News for hackers. Stuff that matters.
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by grumpopotamus on Wednesday December 06, 2017 @01:58AM (#15859130)
>it only takes 4 hours of training to beat Stockfish

In that time I figure they used the equivalent of about 1000 cpu-years. Imagine the things we'll be able to achieve as we can do more and more computation in less and less time.

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by cdancette on Wednesday December 06, 2017 @03:59AM (#15859656)
But how many "cpu hours" of human work were used to design stockfish? You can't really compare that.

Some scientist say the brain has a power of several petaflops, so if you use this, I guess the design of stockfish was way less efficient.

You can't really compare things to cpu years, it doesn't make sense. Power consumption would be a better metric I think.

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by CydeWeys on Wednesday December 06, 2017 @06:25AM (#15860276)
The best metric is total cost, including the cost of the hardware as well as the electricity. It might be worth prorating the hardware by the amount of time it spends on the task, too, assuming the hardware is general enough for many purposes (like TPUs are), vs say something like EFF's DES cracker which was not.
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by gwern on Wednesday December 06, 2017 @11:31AM (#15862389)
A ton of CPU has gone into Stockfish, if only for their distributed computing project fishnet: http://tests.stockfishchess.org/tests
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by gwern on Wednesday December 06, 2017 @02:57PM (#15864402)
To be a little more precise: Stockfish has used >5,667,382 CPU-hours (5.6 million CPU-hours) adding up just the participants who contributed >10,000 CPU-hours according to https://github.com/mcostalba/Stockfish/blob/master/Top%20CPU...
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by nojvek on Thursday December 07, 2017 @08:45AM (#15869882)
Yes but that's training time. At runtime AlphaZero got magnitudes more computation power than stockfish.

A more fair comparison would be use as much computation needed for training but for runtime, use equal wattage hardware.

E.g 20W of cpu in mobile phone running stockfish to 20W of GPU in nvidia TX2 running AlphaZero to 20W human brain.

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by CydeWeys on Wednesday December 06, 2017 @06:22AM (#15860254)
> In that time I figure they used the equivalent of about 1000 cpu-years.

Are you using some kind of conversion factor from TPUs to CPUs? If so, what is it? And is it valid to do that?

You could convert the amount of time it took to render an hour's worth of gameplay from 1 GPU-hour to 50 CPU-days (or whatever), but is that really meaningful?

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by allenz on Wednesday December 06, 2017 @05:50PM (#15865886)
The conversion factor seems to be 1 TPU-hour ~ 500 CPU-hours in terms of flops. We can nitpick that number, but it won't change the conclusion that AlphaZero needs a boatload of compute.
Re:Mastering Chess and Shogi by Self-Play with General Reinf... by CydeWeys on Wednesday December 06, 2017 @11:34PM (#15867650)
I don't see how this is relevant though. A GPU also provides graphics rendering performance equivalent to some boatload of CPU-hours, but who cares? GPUs exist and are used for the tasks they are good at. TPU hardware isn't theoretical; it does exist and it is being mass-produced.

Yes, it needs a boatload of very simple compute (8 bit operations), the kind that CPUs are not even close to ideal at providing economically.

Re:Mastering Chess and Shogi by Self-Play with General Reinf... by red75prime on Wednesday December 06, 2017 @09:29PM (#15867136)
It needs huge amount of computations to perform a task which previously required a boatload of domain experts' brainpower too.