Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.programming.threads > #2596 > unrolled thread

About my Parallel Sort library

Back to article view | Back to comp.programming.threads

Contents

  About my Parallel Sort library Ramine <ramine@1.1> - 2014-09-15 14:37 -0700
    Re: About my Parallel Sort library Ramine <ramine@1.1> - 2014-09-15 14:54 -0700
    Re: About my Parallel Sort library Ramine <ramine@1.1> - 2014-09-16 10:31 -0700

#2596 — About my Parallel Sort library

Hello,


I have to clear something about my other invention called
Parallel Sort library that you will find here:

https://sites.google.com/site/aminer68/parallel-sort-library


As you have noticed i have implemented two libraries one
called Parallel Quicksort that you find here:

https://sites.google.com/site/aminer68/parallel-quicksort


And i have also invented another library that is more scalable
than my Parallel Quicksort and that is my Parallel Sort library above...


Now you have to know why my Parallel Sort library is more scalable
than my Parallel Quicksort...


If you take a look at the source code of those libraries you will
notice in my Parallel Quicksort  that you can not parallelize the 
partition procedure, so that means that there is some parts in my 
Parallel Quicksort library that are not parallizable, but in my other 
Parallel Sort library, all the parts have been parallized: the sorting 
part have been parallelized and the merging part have been parallelized 
two, so that have made my Parallel Sort library more scalable than my 
Parallel Quicksort library. I have implemented a Parallel hybrid 
divide-and-conquer merge algorithm that performs 0.9-5.8 times better 
than sequential merge, on a quad-core processor, with larger arrays 
outperforming by over 5 times. Parallel processing combined with a 
hybrid algorithm approach provides a powerful high performance result.


Hope you will be happy with my Parallel Sort library and
all my libraries are freewares that comes with the source code
this will allow you to learn more about parallel programming.


You can find all my libraries here:

https://sites.google.com/site/aminer68/


Thank you,
Amine Moulay Ramdane.

[toc] | [next] | [standalone]

#2597

Hello,

My Parallel Sort library supports Parallel Quicksort and parallel 
mergeSort and
parallel heapsort, but you have to know that my parallel quicksort
that i have implemented inside this library avoids worst case performance
and it uses the median-of-three.. so all in all i have brought to you
a wonderful Parallel library that is scalable !




Thank you,
Amine Moulay Ra,dame.

[toc] | [prev] | [next] | [standalone]

#2598

On 9/15/2014 2:37 PM, Ramine wrote:
> Hello,
>
>
> I have to clear something about my other invention called
> Parallel Sort library that you will find here:
>
> https://sites.google.com/site/aminer68/parallel-sort-library
>
>
> As you have noticed i have implemented two libraries one
> called Parallel Quicksort that you find here:
>
> https://sites.google.com/site/aminer68/parallel-quicksort
>
>
> And i have also invented another library that is more scalable
> than my Parallel Quicksort and that is my Parallel Sort library above...
>
>
> Now you have to know why my Parallel Sort library is more scalable
> than my Parallel Quicksort...
>
>
> If you take a look at the source code of those libraries you will
> notice in my Parallel Quicksort  that you can not parallelize the
> partition procedure, so that means that there is some parts in my
> Parallel Quicksort library that are not parallizable, but in my other

I mean parallelizable, not parallizable.

> Parallel Sort library, all the parts have been parallized: the sorting


i mean parallelized, not  parallized.

> part have been parallelized and the merging part have been parallelized
> two, so that have made my Parallel Sort library more scalable than my
> Parallel Quicksort library. I have implemented a Parallel hybrid
> divide-and-conquer merge algorithm that performs 0.9-5.8 times better
> than sequential merge, on a quad-core processor, with larger arrays
> outperforming by over 5 times. Parallel processing combined with a
> hybrid algorithm approach provides a powerful high performance result.
>
>
> Hope you will be happy with my Parallel Sort library and
> all my libraries are freewares that comes with the source code
> this will allow you to learn more about parallel programming.
>
>
> You can find all my libraries here:
>
> https://sites.google.com/site/aminer68/
>
>
> Thank you,
> Amine Moulay Ramdane.
>
>
>
>
>
>
>
>
>
>
>
>
>

[toc] | [prev] | [standalone]

Back to top | Article view | comp.programming.threads

csiph-web