On 10/09/09 4:33 PM, "Ingo Macherius" <[email protected]> wrote:

> My benchmarks with 4 cores showed that the cache brings about 10% improvement

This is interesting. I ran some benchmarks (In my Message to phillipe) for a
cache of 21mb that was testing the variation on threads above number of
cores.

I just ran the same 10 trials (8 threads on 8 cores, 0 cache, Linux Priority
-19) 

And got this results :

8 thread, 0mb cache, 10 trials : 44.83 (seconds) mean, Std Dev of .18
8 thread, 21mb cache, 10 trials : 28.05 (seconds) mean, Std Dev of .12

Cache make a big difference in this case. A speed improvement of about 60%.
I don't consider 60% insignificant and is well beyond 10% you were getting.
I find that curious.




_______________________________________________
Bug-gnubg mailing list
[email protected]
http://lists.gnu.org/mailman/listinfo/bug-gnubg

Reply via email to