Author: Robert Hyatt
Date: 20:39:13 09/01/03
Go up one level in this thread
On August 29, 2003 at 18:32:46, Jeremiah Penery wrote: >On August 29, 2003 at 08:46:12, Robert Hyatt wrote: > >>On August 28, 2003 at 19:12:52, Jeremiah Penery wrote: >> >>>But it's not more latency than you get *best case* when using a traditional SMP >>>setup. So you can only gain, even with a "poor algorithm". >> >>If you compare an SMP xeon to a dual 486 you _also_ "win". > >And what is that supposed to demonstrate? That you can win with a poor algorithm, when the hardware is faster. But you won't win anywhere near max theoretical "win". For a chess person, that's important. We work for 5% _all_ the time. > >>But my point was that with a NUMA architecture, you might win a lot less >>than you could, if the algorithm doesn't take into account the specific >>architectural issues with a NUMA machine. >> >>My point was, again, that you want most references from a CPU to go to its >>local memory for max performance. It's an issue on _all_ NUMA-type machines. > >Of course I know that. My point is that with Opteron, even if you are accessing >non-local memory *always*, you are not accessing it slower than you would with, >say, a traditional SMP machine (2x Xeon, for instance). OK.. Buy that F-1, but you don't get it into 6th gear. You will be fast. But you _could_ go a _lot_ faster... That was my point. >Of course you can do a lot better - all I'm saying is that there's no way you're >going to be doing worse. I don't remember saying I would be doing worse. I remember saying I would be doing _bad_. Because potentially all memory references would be non-local. > >Either way you win, even with a crappy NUMA algorithm. As I said "if you call that winning..."
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.