hm... I can't confirm that... I just ran a few tests, and I can do 10k empty playouts 19x19 per second on 4 threats, and about 11-12k on 8 threats. I did the test with only playouts, no treesearch, additional patternmatching or anything. With treesearch, going to more then 4 searchthreats actually slows down my code, due to some blocking issues... (This will be fixed, at some point) But also during treesearch right now I'm using 4 dedicated search/playout threats, and some other threats doing minor work. (nonblocking cleanup and managment of the tree, checking gtpconsole etc)
So I guess it really depends on the implementation and everyone has to make their own tests, how their bot does best. 2014-05-12 22:10 GMT+02:00 Matthew Woodcraft <matt...@woodcraft.me.uk>: > Mikko Aarnos wrote: > > There is a big difference here: Ellis's program can only do light > > playouts. He doesn't have MCTS or patterns. That is parallelized > > extremely simply by just giving each thread an internal board state, > > doing a playout from that, resetting the board state to the > > original, doing a playout etc. There are no bottlenecks there, and > > that shouldn't get any increase in performance from HT as far as I > > know(also see the first sentence of Schmicker's comment). > > I don't think that's right. > > I tried an experiment once with hyperthreading and 'light playouts' and > I got a 40% improvement from using two threads per core. > > > There are plenty of bottlenecks even in such simple code. > > For example, any time you do something equivalent to following a linked > list (eg, finding the stones in a group that you're joining to another > group) the thread will have to wait three or four cycles per 'link' even > if all the data is in level-1 cache. > > > One way to tell whether code is likely to benefit from hyperthreading is > to use a tool that reports the processor's performance counters and look > at the 'instructions per clock' measure. If it's somewhere around 1 then > there are excellent chances of getting good results from hyperthreading. > > -M- > _______________________________________________ > Computer-go mailing list > Computer-go@dvandva.org > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list Computer-go@dvandva.org http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
