Author: Robert Hyatt
Date: 19:45:43 12/25/05
Go up one level in this thread
On December 24, 2005 at 13:11:10, Vincent Diepeveen wrote: >On December 23, 2005 at 13:26:42, Zappa wrote: > >As most people here do not realize very well what the machine is, >here a short comparision. > >The only machine on the planet faster than this for chess, is NASA's >10240 processor SGI machine which has partitions of 2048 processors. > >So basically this is the one fastest machine for chess. > >Let's do a small comparision with hydra. Hydra has 64 cpu's and each cpu >delivers 3 Gflop. So that's about 0.192 Tflop for entire machine. > >This 1060 processor machine delivers 6.4 gflop a processor. So that's >6.784 tflop on paper. That is all interesting, and well-known. And it has _absolutely_ nothing to do with playing chess. I don't do a single "FLOP" while searching a node. I doubt you do either. So how fast the thing can do floating point operations is about as important as how much the machine weighs... > >In reality Zappa uses from the machine 512 processors. 12 processors will be for >i/o, a processor carrying a timer (timing goes central) and one to set coffee >for you meanwhile another gets a fastfood meal for you. > >So he could use in theory 500 processors in Turino. 500 * 6.4 Gflop = 3.2 Tflop. > >Of course all that doesn't matter for practical search efficiency. > >Hydra loses shitloads to search efficiency, after initially winning some by >hardware. Zappa has also big inefficiency of course at such a big machine. > >If i look at diep's speedup at this machine, Diep would be practical having a >hardware advantage of factor 6 to a quad opteron dual core 2.4Ghz in world >champs 2006. > >I expect Anthony to obtain something like that too. > >Vincent > >>So when I went to UIUC as a newly minted World Champion, they were interested >>and after some negotiations I managed to procure some time on NCSA's Cobalt >>supercomputer, an SGI Altix: >> >>http://www.ncsa.uiuc.edu/UserInfo/Resources/Hardware/SGIAltix/TechSummary/ >> >>At Paderborn Zappa will run on 128 CPUs as a bit of a warmup; at Turino I hope >>to use 512. I haven't really had enough time to seriously optimize Zappa for >>this machine, and I have been somewhat disappointed by the Itanium2 CPU, but the >>results are still reasonably impressive. For example: >> >>r1b2r2/p1q1ppk1/6p1/3p3p/7P/5P2/PPPQ2P1/2K1RB1R b - - 0 9 >> >>1... Ra8-b8 2. g2-g4 h5xg4 3. h4-h5 Qc7-b6 4. b2-b3 Qb6-f6 5. Kc1-b1 Rf8-h8 6. >>h5-h6 Kg7-g8 7. f3xg4 Bc8xg4 8. h6-h7 Kg8-f8 9. Qd2-h6 Kf8-e8 10. Bf1-d3 e7-e6 >> = (-0.49) Depth: 17/45 00:03:37.11 5532448kN (25481 KN/s, 3558608 >>splits, 294631 aborts) >> >>r1b2rk1/pp3ppp/1nn1p3/q2pP3/2pP1P2/P1P2NPB/2PB3P/R2QK2R w KQ - 0 8 >> >>1. Ke1-g1 Nc6-e7 2. Nf3-h4 Qa5-a4 3. Qd1-b1 Bc8-d7 4. Qb1-b2 Qa4-c6 5. Ra1-b1 >>Qc6-c7 6. Nh4-g2 Ra8-c8 7. Kg1-h1 Ne7-f5 8. Ng2-e3 Nf5xe3 9. Bd2xe3 Rf8-d8 10. >>Rb1-a1 >> = (0.15) Depth: 20/46 00:04:33.59 7300957kN (26686 KN/s, 6497504 >>splits, 503423 aborts) >> >>Single CPU Zappa on the I2 there gets about 300 knps, so that is an nps speedup >>of 80-85. I'll probably get a bit less in Paderborn, as this is essentially the >>World Champs version of Zappa, and I've been busy de-optimizing it since :) >> >>This is really only 1-2 ply deeper than my quad, but wait until Turino when I've >>had some time to optimize things a bit . . . >> >>anthony
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.