This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: -fprefetch-loop-arrays on PowerPC
- From: Richard Henderson <rth at redhat dot com>
- To: Jan Hubicka <jh at suse dot cz>
- Cc: Andreas Conz <andreasc at neuro dot informatik dot uni-kassel dot de>, mark at codesourcery dot com, gcc-patches at gcc dot gnu dot org
- Date: Sun, 2 Jun 2002 13:59:37 -0700
- Subject: Re: -fprefetch-loop-arrays on PowerPC
- References: <20020531123336.GA24188@atrey.karlin.mff.cuni.cz> <Pine.A41.4.44.0206022231510.54866-100000@nick-5.neuro.informatik.uni-kassel.de> <20020602205116.GE26845@atrey.karlin.mff.cuni.cz>
On Sun, Jun 02, 2002 at 10:51:16PM +0200, Jan Hubicka wrote:
> * loop.c (emit_prefetch_instructions): Properly place the address
> computation.
This is definitely OK for mainline.
I don't recall whether the branch is closed or not, but I would
recommend it there as well. Technically we're generating
incorrect code, only the nature of the prefetch instruction is
that we don't see the fault.
r~