Re: Fixed point cairo.. or no cairo?



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.

> 	Also - I notice my old friend:
> 
>   1         0.0679  ld-2.3.90.so             ld-2.3.90.so             _dl_relocate_object
>   1         0.0679  ld-2.3.90.so             ld-2.3.90.so             _dl_fixup
>   1470     99.8641  ld-2.3.90.so             ld-2.3.90.so             _dl_lookup_symbol_x
> 1236      0.5132  ld-2.3.90.so             ld-2.3.90.so             do_lookup_x
>   1236     83.9674  ld-2.3.90.so             ld-2.3.90.so             do_lookup_x [self]
>   197      13.3832  ld-2.3.90.so             ld-2.3.90.so             strcmp
>   39        2.6495  ld-2.3.90.so             ld-2.3.90.so             _dl_name_match_p
> 
> 	A small but useful part of my research in this area just got merged
> up-stream ( to binutils / glibc ) implementing a new, far more efficient
> hash for symbol lookup[1]. The punch line is if you care enough, you
> should back-port the glibc & binutils patch, and use
> -Wl,--hash-style=both or --hash-style=gnu if you want to re-do your ABI
> to save some space :-)

What ABI compatibility issues does that raise out of interest? Does
everything need to use those options and if so, are they enabled by
default in recent binutils/glibc?

Regards,

Richard

-- 
Richard Purdie
Openedhand Ltd.




[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]