I checked it now. I picked up a random function and counted # of asm
instructions. It is really so that the optimized code was shorter by some
14%. I just wonder why this does not show up in the final product speed. (My
experience from the past says that speed optimization always brings
measurable improvements.) I tried to eliminate things like callbacks to 68K
code (those I knew about), which could obscure the results. Stil no
change...
With best regards
Jan Slodicka
----- Original Message -----
From: "Ben Combee" <[EMAIL PROTECTED]>
To: "Palm Developer Forum" <[EMAIL PROTECTED]>
Sent: Wednesday, June 25, 2003 9:28 PM
Subject: Re: Armlet optimization
> At 06:00 AM 6/25/2003, Jan Slodicka wrote:
> >Hello
> >
> >I am using CW9 and I tried to test the influence of global optimizations
on
> >the armlet speed. However, the results indicate absolutely no speed
> >difference irrespectively of whether the optimizations are off or set to
> >level 2. Is it right or am I missing something?
>
> Have you checked your code at the assembly level. There should be real
> changes between level 0 and level 2, especially when using more
> registers. Are you building for Thumb or ARM code.
>
> The original ARMlet compiler in V9 has problems with optimization; when
9.2
> is released, it will have a ARM compiler that's been through another seven
> months of testing and optimization and performs a bit better.
>
> --
> Ben Combee <[EMAIL PROTECTED]>
> CodeWarrior for Palm OS technical lead
> Palm OS programming help @ www.palmoswerks.com
>
>
> --
> For information on using the Palm Developer Forums, or to unsubscribe,
please see http://www.palmos.com/dev/support/forums/
--
For information on using the Palm Developer Forums, or to unsubscribe, please see
http://www.palmos.com/dev/support/forums/
