gmp benchmarks on a Niagara T5220

[Dennis Clarke]

> What GMP version are you running?

   5.0.4 and all tests pass.

eris-sparc-SunOS5.10 $ tail /usr/local/include/gmp.h
#define __GMP_CFLAGS "-mno-app-regs -mno-vis -m64 -O2 -D_TS_ERRNO -DSOLARIS2=8
-D_POSIX_PTHREAD_SEMANTICS -D_LARGEFILE64_SOURCE"

/* Major version number is the value of __GNU_MP__ too, above and in mp.h. */
#define __GNU_MP_VERSION 5
#define __GNU_MP_VERSION_MINOR 0
#define __GNU_MP_VERSION_PATCHLEVEL 4
#define __GNU_MP_RELEASE (__GNU_MP_VERSION * 10000 + __GNU_MP_VERSION_MINOR *
100 + __GNU_MP_VERSION_PATCHLEVEL)

#define __GMP_H__
#endif /* __GMP_H__ */

>
>   GMPbench:         75.594
>
> Cool, we have a new low-score result (unless you count the results from
> my old 233 MHz Pentium laptop from 1998)!

I can dig up an old Pentium III at 400MHz to run the same test.
Just for giggles.

> Does this machine have serious FPU problems, like T1?  Then GMP 5.1
> should help a lot, but the solid last place will not be threatened by
> these optimisations.  :-)

As I generally say to people, stay clear of anything with a Niagara
chip in it if you want to do floating point at all. I have no idea
what the real issue is but I'll be happy to crank out some digits of
pi just to see.  I thought that the T2 had a FPU in each core.

Dennis



-- 
--
http://pgp.mit.edu:11371/pks/lookup?op=vindex&search=0x1D936C72FA35B44B
+-------------------------+-----------------------------------+
| Dennis Clarke           | Solaris and Linux and Open Source |
| dclarke at blastwave.org   | Respect for open standards.       |
+-------------------------+-----------------------------------+