Author: Robert Hyatt
Date: 05:56:49 09/24/01
Go up one level in this thread
On September 24, 2001 at 00:46:35, Slater Wold wrote: >On September 23, 2001 at 23:38:40, Robert Hyatt wrote: > >>On September 23, 2001 at 23:08:10, Slater Wold wrote: >> >>>On September 23, 2001 at 22:36:38, Robert Hyatt wrote: >>> >>>>On September 23, 2001 at 18:20:30, Vincent Diepeveen wrote: >>>> >>>>>On September 23, 2001 at 15:30:08, Lonnie Cook wrote: >>>>> >>>>>>* It weighs 106 tons >>>>>> >>>>>>* costs 110M for the unit itself (doesn't include the ungodly sum to run it >>>>>>every day) >>>>>> >>>>>>* Has 8,192 IBM Power3 processors >>>>> >>>>>>* 12.3 trillion ops per sec. >>>>>> >>>>>>* took 28 tractor-trailer trucks to deliver >>>>>> >>>>>>this was the part that astounded me. It said it was 1,000 X's faster than Deep >>>>>>Blue!! >>>>>> >>>>>>so we're talking about a machine that in theory could do 200,000,000,000 nps!! >>>>> >>>>>Noop. >>>>> >>>>>IBM power3 processors. i do not know what speed they run at. Let's guess >>>>>they run at 375Mhz. Hehe , a cheated guess kind of. >>>>> >>>>>Now i have some numbers on these processors, but those are a few years old >>>>>of course. These processors suck bigtime of course. NO one wants to run >>>>>on 375Mhz processors nowadays. But well let's assume that at a stupid >>>>>cluster which ASCI white is, that you can get a decent speedup. >>>>> >>>>>Now how fast do i run at 1 node? Well that's like 15k nodes a second. >>>> >>>>That math is bad. I'll "race" you using any PIV of your choice, me using >>>>an 800mhz 21264 of my choice. And my lowly 800mhz processor will toast your >>>>doors off. >>> >>>Here's a race on Crafty, using the same Crafty and settings: >>> >>>AMD 2x1.4Ghz >>>Total nodes: 95124934 >>>Raw nodes per second: 1219550 >>>Total elapsed time: 78 >>>SMP time-to-ply measurement: 8.205128 >>> >>>Alpha 21264(EV6) (2x667mhz) >>>Total nodes: 70350064 >>>Raw nodes per second: 901923 >>>Total elapsed time: 78 >>>SMP time-to-ply measurement: 8.205128 >>> >>>Interesting! >>> >> >> >>Your alpha numbers are not particularly good. Tim Mann ran a 21264/600 last >>year and his single cpu machine was giving numbers like this on win at chess: >> >>total positions searched.......... 300 >>number right...................... 300 >>number wrong...................... 0 >>percentage right.................. 100 >>percentage wrong.................. 0 >>total nodes searched.............. 236973211.0 >>average search depth.............. 4.5 >>nodes per second.................. 783641 >>White(1): execution complete. >> >> >> >>And yes, I mean that 800K was _one_ cpu. You probably didn't use the best >>alpha options to compile it. You should be seeing 1.5M nodes per second >>on that dual, or a bit more. Tim's machine was 600mhz... > >My 2x1.4Ghz gets 299/300 in the same amount of time. The only one it doesn't >get, from what I understand, it did get it on that version. (The version Tim >Mann used.) > >The machine I quoted WAS Tim Manns machine! As given on Michel's website of >Crafty benches. >(http://home.wanadoo.nl/michel.langeveld/CraftyBench/craftybench_hardware_withouthash.html) > I did not compile that Crafty. I am guessing Tim Mann did. OK.. then that _might_ be older data. Data prior to the "lockless hashing" which was hurting the alpha... > >I admit, Alpha's are impressive. Just not practical for me. As often people >tell me, a 2x1.4Ghz is not practical for them. > >There are positions where I get 1.2M nps, and some where I've hit 2M nps. The >average (in a real game) is about 1.5M. > >*Perhaps* when I sell my 2x1.7Ghz Intel, I will invest in an Alpha. That should >be interesting! > >One question: Obviously a node on an Alpha is not equal to a node on a x86 >system. Mind sharing why? Or giving me some references to read up on. I've >only been around a few Alpha machines, and that was pretty recently. And they >were all running Windows! I've only used alphas running "tru64" which is the alpha's version of unix. The alpha has a couple of advantages over the X86: 1. 64 bits, which obviously fits crafty better; 2. 256 bit wide bus rather than 64, which ups the memory bandwidth significantly on the alpha. > >Thanks Bob! > > >Slate > >> >> >> >> >>>Slate >> >> >> >> >> >>> >>>> >>>>Don't just assume that 375mhz is bad. The PPC is _not_ a bad machine. I >>>>have run on SP's... >>>> >>>> >>>> >>>> >>>>> >>>>>Still probably optimistic number of nodes a second. >>>>> >>>>>So at 8192 processors, from which you can perhaps use a 1000 at a time, >>>>>I would get 15M nodes a second. >>>>> >>>>>Now that looks great, but that's of course on a CLUSTER. Speedup perhaps >>>>>10%. 1.5M nodes a second effectively, but the bigger the depth the less >>>>>the speedup gets as the branching factor will be worse, unless i accept >>>>>that the thing first slows down at each processor (which is a likely >>>>>approach) and pray that the latency is more than fast at this thing. >>>>> >>>>>So you sure outsearch deep blue by many plies, but not if a new deep >>>>>blue would be pressed on a chip using nullmove and DDR-RAM at it. >>>>> >>>>>So you are not faster in NPS, but search improvements would let it >>>>>search deeper. that still wouldn't make my DIEP faster on this machine >>>>>than DB was in nodes a second. >>>>> >>>>>Of course DBs focus upon only getting the maximum number of NPS (that's >>>>>how they advertised the thing. search depths have no commercial value) >>>>>sure made it faster than what i would get on this machine. >>>>> >>>>>>Is this really so for those in the know with hardware and these types of >>>>>>machines?
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.