This is the mail archive of the
libc-help@sourceware.org
mailing list for the glibc project.
Re: Proposal for CPU dispatching in libc
- From: Petr Baudis <pasky at suse dot cz>
- To: Agner Fog <agner at agner dot org>
- Cc: libc-help <libc-help at sourceware dot org>, lucaregini at yahoo dot it
- Date: Thu, 2 Jul 2009 14:52:05 +0200
- Subject: Re: Proposal for CPU dispatching in libc
- References: <489ACA0D.2090705@agner.org> <119aab440808070431t1a935240i948a1206b720bfe@mail.gmail.com> <489AE2B2.9010703@agner.org> <119aab440808070533q1897acc9kb0223b09d64e1922@mail.gmail.com> <489BE528.7090807@agner.org> <119aab440808080522ne73089al9a0d36b3befe24bd@mail.gmail.com> <489D537F.3010005@agner.org> <4A4C6D86.8040705@agner.org> <20090702085136.GA28788@machine.or.cz> <4A4C912C.6090109@agner.org>
On Thu, Jul 02, 2009 at 12:51:24PM +0200, Agner Fog wrote:
> Looks great! cpu-dispatching in the loader is a new invention, much more
> efficient than what is done in Intel's compiler and libraries. I hope
> you didn't patent this invention :-)
>
> The new @gnu_indirect_function attribute needs to be documented for gas.
> Is it also available in gcc as a function attribute?
You complained about noisy libc-help and are asking to move the
discussion to libc-alpha, so I'm surprised you missed this since how to
implement this in gcc as a function attribute is almost all the traffic
there is at libc-alpha in the last week or so.
> Is it possible to build a slim version of libc with certain instruction
> set versions excluded? This could be useful for embedded applications.
That would be a task for eglibc in the current situation, if/when the
ifunc architectures overlap with size-sensitive architectures.
--
Petr "Pasky" Baudis
The lyf so short, the craft so long to lerne. -- Chaucer