Author: Robert Hyatt
Date: 13:22:17 10/07/03
Go up one level in this thread
On October 07, 2003 at 14:11:24, Tom Kerrigan wrote: >On October 06, 2003 at 09:43:55, Robert Hyatt wrote: > >>On October 06, 2003 at 06:03:21, Tom Kerrigan wrote: >> >>>On October 04, 2003 at 23:42:01, Robert Hyatt wrote: >>> >>>>On October 04, 2003 at 21:00:34, Tom Kerrigan wrote: >>>> >>>>>I had the chance to run my program on a dual P4 Xeon (with hyperthreading). >>>>> >>>>>First off, there have been some involved arguments about the design and >>>>>performance of hyperthreading on this board in the past. I'd like to settle one >>>>>argument, namely that single threaded programs do not slow down when >>>>>hyperthreading is on. Actually, my program did slow down by 1.3% but I think >>>>>this is marginal and easily attributed to the scheduler, not hyperthreading. >>>>> >>>>>The odd part is that hyperthreading DOES slow down my program when running 2 >>>>>threads. With HT off, my program searches 90% more NPS with a 2nd thread. With >>>>>HT on, it only searches 53% more NPS. The idle time reported by each thread is >>>>>low and the nodes are split evenly, so it seems both processors are slowed down >>>>>equally. What must be happening is that HT is activated some (or all?) of the >>>>>time while searching but I have no idea what might be activating it. >>>> >>>> >>>>Your explanation is not very clear. You have a dual. Did you run two >>>>threads with HT on? Which means that the two threads might run on two >>> >>>With it on and off. I think I made that pretty clear in my post. >> >>Yes, but you didn't quite make it clear about how you ran the test. IE I >>_think_ you ran two threads on a machine with SMT off, then two threads on >>a machine with SMT on. That invites the problem I have discussed here many > >Right. That's pretty clear to me from: > >"With HT off, my program searches 90% more NPS with a 2nd thread. With HT on, it >only searches 53% more NPS." > >>times, that no current O/S (except for a windows .net kernel or a linux > >You keep saying Windows .NET but there is no such thing. I think that's what >Windows Server 2003 was going to be called for a while. Do you mean that? Well, >in any case, I might as well be using whatever kernel that is. I'll plead ignorance. When SMT first hit the street and I got my hands on one, I was interested in this very issue. It was broken on linux (still is unless you use a non-standard kernel). It was broken on windows 2K and windows XP. When I called microsoft they said "it will be fixed on the windows .net server edition". What that really means I don't know. If you have access to the latest kernel, it would be good to run and report the results. It is odd for people to run 1, 3 and 4 thread tests and get good numbers, but when they run 2 thread tests things to go hell in a handbasket for this very problem. It needs fixing if for nothing else than to stave off the questions that will arise. > >-Tom
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.