Re: PATCH: Fix ll/sc for mips (take 3)

[Daniel Jacobowitz <dan@debian.org>]

On Fri, Feb 01, 2002 at 03:15:13PM -0800, H . J . Lu wrote:
> On Fri, Feb 01, 2002 at 06:01:26PM -0500, Daniel Jacobowitz wrote:
> > On Fri, Feb 01, 2002 at 10:29:43AM -0800, H . J . Lu wrote:
> > > On Fri, Feb 01, 2002 at 12:45:02PM +0100, Maciej W. Rozycki wrote:
> > > > On Thu, 31 Jan 2002, H . J . Lu wrote:
> > > > 
> > > > > > Gas will fill delay slots. Same object codes will be produced, so I
> > > > > > think you don't have to do that by hand. 
> > > > > 
> > > > > It will make the code more readable. We don't have to guess what
> > > > > the assembler will do. 
> > > > 
> > > >  But you lose a chance for something useful being reordered to the slot.
> > > > That might not necessarily be a "nop".  Please don't forget of indents
> > > > anyway.
> > > > 
> > > 
> > > Here is a new patch. I use branch likely to get rid of nops. Please
> > > tell me which indents I may have missed.
> > 
> > Can you really assume presence of the branch-likely instruction?  I
> > don't think so.
> 
> Why not? Can you show me a MIPS II or above CPU which doesn't have
> branch-likely instruction? From gcc,
> 
> /* ISA has branch likely instructions (eg. mips2).  */
> /* Disable branchlikely for tx39 until compare rewrite.  They haven't
>    been generated up to this point.  */
> #define ISA_HAS_BRANCHLIKELY    (mips_isa != 1                          \
>                                  /* || TARGET_MIPS3900 */)                      
> 
> Did I miss something?

My fault.  I was indeed thinking of the tx39, which is not normally
MIPS2.

-- 
Daniel Jacobowitz                           Carnegie Mellon University
MontaVista Software                         Debian GNU/Linux Developer