ts-7000
[Top] [All Lists]

[ts-7000] Re: speed improvements using eabi?

To:
Subject: [ts-7000] Re: speed improvements using eabi?
From: "charliem_1216" <>
Date: Fri, 22 May 2009 13:49:58 -0000
--- In  "j.chitte" <> wrote:
>
> Hi,
> 
> has anyone benchmarked TS72xx running eabi only against a standard TSlinux 
> installation.

Hi --

See here:
http://www.freelists.org/post/linux-cirrus/26-performance-loss-on-TS7250-vs-24

But!  Note at the time of that post, I was chasing a performance problem with 
2.6 kernels that turned out to be the processor was running half-speed.  
(That's the origin of the 'nFast bit' patch ...).  So when reading the post 
above, you need to *double* the performance of the 2.6 OABI and EABI.  Not sure 
I ever re-did the benchmarks with the CPU running full-speed.
 
> 
> I've seen quite a few comments on consideralbe improvement in floating point 
> work but what sort of gains are there general performance and interger 
> insensive tasks?
> 
> I make frequent gnuplot runs that take around 16s on TSlinux. Will the more 
> efficent eabi provide noticable gains here?

Gnuplot can be very FP intensive, IIRC, so I'm sure you would approach the  
18-20X speed up for EABI FP performance.  I'd guess your runs would be under a 
second, but it depends on what you have gnuplot doing.

regards, ....... Charlie

> 
> TIA.
> 
> /js
>




------------------------------------

Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/ts-7000/

<*> Your email settings:
    Individual Email | Traditional

<*> To change settings online go to:
    http://groups.yahoo.com/group/ts-7000/join
    (Yahoo! ID required)

<*> To change settings via email:
     
    

<*> To unsubscribe from this group, send an email to:
    

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/

<Prev in Thread] Current Thread [Next in Thread>
Admin

Disclaimer: Neither Andrew Taylor nor the University of NSW School of Computer and Engineering take any responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the birding-aus mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU