Slashdot Mirror


Intel Dual Core Xeon Benchmarked

An anonymous reader writes "A few weeks back, Intel launched a new dual core chip with little applause. It appears we know now why, as the chip has been benchmarked by the chaps at GamePC. In tests against the dual core AMD Opteron processor, Intel's new chip gets thoroughly thrashed, losing out in terms of raw performance while eating a lot more power. "

335 comments

  1. great by Prince+Vegeta+SSJ4 · · Score: 2, Funny

    yeah, but can it run Duke Nukem Forever?

    1. Re:great by eln · · Score: 3, Funny

      Don't be ridiculous, everyone needs you need an Infinium Phantom Console to run Duke Nukem Forever.

    2. Re:great by Anonymous Coward · · Score: 0

      Silly you! Of course it can't. However it can run Dukenukem for about ten minutes before nation wide blackout.

    3. Re:great by Anonymous Coward · · Score: 0

      but will it run Forever?

    4. Re:great by niteskunk · · Score: 1

      Duke Nukem Forever? HA!

      Now VISTA on the other hand...

  2. I'm kinda shocked... by erroneus · · Score: 1

    Intel knew what they were up against and somehow didn't cut it? Intel has been the masters of their domain for a long time and I'm rather astounded that they couldn't come up with something to 1-up the competition this go-around. They have so much in the way of resources to throw at this too.... why?

    I don't know what's going on behind the doors of Intel, but have people in business department been cutting back on the R&D again?

    1. Re:I'm kinda shocked... by evil+agent · · Score: 1

      Yeah, I find it pretty amazing (and stupid) myself. It's unfortunate that speed of deployment is more important than quality of development. What can I say, we are an impatient people...

      --
      End transmission.
    2. Re:I'm kinda shocked... by killmenow · · Score: 3, Insightful
      Intel knew what they were up against and somehow didn't cut it? Intel has been the masters of their domain for a long time and I'm rather astounded that they couldn't come up with something to 1-up the competition this go-around. They have so much in the way of resources to throw at this too.... why?
      Why? ... WHY? ... Because.
    3. Re:I'm kinda shocked... by erroneus · · Score: 1

      Mod this parent insightful... wow. That little page speaks volumes about what is wrong with Intel today.

    4. Re:I'm kinda shocked... by Thuktun · · Score: 1

      Intel has been the masters of their domain for a long time [...]

      (Insert inane Seinfeld reference here.)

    5. Re:I'm kinda shocked... by justsomebody · · Score: 1

      It is quite simple in fact. Intel was always used to be followed so there was no rush on their R&D department. AMD and others always only tried to achieve what Intel achieved. So AMD putting out 64-bit before them was probably quite a surprise. Now it is obvious that Intel is following AMDs R&D footsteps.

      Intel somehow just can't achieve former glory. And it won't. Intel was always just boosting and never stand behind the words. Anyone remembering 64-bit RISC based Merced. Well, Merced was out (with delay) but for sure it wasn't 64-bit or based on RISC core. Same goes for P4 fiasco. P4 was nothing but a nice commercial. Itanium (or better Itanic was not better either). The only good thing Intel put out in last imes was P4M (which has less to do with P4 than with P3), but even here I can't wait nothing but to get rid of my notebook as soon as possible and buy either Turion or hopefully some Cell based notebook.

      Basicaly, Intels R&D department sucks under pressure. It was nice until others were just trying to achive what they did, but now that others put out things before Intel? Well, result is here.

      --
      Signature Pro version 1.13.2-3 release 83.5 beta3try7 after-breakfast edition
    6. Re:I'm kinda shocked... by Aldric · · Score: 1

      They are playing catch up. They were just recovering from the shock of having to be compatible with AMD64 when AMD announced dual core which the Athlon64 and Opterons had been designed to support. Intel's chips hadn't been designed for dual core and it had to be forced in without enough time to redesign. Hence, inferior performance and higher power consumption.

