[mdlug] [Fwd: Re: [opensuse] 64 bit vrs 32 bit advantages speed etc.]

[David Lane]

Compiler settings help too.

David 

----- Original Message ----
From: Aaron Kulkis <akulkis3 at hotpop.com>
To: MDLUG's Main discussion list <mdlug at mdlug.org>
Sent: Wednesday, October 31, 2007 9:58:02 AM
Subject: Re: [mdlug] [Fwd: Re: [opensuse] 64 bit vrs 32 bit advantages speed etc.]


David Lane wrote:
> The key to testing is the applications that exploit the 64bit chip.
> 
> or  handling a multi-tasked heavy load like what is the response from
 a 
> good sized data base query.
> 
> The testing of adding the sums of the square roots from 1 to 
> 1,000,000,000 is okay but what about rendering a movie and
 > something else.
> 
> 

Right.  This shows that, in a case like this (compiling)
which is not a fundamentally 64-bit task, there's no
real performance increase.

For the time being, if you're buying new equipment,
you're probably better off getting 32-bit hardware
at rock-bottom prices, because not only the software,
but that for most tasks being done today, the nature
of the problem being solved is still usually 32-bit
or even less.

> ----- Original Message ----
> From: Aaron Kulkis <akulkis3 at hotpop.com>
> To: "mdlug at mdlug.org" <mdlug at mdlug.org>
> Sent: Tuesday, October 30, 2007 3:09:34 PM
> Subject: [mdlug] [Fwd: Re: [opensuse] 64 bit vrs 32 bit advantages
 speed 
> etc.]
> 
> 
> 
> -------- Original Message --------
> Subject: Re: [opensuse] 64 bit vrs 32 bit advantages speed etc.
> Date: Tue, 30 Oct 2007 14:42:23 -0400
> From: Buddy Coffey <bcoffey at XXXXX.XXXX <mailto:bcoffey at XXXXX.XXXX>>
> To: opensuse at opensuse.org <mailto:opensuse at opensuse.org>
> 
> 
>  >>> Has anyone run benchmarks on an identical system with 32 bit vrs
 64 
> bit?
>  >>>
>  >>>     
> Here is a benchmark of 32 bit vs 64 bit openSuSE 10.3 on a Core 2 Duo
> system.
> 
> I have both 32 bit and 64 bit versions installed in separate
 partitions
> on the same system with all updates applied.
> 
> I ran my computationally intensive code GEMACS
 (http://www.gemacs.com)
> compiled natively for both 32 and 64 bits with the Intel 9.1
 compilers.
> The code performs little I/O and zero graphics.  The code is
> multi-threaded and fairly well balanced, hence, the total CPU numbers
> are about 2X the elapsed time numbers.
> 
> 64 bit:
>   Elapsed time:  59.316 sec
>   Total CPU time: 112.43 sec
> 
> 32 bit:
>     Elapsed time: 59.749 sec
>     Total CPU time: 105.67 sec
> 
> 
> I would be glad to run other comparisons if anyone would like them.
> 
> Buddy Coffey
> Applied Research Associates
> Computational and Applied Electromagnetics
> 
> 
> _______________________________________________
> mdlug mailing list
> mdlug at mdlug.org <mailto:mdlug at mdlug.org>
> http://mdlug.org/mailman/listinfo/mdlug
> 
> 
> __________________________________________________
> Do You Yahoo!?
> Tired of spam? Yahoo! Mail has the best spam protection around
> http://mail.yahoo.com
> 
> 
>
 ------------------------------------------------------------------------
> 
> _______________________________________________
> mdlug mailing list
> mdlug at mdlug.org
> http://mdlug.org/mailman/listinfo/mdlug



_______________________________________________
mdlug mailing list
mdlug at mdlug.org
http://mdlug.org/mailman/listinfo/mdlug





__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mdlug.org/pipermail/mdlug/attachments/20071031/22bd1c1d/attachment-0001.html>