This is the mail archive of the
mailing list for the GCC project.
Re: stepanov on sparc; sparc backend scheduling issues
- To: Gabriel Dos Reis <gdr at codesourcery dot com>
- Subject: Re: stepanov on sparc; sparc backend scheduling issues
- From: Jakub Jelinek <jakub at redhat dot com>
- Date: Sat, 26 May 2001 22:35:25 +0200
- Cc: Joe Buck <jbuck at synopsys dot COM>, Richard Henderson <rth at redhat dot com>, David Edelsohn <dje at watson dot ibm dot com>, Mark Mitchell <mark at codesourcery dot com>, jfm2 at club-internet dot fr, gcc at gcc dot gnu dot org
- References: <200105260115.SAA08268@toledo.synopsys.com> <email@example.com>
- Reply-To: Jakub Jelinek <jakub at redhat dot com>
On Sat, May 26, 2001 at 08:50:13AM +0200, Gabriel Dos Reis wrote:
> Joe Buck <jbuck@synopsys.COM> writes:
> | ...Certainly we are best off by default using only the
> | v7 instruction set, but I think we should tune for whatever is the
> | most common architecture currently in use.
> I 100% agree with Joe.
> | I don't know if that should be Ultrasparc
> Maybe v9?
If -mtune= should default to something different to -mcpu=, then surely
-mtune=ultrasparc, there is no tuning for v9, since v9 is not a chip (though
-mcpu=v9 -mtune=ultrasparc makes sense).
gcc does not tune for HAL sparc64 chips and even if it did, UltraSPARCs are
far more common.