This is the mail archive of the
mailing list for the GCC project.
Re: powerpc & unaligned block moves with fp registers
- To: dj at redhat dot com, dje at watson dot ibm dot com
- Subject: Re: powerpc & unaligned block moves with fp registers
- From: mike stump <mrs at windriver dot com>
- Date: Fri, 2 Nov 2001 13:11:55 -0800 (PST)
- Cc: gcc at gcc dot gnu dot org
> To: DJ Delorie <firstname.lastname@example.org>
> cc: email@example.com
> Date: Thu, 01 Nov 2001 23:59:12 -0500
> From: David Edelsohn <firstname.lastname@example.org>
> DJ> Um, the 603e in big-endian mode can do unaligned integer moves all by
> DJ> itself, but traps sufficiently unaligned fp moves, according to the
> DJ> programming manual from Motorola. I'm not sure why you'd think that
> DJ> it's the operating system's fault that it's doing this, especially in
> DJ> an embedded system with no operating system.
> Because this is a performance issue. SLOW_UNALIGNED_ACCESS
> already discourages "sufficiently unaligned fp moves". Only the
> customer's OS requires stricter alignment just for FPRs. The current
> definition of SLOW_UNALIGNED_ACCESS is good for everyone else.
Our issue is not a performance issue. It is a correctness issue.
While SLOW may work in our case, SLOW isn't descriptive of the right
fix. The right description is, don't use the resource, period. We
don't want to lie and pretend it is slow to try and discourage the use
of the resource. As Master Yoda once said, Lying leads to suffering.
Saying it is slow, is a lie.