(2) I noted the following in the gcc 2.6.1 announcement:
   
   Noteworthy changes in GCC version 2.6.1:
   ...
   The following new configurations are supported:
   
           GNU on x86 (instead of treating it like MACH)
           NetBSD on SPARC and Motorola 68k
   	...
   
   Anyone tried building 2.6.1 on a NetBSD/SPARC system yet?  I wonder what new

it should work.  i did the port of 2.6.0 to netbsd/sparc a few
months back, but i've since deleted it -- it didn't seem to
make much difference, though it was clearly capable of building
workable kernels ;-)

gcc 2.6.2 is out now apparently.  maybe i'll d/l it tonight and
give it a go.  but this static/dynamic problem isn't going to
be related to the compiler -- the linker(s) are at fault? here..

as chris noted, it's affected by cache somehow -- i had been
getting ~31k for that dhrystone, then suddently i was getting
~42k .. turns out that charles was running gdb at sometimes
and not at others ..

i don't see any difference when i put some code above or below
the loop, or anywhere else, either.

.mrg.