>IMO Sun has done its fair share of misleading benchmarking, however this entry is relatively interesting.

Assuming suncc even generates correct code.
Some time ago I spent time analyzing some testcases from
http://embed.cs.utah.edu/embarrassing/dec_09/
(very interesting site btw if you really want
to compare optimizations of different compilers)
and there were several quite clear bugs in suncc
volatile code generation. While there was some
dubious code from other compilers too suncc was
the only one with a large number of problems.

Overall based on that experience I would say the global
optimizations of the major compilers on non tuned
code seem to be mostly similar.

-Andi


>http://blogs.sun.com/BestPerf/entry/free_compiler_wins_nehalem_race
>
>Without autopar, and with base flags only, it handily outperforms gcc on specfp2006 on Nehalem.
>
>http://blogs.sun.com/jhenning/entry/sun_studio_trounces_intel_compiler
>>
>
>Showed it beating icc in a similar configuration, although both using peak flags in that case.
>
>I have a theory that on a rather large and popular (commercial) enterprise software
>package (so primarily integer), sun cc does significantly better than gcc as well
>(though not as large gap as these FP tests). I'm handwaving a bit based on reported
>benchmark numbers from various sources, so my anecdote doesn't carry much weight unfortunately.