>>At 256K FFT I was seeing 0.11 secs/iter with
>>Mlucas against 0.15 secs/iter for MLU, at 512K FFT the figures were
>>0.25 secs/iter and 0.29 secs/iter respectively.
>
>...and don't forget the added benefits due to Mlucas being able to
>test significantly larger exponents at the same FFT length, as well
>as having intermediate runlengths between powers of two. 0.11 seconds
>at 256K is impressive - that's faster than on my 400MHz Alpha 21164
>(0.16 sec) and Prime95 on a 400MHz PII (0.13sec), though, to be fair,
>both of the latter systems have a smaller (512KB) L2 cache.
Observing the running process with top, it looks to me as if
the 256K Mlucas fits completely in the L2 cache, whereas MLU
takes about 12Mb. At 512K FFT around 60% of the running process
will fit in the L2 cache. It's a cache size issue here.
On my Ultra-5 with a small 256Kb L2 cache I get 0.58 secs/iter
for MLU against 0.78 secs/iter for Mlucas at 512K FFT.
>>Mlucas runs significantly faster if you can compile and run it
>>on a 64-bit Solaris 7 system.
>
>This is the first I've heard of this - roughly how much of a speedup
>do you see?
I'm a bit red-faced on this one. I just tried it again and it doesn't.
This is still a mystery to me. It would seems to me that for
this type of code that having full access to the 64-bit instruction
set of the UltraSPARC CPUS and running it on a 64-bit operating system
would give you the best performance. But that doesn't seem to be the
case.
Ernst, would you expect your code to run faster this way?
Bill Rea, Information Technology Services, University of Canterbury \_
E-Mail b dot rea at its dot canterbury dot ac dot nz </ New
Phone 64-3-364-2331, Fax 64-3-364-2332 /) Zealand
Unix Systems Administrator (/'
_________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
