[email protected] wrote on
28/04/2009 22:01:23:
> I actually usually compile without thread support. I feel it's safer and
> is more stable, and therefore prefer to compile without threads. I can
> also see that my own builds, without thread support, is considerably
> faster (in terms of eval/sec) than a single threaded build supporting
> threads. I therefore believes the thread code adds some overhead.
>
> The numbers in evals/sec
> My own non-thread build: ~56600 eval/sec
> MaX build single thread: ~48100 eval/sec
Wow, that's a lot !
I double checked here (office PC: Pentium 4, 1 core, 2 threads):
MaX build with single thread : ~32400 eval/s
MaX build with MT code, 1 thread : ~24800 eval/s
MaX build with MT code, 2 threads : ~34600 eval/s
However, a quick rollout (648 trials, expert, full, 2 top moves of postion
t60BYCButycAAA:cAnnAWAASAAA) has shown the following:
MaX build with single thread : 2m04s
MaX build with MT code, 1 thread : 2m04s
MaX build with MT code, 2 threads : 1m48s
Would tend to prove that the "eval speed" code is not really relevant in
threaded case, but overhead for threaded code is neglectible in real
usage.
MaX.
_______________________________________________
Bug-gnubg mailing list
[email protected]
http://lists.gnu.org/mailman/listinfo/bug-gnubg
