From: aminer on

Hello


Parallel Compression 1.0


Author: Amine Moulay Ramdane


Description:

Parallel Zlib and Parallel Bzip algorithms that use my Thread Pool
Engine.


Please look at pzlib.pas and pbzip.pas inside the zip file - compile
and execute them...


And please see the benchmarks here:

http://pages.videotron.com/aminer/ParallelCompression/parallelbzip.htm


Language: FPC Pascal v2.2.0+ / Delphi 7+: http://www.freepascal.org/


Operating Systems: Win , Linux and Mac (x86).


Required FPC switches: -O3 -Sd -dFPC -dWin32 -dFreePascal

-Sd for delphi mode....

Required Delphi switches: -DMSWINDOWS -$H+

For Delphi 5,6,7 use -DDelphi

For Delphi 2005,2006,2007,2009,2010+ use the switch -DDELPHI2005+




Sincerely,
Amine Moulay Ramdane.

From: Alex Fraser on
On 01/04/2010 00:21, aminer wrote:
> Parallel Compression 1.0
>
> Author: Amine Moulay Ramdane
>
> Description:
>
> Parallel Zlib and Parallel Bzip algorithms that use my Thread Pool
> Engine.
>
> Please look at pzlib.pas and pbzip.pas inside the zip file - compile
> and execute them...
>
> And please see the benchmarks here:
>
> http://pages.videotron.com/aminer/ParallelCompression/parallelbzip.htm

How does this compare in terms of speed-up with
http://compression.ca/pbzip2/ ?

The closest processor benchmarked there, a Core2 Q9550, shows almost
linear speed-up from one to four threads. However, from your benchmarks
(2.7x for 3 threads and 3.3x for 4) and what I know of bzip2 this could
well be due to the difference in L2 cache between the Q6600 (8MB) and
Q9550 (12MB).

Alex
From: aminer on

Alex Fraser wrote:
> L2 cache between the Q6600 (8MB) and Q9550 (12MB).

Of course, it's not the same cache size.

And as you have noticed - look again http://compression.ca/pbzip2 -
it's not 3x for 3 nor 4x for 4 ...

Also - look inside the zip- i am using ParallelStructuredStorage.pas -
- a portable compound file system -


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


Sincerely,
Amine Moulay Ramdane.



Alex Fraser wrote:

> How does this compare in terms of speed-up withhttp://compression.ca/pbzip2/?
>
> The closest processor benchmarked there, a Core2 Q9550, shows almost
> linear speed-up from one to four threads. However, from your benchmarks
> (2.7x for 3 threads and 3.3x for 4) and what I know of bzip2 this could
> well be due to the difference in L2 cache between the Q6600 (8MB) and
> Q9550 (12MB).
>
> Alex


On Apr 1, 7:55 am, Alex Fraser <m...(a)privacy.net> wrote:
> On 01/04/2010 00:21, aminer wrote:
>
> > Parallel Compression 1.0
>
> > Author: Amine Moulay Ramdane
>
> > Description:
>
> > Parallel Zlib and Parallel Bzip algorithms that use my Thread Pool
> > Engine.
>
> > Please look at pzlib.pas and pbzip.pas inside the zip file - compile
> > and execute them...
>
> > And please see the benchmarks here:
>
> >http://pages.videotron.com/aminer/ParallelCompression/parallelbzip.htm
>
> How does this compare in terms of speed-up withhttp://compression.ca/pbzip2/?
>
> The closest processor benchmarked there, a Core2 Q9550, shows almost
> linear speed-up from one to four threads. However, from your benchmarks
> (2.7x for 3 threads and 3.3x for 4) and what I know of bzip2 this could
> well be due to the difference in L2 cache between the Q6600 (8MB) and
> Q9550 (12MB).
>
> Alex