This is the mail archive of the crossgcc@sourceware.cygnus.com mailing list for the crossgcc project.

See the CrossGCC FAQ for lots more infromation.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]

Re: Fast Floating Point Alternatives for 68K and GCC?

To: David Williams <davidwilliams at ozemail dot com dot au>
Subject: Re: Fast Floating Point Alternatives for 68K and GCC?
From: Peter Jeremy <peter dot jeremy at alcatel dot com dot au>
Date: Mon, 6 Mar 2000 15:19:10 +1100
Cc: crossgcc at sourceware dot cygnus dot com
References: <001001bf86c9$34eaba10$2a84c389@fiddesenterprises.com><38C32941.D809586A@ozemail.com.au>

On 2000-Mar-06 14:50:07 +1100, David Williams <davidwilliams@ozemail.com.au> wrote:
>Being fairly ignorant of coldfire, does this work on plain old 68000 core
>processors?

Based on a quick look, yes it does.

> Would the some sort of speed improvement be expected on 68000 core
>processors

No, it'll be slower than the original code.  Most of the conditional
assembly has been deleted, leaving only the CF-specific code.  In
a number of cases, single 68k instructions have to be expanded for
the CF - and the expanded sequences will be slower on the 68k.

(And if you're really after quick-and-dirty FP arithmetic, IEEE isn't
the way to go.  It is comparatively slow (though far more robust).
You might like to try and find a copy of Motorola's FFP).

Peter

------
Want more information?  See the CrossGCC FAQ, http://www.objsw.com/CrossGCC/
Want to unsubscribe? Send a note to crossgcc-unsubscribe@sourceware.cygnus.com

References:
- RE: Fast Floating Point Alternatives for 68K and GCC?
  - From: David J. Fiddes
- Re: Fast Floating Point Alternatives for 68K and GCC?
  - From: David Williams

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]