This is the mail archive of the crossgcc@sources.redhat.com mailing list for the crossgcc project.

See the CrossGCC FAQ for lots more information.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: Floating point emulation

From: Peter Barada <pbarada at mail dot wm dot sps dot mot dot com>
To: y dot rutschle at indigovision dot com
Cc: Daniel dot Lidsten at combitechsystems dot com, crossgcc at sources dot redhat dot com
Date: Mon, 2 Dec 2002 10:49:57 -0500
Subject: Re: Floating point emulation
References: <004B1D7A5257174C9044A1B7BD0E60ED232C6A@ratatosk.combitechsystems.com> <20021129094643.W1687@localhost>

>I haven't used floats in years (decades? hmm) so don't quote
>me on that...
>(Incidently, if you are compiling with -msoft-float, I don't
>expect that using doubles will "increase performance", as
>you'll double the amount of work the processor has to do...)

It all depends on the hardware implementation of the FPU.  If the FPU
can only operate in double precision, then to properly model single
precision operations requires rounding instructions to be added after
every operation to force the final result to appear as if it was
calculated in single precision.  This can indeed slow it down.

-- 
Peter Barada                                   Peter.Barada@motorola.com
Wizard                                         781-852-2768 (direct)
WaveMark Solutions(wholly owned by Motorola)   781-270-0193 (fax)

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

Follow-Ups:
- Re: Floating point emulation
  - From: Yves Rutschle

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