice that it looks like the Amdahl's law rational function with a corresponding serial part, this is why USL methodology is working perfectly and it predicts scalability and it doesn't have a limitation,because the simulation of the empirical world in parallel programs look like the rational function of the Amdahl's law. So now you have finally understood that USL methodology is an amazing tool that predict effectively scalability using nonlinear regression or polynomial regression. I have just updated my USL programs that works great to version 3.1... I have included the 32 bit and 64 bit windows executables of my programs inside the zip file to easy the job for you. You can download my USL programs version 3.1 with the source code from: https://sites.google.com/site/aminer68/universal-scalability-law-for-delphi-and-freepascal Thank you, Amine Moulay Ramdane. |
| Ramine <ramine@1.1>: Apr 25 07:45PM -0700 Hello... USL methodology is amazing and it works ! My previous proof was not correct... I will explain why USL methodology is amazing and it works ! The Amdahl's law is a rational function... and when in a parallel program you have a locked region using for example locks, when you will draw the scalability graph of this parallel program , you will notice that it looks like the Amdahl's law rational function with a corresponding serial part, this is why USL methodology is working perfectly and it predicts scalability and it doesn't have a limitation, becaise the simulation of the empirical world in parallel programs look like the rational function of the Amdahl's law. So now you have finally undertood that USL methodology is an amazing tool that predict effectively scalability using nonlinear regression or polynomial regression. I have just updated my USL programs that works great to version 3.1... I have included the 32 bit and 64 bit windows executables of my programs inside the zip file to easy the job for you. You can download my USL programs version 3.1 with the source code from: 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