botnet vs BlueGene

[jswaff]

This article:
http://www.itnews.com.au/News/60752,sto ... uters.aspx

makes the claim that the "Storm Worm" botnet would defeat BlueGene in a game of chess. (Ok, suppose such programs existed.)

I believe the claim is wrong, simply because:
1. There is no known way to efficiently split the search space among millions of processors, so more is not necessarily better.

2. Latency of geographically separated systems (Internet) vs. high speed interconnects of BlueGene.

Who do you think would win?

--
James

[bob]

This article:
http://www.itnews.com.au/News/60752,sto ... uters.aspx

makes the claim that the "Storm Worm" botnet would defeat BlueGene in a game of chess. (Ok, suppose such programs existed.)

I believe the claim is wrong, simply because:
1. There is no known way to efficiently split the search space among millions of processors, so more is not necessarily better.

2. Latency of geographically separated systems (Internet) vs. high speed interconnects of BlueGene.

Who do you think would win?

--
James

It's a stupid statement made by someone that just doesn't understand parallel alpha/beta searching and the issues a distributed implementation has to overcome. Yes, "botnet" is far more powerful. The FBI claims there are over 3,000,000 computers infected with this virus today, with 4 "controlling machines" that can turn them on a target. Blue Gene has no hope of matching that kind of power. And discussing this with respect to chess is even harder to deal with since either machine has a tough time with chess...