Re: Mach-O Speed ?!?!?!?!?
Re: Mach-O Speed ?!?!?!?!?
- Subject: Re: Mach-O Speed ?!?!?!?!?
- From: Mark Eaton <email@hidden>
- Date: Tue, 5 Feb 2002 14:27:50 -0800
On Tuesday, February 5, 2002, at 12:20 AM, Bruno Blondeau wrote:
on 5/02/02 5:50, email@hidden -
email@hidden wrote:
Subject: Re: Mach-O Speed ?!?!?!?!?
From: Chilton Webb <email@hidden>
To: Cocoa Dev <email@hidden>
I've been going on the exact opposite premise, that the goal of all
great and powerful developers should be to move their Carbon apps to
Mach-O as soon as possible in order to make their software run faster.
Was I wrong?
Well, it's simply because CFM is not a first class citizen in MacOS X.
It seems there is a translation from CFM to MachO at runtime, so that's
why
Carbon apps should switch to MachO...
I remember having seen several developers complaining seeing slowdowns
from
processor intensive (graphic-less) applications when moving from
CLASSIC CFM
to MacOS X & Mach-O. And it's not a matter of MacOS X sucking CPU
cycles in
the background since in a lot of cases, the developer also noticed the
application was running faster under Classic than under MacOS X
(natively)...
Maybe there was some other problems in these cases, but it seems there
is
something that needs to be done here.
I could certainly see degenerate cases where certain types of code could
take a slowdown that is noticeable. PC relative addressing on PPC causes
a pipeline flush and any branch prediction is discarded.
I don't think in the general case that the performance hit would be
anywhere near 40%, but its certainly more than zero.
-mark
_______________________________________________
cocoa-dev mailing list | email@hidden
Help/Unsubscribe/Archives:
http://www.lists.apple.com/mailman/listinfo/cocoa-dev
Do not post admin requests to the list. They will be ignored.