On Fri, 2006-08-11 at 09:53 +0300, Jorn Baayen wrote:
> On Tue, 2006-08-08 at 11:03 +0100, Richard Purdie wrote:
> > On Tue, 2006-08-08 at 10:24 +0100, Michael Meeks wrote:
> > >   Ah - interesting; so poking at:
> > > 
> > > http://www.o-hand.com/~jorn/pango-benchmarks/28/full-report.txt
> > > 
> > >   I see a ton of vmlinux stuff apparently emulating the FPU - but,
> > > unfortunately, it doesn't appear to tell me where those calls came from
> > > (?) is there a pretty picture that shows that ? [ something like
> > > 'sysprof' output would do that I guess ].
> > 
> > Floating point instructions generate CPU exceptions on ARM and I don't
> > think oprofile or sysprof support back tracing through the CPU exception
> > handler.
> > 
> > One solution would be to run the tests against a soft floating point
> > image, then the floating point instructions would show up as any other
> > library instead of generating exceptions. They have slightly less
> > overhead in that case but it would show them in context in the stack
> > back traces.
> 
> Done: http://www.o-hand.com/~jorn/pango-benchmarks/210-softfloat/

Now if we look at the cairo profile here (cairo.txt), we see that 7.7%
and 3.8% are you used by __muldf3() and __adddf3(), respectively. These
are softfloat functions, confirming suspicions that FP is a problem.


Jorn

-- 
OpenedHand Ltd.
http://o-hand.com/

_______________________________________________
Performance-list mailing list
[email protected]
http://mail.gnome.org/mailman/listinfo/performance-list

Reply via email to