topic Amdahl equation and scalability in IntelĀ® Moderncode for Parallel Architectures
https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Amdahl-equation-and-scalability/m-p/951929#M5185
<P></P>
<P>Hello,<BR /><BR />I have come to another interresting subject, the Amdahl's equation<BR />that is equal to 1/(S+P/N)<BR />(S:the percentage of the serial part,<BR />P: percentage of the parallel part<BR />N: the number of cores)<BR /><BR />So we have to be smart, so follow with me, i have read on some documents something that look like this: if the Serial partis 0.1% and the parallel part is 0.9% and we have 4 cores, so the Amdahl equation will equal to 1/ 0.1 + 0.225 = 3X , so this will scale to 3X, but i don't agree with this , cause i think this Amdahl equation do not give a correct picture,so imagine that the serial part take 1 second and<BR />the parallel part 9 seconds, that means S= 0.1% and P=0.9%,so with 4 cores you will say that this will run four P parts in 9 seconds<BR />and four S parts in 4 seconds this will equal 13 seconds, but the serial part will run in 4*10 seconds , so the scalability will equal 40 seconds divide<BR />by 13 seconds so this will scale to 3X, this is exactly what i have found with the Amdahl's equation. But the Amdahl's equation is not<BR />so precise and it doesn't give a correct picture, cause i think the Amdhal equation is for only the ideal contention scenario as<BR />i have just explain to you , but in a none contention scenario you will for example run four S parts in 1 seconds and four P parts in 9 seconds this will give a scalability equal to 40 seconds divide by 10 so this will scale to 4X in a none contention scenario, hence if you have less contention it will scale better than 3X , so this is why i say that the Amdahl equation doesn't give you a correct picture, and more than<BR />that if in pratice the serial part is small and there is more randomness in the parallel part, you will have less contention i think, so the example that i just gave you will scale to much better than 3X , so hope you have undertood this important ideas that i am giving you.<BR /><BR />Please read this, they say:<BR /><BR />"Amdahl's law, also known as Amdahl's argument,[1] is used to find the maximum expected improvement to an overall system"<BR /><BR />read here:<BR /><BR /><A href="http://en.wikipedia.org/wiki/Amdahl%27s_law" target="_blank">http://en.wikipedia.org/wiki/Amdahl%27s_law</A><BR /><BR /><BR />I think that's false, it's not the "maximum expected improvement to an overall system", and i have explained to you why in my previous post , what i have explained is that the Amdahl equation gives you the scalability that you will have in an IDEAL CONTENTION SCENARIO , but if you have less contention it will scale much better, and in a none contention scenario it will have a perfect scalability,so i have<BR />proved to you and explainaed to you in my previous post that the Amdahl equation doesn't<BR />give a correct picture. Hope you have understood my arguments and my ideas against Amdahl's equation.<BR /><BR /></P>
<P>You will find my parallel libraries in the following website:</P>
<P>ttp://pages.videotron.com/aminer/</P>
<P></P>
<P>Thank you,<BR />Amine Moulay Ramdane.<BR /><BR /></P>Thu, 10 Oct 2013 00:40:21 GMTaminer102013-10-10T00:40:21ZAmdahl equation and scalability
https://community.intel.com/t5/Intel-Moderncode-for-Parallel/Amdahl-equation-and-scalability/m-p/951929#M5185
<P></P>
<P>Hello,<BR /><BR />I have come to another interresting subject, the Amdahl's equation<BR />that is equal to 1/(S+P/N)<BR />(S:the percentage of the serial part,<BR />P: percentage of the parallel part<BR />N: the number of cores)<BR /><BR />So we have to be smart, so follow with me, i have read on some documents something that look like this: if the Serial partis 0.1% and the parallel part is 0.9% and we have 4 cores, so the Amdahl equation will equal to 1/ 0.1 + 0.225 = 3X , so this will scale to 3X, but i don't agree with this , cause i think this Amdahl equation do not give a correct picture,so imagine that the serial part take 1 second and<BR />the parallel part 9 seconds, that means S= 0.1% and P=0.9%,so with 4 cores you will say that this will run four P parts in 9 seconds<BR />and four S parts in 4 seconds this will equal 13 seconds, but the serial part will run in 4*10 seconds , so the scalability will equal 40 seconds divide<BR />by 13 seconds so this will scale to 3X, this is exactly what i have found with the Amdahl's equation. But the Amdahl's equation is not<BR />so precise and it doesn't give a correct picture, cause i think the Amdhal equation is for only the ideal contention scenario as<BR />i have just explain to you , but in a none contention scenario you will for example run four S parts in 1 seconds and four P parts in 9 seconds this will give a scalability equal to 40 seconds divide by 10 so this will scale to 4X in a none contention scenario, hence if you have less contention it will scale better than 3X , so this is why i say that the Amdahl equation doesn't give you a correct picture, and more than<BR />that if in pratice the serial part is small and there is more randomness in the parallel part, you will have less contention i think, so the example that i just gave you will scale to much better than 3X , so hope you have undertood this important ideas that i am giving you.<BR /><BR />Please read this, they say:<BR /><BR />"Amdahl's law, also known as Amdahl's argument,[1] is used to find the maximum expected improvement to an overall system"<BR /><BR />read here:<BR /><BR /><A href="http://en.wikipedia.org/wiki/Amdahl%27s_law" target="_blank">http://en.wikipedia.org/wiki/Amdahl%27s_law</A><BR /><BR /><BR />I think that's false, it's not the "maximum expected improvement to an overall system", and i have explained to you why in my previous post , what i have explained is that the Amdahl equation gives you the scalability that you will have in an IDEAL CONTENTION SCENARIO , but if you have less contention it will scale much better, and in a none contention scenario it will have a perfect scalability,so i have<BR />proved to you and explainaed to you in my previous post that the Amdahl equation doesn't<BR />give a correct picture. Hope you have understood my arguments and my ideas against Amdahl's equation.<BR /><BR /></P>
<P>You will find my parallel libraries in the following website:</P>
<P>ttp://pages.videotron.com/aminer/</P>
<P></P>
<P>Thank you,<BR />Amine Moulay Ramdane.<BR /><BR /></P>Thu, 10 Oct 2013 00:40:21 GMThttps://community.intel.com/t5/Intel-Moderncode-for-Parallel/Amdahl-equation-and-scalability/m-p/951929#M5185aminer102013-10-10T00:40:21Z