Author: Jesper Antonsson
Date: 14:45:00 11/18/01
Go up one level in this thread
On November 18, 2001 at 15:59:31, Tom Kerrigan wrote: >On November 17, 2001 at 20:52:36, Jesper Antonsson wrote: > >>To answer the original posters question, no, there is not enough knowledge about >>DB to create a DB-emulator. If IBM made all DB information public (which would >>probably involve documentation work for them), I think it would take perhaps six >>months, full time for one person, to create an emulator. > >I doubt that. Maybe it would take 6 months for a great implementation, but just >hacking together a mess of eval terms does not take long. Sure, but you would want reasonable speed and as good emulation as possible. I expect that it would take some time to do that because of complexity in the eval, the two searches and in their interaction. Perhaps I'm wrong, though, perhaps a talented person could do it in less than a month, if there is perfectly good documentation available to him or her. >>Of course, to emulate a massively parallel beast like that perfectly on a serial >>machine would be almost impossible, I don't expect that even DB got repeatable > >And unnecessary. Why try to simulate an MP program when you can save developer >time and reduce overhead by just not implementing the parallel parts... Did I say one should implement the parallel parts? No, but if you want to replicate behaviour, then you have to consider what the parallelism in the original *does*. >>results all the time, but I think you could get close enough. The speed of the >>emulator, NPS-wise, would be way below what we see in current micros because, >>among other things, the eval is probably to complex to run quickly in software. > >We do not have enough information to make that claim. How do you know that DB's >evaluation is any more or less complex than MChess's, CS Tal's, or even, say, >HIARCS? I said "probably", and I base it on things Bob said years ago. But think about it, if you could do complex eval for free in hardware, would you only implement stuff that could be efficiently implemented in software too? I wouldn't, so I expect that at least some of the stuff they did would run slowly in software.
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.