Author: Vincent Diepeveen
Date: 14:44:44 07/08/03
Go up one level in this thread
On July 08, 2003 at 16:16:00, Rajen Gupta wrote: Opteron blows everything away in the server market. Of course only dudes who want to buy a server buy a dual or quad opteron. The itanium2s are buggy and the madisons very expensive. the intel c++ compiler is not reliable in short and produces as proven by prof A v/d Steen at the 1.3Ghz Madisons incorrect results at testsets (so that can be either copmiler issue or hardware issues). In short in critical server environments you cannot trust it. You want to trust your $1 million database at such a machine? In that case the opteron blows everything away. Also for computerchess it is way faster. Even a chicken can see it. Just checkout the speed of crafty at it when compiled 64 bits. 1562 its score. The Alpha 1.26Ghz and the P4 and the Itanium2s do not even get close to that. What i see is a killer cpu which for the 'average' person is less accessible of course because of its price (the quad version at 1.8Ghz is like $2000 a piece and the dual version is like $767 a piece so that'll be like 1000 euro in the shops in europe). In short you pay for it about what you pay for a Xeon (Xeon MP pricier). The prescott is a poor 32 bits cpu as far as we know from the publications so far from intel. We know they also go support the x86-64 with a new cpu, all their publications about x86-64 have stopped being negative. if you ask carefully to intel spokesmen you can only conclude they go produce a x86-64 chip of their own. If x86-64 would be a bad thing, why would intel do effort now to also develop a cpu that can use it? In short i can conclude only 1 thing. the opteron is a big big winner and it is too bad windows didn't yet release a 64 bits version. As soon as they will it blows for everything of course the 32 bits chips away. It is trivial this thing with the fast latencies and big L2 cache is created for Databases. It's trivial it's faster for games. It's trivial it's faster for computer chess. I wouldn't know a single thing where it is bad when used a native 64 bits application for it. At the itanium2 you don't bench 32 bits applications either of course. Only 64 bits. It's more than strange that some only conclude it's slightly faster than k7 for 32 bits software. This is real weird. They didn't measure itanium using 32 bits binaries either! When windows 64 bits gets released for x86-64 then trivially they'll soon release after that a visual c++ for 64 bits too. Until then you can use for big companies the thing very nicely already under linux 64 bits and until then already use it for 32 bits windows now and then. Of course it is also a bit NUMA. So most applications that are NUMA like big database will relatively be even faster at it than most tests indicate currently. >On July 08, 2003 at 15:37:39, Russell Reagan wrote: > >>On July 08, 2003 at 15:18:55, Rajen Gupta wrote: >> >>>http://www.amdzone.com/articleview.cfm?articleid=1304 >>> >>>looks like a tie with the pentium 3.2: hardly a pentium killer! my heart bleeds >>>for the poor opteron when intel releases a prescott! >> >>Please post the link to the page where the have the results of the chess program >>benchmarking that they did. > >they didn't: and i am talking of the chip's overall performance as most >end-users dont buy a chip for its chess performance only: (even on this forum of >die-hard computer chess fanatics its quite probable that there are more intel >based systems being used) if this so-called pentium killer does not measure up >(and i have a horrible feeling it won't), it will be the end of AMD as we know >it; for the last 2 yrs they have been telling us: > >"never mind the athlon; it is only stop gap; wait for the hammer; it is going >to smash intel;" and finally after endless delays it does show up it appears to >be almost geting a smashing itself! > >if AMD disappears, we will then be subject to intel's monopoly which will be a >horrible thing for us all: hence my disappointment with AMD: always too little >and too late!
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.