Author: Robert Hyatt
Date: 15:19:08 03/05/03
Go up one level in this thread
On March 05, 2003 at 15:37:00, Vincent Diepeveen wrote: >On March 05, 2003 at 11:37:48, Robert Hyatt wrote: > >>On March 05, 2003 at 10:20:05, Vincent Diepeveen wrote: >> >>>On March 05, 2003 at 02:05:30, Aaron Gordon wrote: >>> >>>and those AMD chips are way faster than the intels too :) >> >>I'm still waiting for a > 2.1M nps number from Crafty's benchmark, no >>.craftyrc/crafty.rc >>file used. My 2.8 produced 2.16M nodes per second on the raw benchmark >>number... > >Even at specint the XP is faster for you than the P4, so i do not know what you >talk about. I thought I was very clear. I posted the output for the "bench" command on my dual xeon with SMT on. it reported 2.16M nodes per second. I simply said "I have not seen _anyone_ report a faster NPS for Crafty than that, so far." That's _all_ I said. I think the 2.16 can be improved on by using a very late MSVC compiler, perhaps Eugene can test his latest one day as MSVC seems to produce better code than any compiler I have seen, for the X86 architecture. But Intel is fairly close and it produced the 2.16M number. I don't care about specint. That is a "base crafty". No assembly. No "compact-attacks" which was written to be cache friendly. So that has nothing to do with the "real crafty" that is customized for the X86. > >Not to mention the huge NPSes which get produced for special compiled crafties >for the AMD K7. No i'm not referring to the intel c++ 7.0 compiler which you use >for your P4, that compiler is horrible for K7s. > >Apart from that you are always in the minority. Most people care more about the >deep fritz and deep shredder and DIEP actually than they *ever* will do about >crafty. I suspect they care more about fritz or shredder. I'll bet ther are 100000X times more copies of crafty running on other machines than there are Dieps. We quit counting when the number of unique IP addresses downloading the crafty.tar / crafty.zip files passed 1M about 3 years ago. You got 1M+ users? I have 5000 people on the crafty mailing list for example. You think you have more diep users? :) > >No one for example was capable of reproducing a 30% speedup at a dual Xeon >system for SMT. No one ever was capable, not even at specint to produce the >speed you got 'at home' at a 600Mhz clocked 21264c. Eugene did. I did with the specific problem set I ran. I produced 20% with another problem set. > >Even the 21264c at 1 Ghz at specint is a lot slower than a 1.5Ghz K7 or a 2Ghz >P4, so i wonder always about your testing methods. You should wonder about your own "testing methods". For example: "On my dual, crafty produces _no_ speedup using two processors." "On my dual, crafty produces 1.4 speedup using two processors." "on your non-existant machine you can't get a speedup of 1.7." the list goes on. The difference between us is I post the raw data to go along with the test results. And others reproduce it. > >It's very easy. Compile a crafty version with intel c++ 7.0 for windoze. then >run the bench under windows. then compare with the bench at (dual) XP. test >finished. Feel free to do so. That's what I asked for. It is not "very easy" here. There isn't a single AMD processor in the building. There are thousands of Intel processors of course. > >>Of course this machine doesn't exist, so the numbers are imaginary. > >You should checkout numbers posted at CCC by dual AMD owners a bit more. > I have. I haven't seen >2.16M yet. As I said. perhaps _you_ should check them out a bit more... One might be faster, I don't know. But it hasn't shown up yet. >>> >>>>On March 04, 2003 at 21:57:58, Nolan Denson wrote: >>>> >>>>>There are no draw backs when looking to get a computer that using >>>>>Hyper-Threading. If you do not like the feature you can just simply turn it off. >>>>>There are many system on the market that claims to be Hyper Threading enabled. >>>>>Intel has a utility program that checks for Hyper Threading ... >>>>> >>>>>1. You must have the proper CPU's. >>>>>2. You must have the proper motherboard. >>>>>3. You bios must support it. >>>>>4. Your Operating system must support it. >>>>> >>>>>Once these things are met your system will indicate that Hyper Threading is >>>>>enable before booting into the Operating System. >>>>> >>>>>It is not an indication that you will see when the computer is turned on and the >>>>>Bios is posting. >>>>> >>>>>Soon all of Intel processcor's will have Hyper Threading. So if what you are >>>>>using your processor slows down with Hyper Threading, just simply turn it off >>>>>via the Bios. >>>> >>>>How convenient. Have to reboot 20 times per day to turn it on/off just so your >>>>applications run optimally. I'll be sticking with the cooler running, faster, >>>>and cheaper AMD chips. :) >>>> >>>>>On March 04, 2003 at 17:39:42, Vincent Diepeveen wrote: >>>>> >>>>>>On March 04, 2003 at 16:32:33, Jay-R Delacruz wrote: >>>>>> >>>>>>>Do the deep versions of Fritz, Junior and Shredder support hyper-thread? Can >>>>>>>someone please tell me before upgrading my PC to try the deep versions? >>>>>> >>>>>>I just read email from Frans Morsch. DeepFritz7 gets 5-10% speedup by >>>>>>hyperthreading. >>>>>> >>>>>>Shredder gets more speedup in nodes a second than that, but it gets no speedup >>>>>>from it as it gets SMP already a far smaller speedup (1.5 or so), so it is >>>>>>smarter to turn SMT/HT off for it. perhaps shredder8 will fix this. >>>>>> >>>>>>For diep it speeds me up about 11% in NPS but i cannot garantuee that at a 4 >>>>>>processor it will give a positive speedup. >>>>>> >>>>>>When running 2 processes at a P4 at 3.06ghz it will give for sure some speedup >>>>>>because it goes from 100k nps to 120k nps. Nearly 20% speedup it gets with it >>>>>>(18.6 or something) which gives a positive speedup also in depth. >>>>>> >>>>>>For deepjunior we know that it already works bad at 8 processor Xeon 1.6Ghz >>>>>>versus 4 processor Xeon 1.9Ghz, so i *assume* for now that SMT/HT will not give >>>>>>it much benefit for it at all, but perhaps Amir or Shay wants to give a >>>>>>statement regarding this themselves. >>>>>> >>>>>>We talk of course about the SMT/HT from Xeon processors up to 2.8Ghz now for >>>>>>those which have it enabled. For the P4 3.06Ghz and also Xeons of that and above >>>>>>things are a different matter. >>>>>> >>>>>>Best regards, >>>>>>Vincent
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.