About my parallelsort library ...

[aminer]

Hello,

If you take a look at the graph of the benchmarks that i did on
my parallelsort library , you will notice that i am getting a superlinear
speed up , look at this:

http://pages.videotron.com/aminer/parallelsort/parallelsort.htm


So a question follows:

How am i getting this superlinear speed up on this example using
10 millions of strings?


My answer:

Cause when you are using mutliple threads and mutiple cores,
my parallelsort library is maximizing BETTER the locality , that means
the caches are used more efficiently when more threads and more cores
are used .



You can download my parallelsort library from:


http://pages.videotron.com/aminer/



Thank you.


Amine Moulay Ramdane

[Blaazen]

Nice. 

There are so many interesting things on your page (and I have not enough time to testing).

[aminer]

I wrote:

>Cause when you are using mutliple threads and mutiple cores,
>my parallelsort library is maximizing BETTER the locality

I mean exploit better the cache locality.


thank you.



Amine Moulay Ramdane.