[Beowulf] re: open64 from AMD (was newbie)

[Mark Hahn]

> I had no idea that the MIPSPro compiler had been resurrected so I was 
> interested to hear about the AMD effort.

me too, but it brings up a thorny topic: how to compare the performance
of different compilers?  the obvious "run it on your code and see" is 
not helpful in my case, since my goal is to have a good choice for 
a large shared HPC organization (several thousand users currently.)

macrobenchmarks (gromacs-level stuff) are excellent and realistic,
but it seems like performance is often dominated by small config tweaks.
does that make them less relevant for benchmarking compilers?
I guess not, though it does mean that some gromacs users may find 
the comparison irrelevant.

how about microbenchmarks?  codes like polyhedron might be reasonable
to start with.  HPCC?  byte unix benchmarks?