Hunting for performance regressions in libstdc++

[Dan Kegel <dank at kegel dot com>]

I have a sneaking suspicion that some of my app's
performance problems might be due to gcc-3.4.3's libstdc++
being somehow slower than SGI's STL, so I'm planning
on doing some performance testing of various implementations
of STL.

Rather than building my app with the various STLs
(which might be somewhat painful), I'd like to start
with small to medium benchmarks.

So far, I've found five candidates:

tramp3d (http://www.tat.physik.uni-tuebingen.de/~rguenth/gcc/tramp3d-v3.cpp.gz)
botan (http://botan.randombit.net/)
have been mentioned recently as C++ test cases.
Both reportedly have regressed in performance recently
(http://www.mail-archive.com/gcc@gcc.gnu.org/msg05755.html)

Peter Schmid ran some performance regression tests
three-four years ago using bench_plus_plus:
http://gcc.gnu.org/ml/libstdc++/2001-03/msg00188.html
http://gcc.gnu.org/ml/libstdc++/2002-03/msg00165.html
and found performance regressions in gcc-3.1 relative to gcc-2.95.3
Perhaps it's time to run that suite again.

http://gcc.gnu.org/PR21314 is a report of a performance
regression with gcc-4.0 and -Os.

I suppose I could run http://www.kegel.com/dkcorbabench/
against ace/tao with both client and server on the same
machine, and a small number of connections.  Not sure
this is a good STL benchmark, but ACE/TAO is kind of
a poster child for large C++ frameworks, so it's worth a shot.
I'd be careful to get ace to use STL (http://www.theaceorb.com/faq/#138).

Any more come to mind?

Thanks,
Dan


--
Trying to get a job as a c++ developer?  See http://kegel.com/academy/getting-hired.html