Author: Robert Hyatt
Date: 07:12:58 08/30/04
Go up one level in this thread
On August 30, 2004 at 06:03:18, Gerd Isenberg wrote: >On August 29, 2004 at 21:27:55, Robert Hyatt wrote: > >>Here is a quote from ICC: >> >>quote on=================================================== >>DIEP(C DM)(64): because they claimed having 'solved' chess and people like hyatt >>supporting that indirectly (by saying that nothing ever can get better than that >>old program) >>quote off================================================== >> >>This is _another_ case where I want to see a _specific_ quote, or a specific >>citation for an article where I made that statement (nothing can ever get better >>than DB). I've never said it. I've never implied it. In fact, I have been >>quoted more than once where I predicted that hardware would eventually take us >>well beyond DB's speed/performance. >> >>My quote was that in 1997, it would take 10+ years for a micro-computer based >>program to approach DB's speed. Today I can hit 10M nodes per second on a quad >>opteron, 20M on an 8-way. Probably approaching 40M on a 16-way box. That isn't >>as fast as DB, but it is in the ballpark. And I still have 3 more years on my >>"prediction". Next year AMD has promised a dual-core opteron, so that 16-way >>box will instantly become a 32-way box. 80M if there is no clock speed >>improvement, yet they say it will be faster via clock as well. So 2007 may be >>enough time to hit 200M roughly, if not more. >> >>But to Vincent, once again, please provide an exact quote with the source, or an >>exact citation of a paper I wrote, where I made the statement you claimed I >>made. All I claim is that you are a liar. >> >>Here's yet another case to join the JICCA paper you claimed I wrote, the CCC >>posts you claimed I made, etc. >> >>The list is growing. >> >>Your credibility is shrinking. Why don't you just adopt the policy of not using >>_my_ name with your nonsense? I don't exactly drop your name in every >>conversation I hold. You ought to do the same. You'd look a lot less ignorant. > > >Hi Bob, > >what about a concealed microphone to publish even more junk from Vincent? ;-) >I admit, that you have to response, if you got attacked by Vincent. > >One problem with your deathless dispute with Vincent is that the "average" >poster here is no longer able to prove who was absolutely right, due to lack of >knowledge and competence. And like in other (political) conflicts with some >escalation cycles over years, one really has problems to look for the initial >"thrown of the first stone". > >Using an "absolute truth" scale, it is probably 90% to 10% in favour to you, or >even better. But unfortunately, it seems, there is often no "absolute truth". > >For instance the memory latency discussion, was "only" about the definition of >memory latency. So in some "pragmatic" sense of latency, how long a random hash >read could take with all the possible TLB issues, Vincent was right. No he wasn't. Remember the "page size" issue? Run them at 2mb and the TLB issue changes a _lot_ as I mentioned. Other processors have a much bigger TLB to boot. But latency is too-well defined. Time to do _one_ read from memory. Not "time to read two or four page tables plus the time to read the actual data." > >With the correct definition of memory latency you was right. > >I found that discussion productive in the way, that we now all know more about >the difference of memory latency and the worst case behaviour of a random read. > >Cheers, >Gerd
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.