-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Paul Mundt wrote: <snip> >>All software FP implementations are of course very CPU intensive. You >>have to calculate the FP result in software which takes several hundred >>cycles while in hardware it would only take just a few cycles. So FP on >>emebdded devices will probably always be dead slow - at least for the >>next future. >> > > This is not necessarily true either, and is one of the bigger reasons for > pushing EABI. It makes sense to use VFP for what it supports natively, > most of the rest of it is better left to something like soft-float. > Kernel FP emulation is slow by definition.
What's nokia's position on EABI[1]? I've heard debian has been discussing this an other distros for ARM devices (Familiar and OpenZaurus) are planning a switch too. I know glibc lacked EABI support and RMK raised some more concerns, but I haven't been paying attention to it for the past few months. So I'm very interested in nokia's point of view on this EABI thing :) regards, Koen [1] http://www.codesourcery.com/gnu_toolchains/arm/faq.html -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (Darwin) iD8DBQFDZhPIMkyGM64RGpERAiAuAJ9feX4ZGEOJKZtopkMVfjnivSyFWgCfZxKY gaZiv8f7eG6LrxuPLd8jmA8= =JDIQ -----END PGP SIGNATURE----- _______________________________________________ maemo-developers mailing list maemo-developers@maemo.org https://maemo.org/mailman/listinfo/maemo-developers