    7. Re:I'm kinda shocked... by airjrdn · · Score: 1

      You're new to the business world aren't you? Time to market > Quality of product. Whether they admit it or not, that's the way many sucessful companies work.

    8. Re:I'm kinda shocked... by Brazilian+Joe · · Score: 1

      They HAD to have a competing offer with waaay too little time for R&D. So they patched up 2 cores with an inferior solution so that they can say 'we have one of these too'. They know it's inferior, but those who are braindead brand buyers will go for it anyway. It will buy them time until they come up with a proper solution in the 2nd gen of their dual cores.

    9. Re:I'm kinda shocked... by Anonymous Coward · · Score: 0

      ahahaaahahahahahaa, economics and MBA. when the ceo knows more about supply and demand, and social-networking, and getting contracts, and making contacts you really cannot expect him to do the tech r&d.
      On the other hand, he has done plenty to get intel as widely distributed as it currently is. I personally think that it is enough and he should either step down or pair up with a techie ceo. Then intel would be more balanced between marketing and product's performance.
      Parent did a good job posting this link. Mod him up please, it is worth it.

    10. Re:I'm kinda shocked... by diegocgteleline.es · · Score: 1

      They have so much in the way of resources to throw at this too.... why?

      They probably did, but x86-64 got there sooner. IMO, it's clear that Intel _did_ have something. Hell, do people really think that intel didn't planned nothing after pentium4 and that they were going to keep releasing faster & hotter pentium4's forever? Intel _did_ have to have something, but x86-64 instruction set would have made it obsolete. Perhaps a alternative 64-bit CPU for desktops? God knows. As torvalds said once, even for Intel or AMD making a CPU from papers to the fabs can take even 2 years or even more. AMD did beat intel with x86-64 success, now Intel has to change all their roadmap. I think it'll take a while for intel to compete & beat amd again, presscot and those dual xeons are just a emergency measure they're taking meanwhile they redesign their roadmap

      (I hate talking like I could predict the future, but it has to be true dammit, Intel is not stupid)

    11. Re:I'm kinda shocked... by smooth123 · · Score: 1

      Well why is it that people are shocked... its a common phenomenon..once you have vendor lock in what purpose does one have to actually spend on R&D. In Intels case it does not matter that they are actually lagging behind..they know it will take a long time for AMD to come anywhere close to put a serious dent in their profits. It s like MS, they maay be better products than some of theirs but for the innocent many, the technologically challenged, brand matters more than anything else, and intel aldready has that...heck I have a hard time getting my friends who were in school (VLSI majors) with me to buy AMD. so we can only hope that AMD gains more popularity faster

    12. Re:I'm kinda shocked... by Anonymous Coward · · Score: 0

      Netburst (P4) was a bad architecture, a mistake, a dead end. If you look you can find much discussion from back when the Willamette core launched.

      Netburst's only virtue was high clock speeds, which Intel deemed necessary to their business. AMD beat them to a GHz, and Intel couldn't allow AMD to keep their lead in the clock frequency.

      Essentially about 4 years of R&D got largely wasted on NetBurst, and now they have to go back to their P3 architecture and evolve it into something comparable to (and compatible with!) K8.

      It's not surprising at all that Intel's behind right now. They should be largely caught up by this time next year if all goes well for them, however.

    13. Re:I'm kinda shocked... by halltk1983 · · Score: 1

      Yet many of the people who say they believe as you criticize Microsoft for delaying Vista.

      /unzips flame-suit.

      This message is brought to you by a user of Gentoo Linux, and I'm not fond of Microsoft, as you can tell by my sig.

      --
      Watch for Penguins, they eat Apples and throw rocks at Windows.
    14. Re:I'm kinda shocked... by IPFreely · · Score: 2, Insightful
      I think they did achieve their exact goal with this release. It's just not the goal you were thinking of.

      Intel is trying to save their exclusive customers, like Dell. Dell and the others needs something to compete with AMD or else they are going to have to start using AMD. Intel does not want that. They don't want to lose their exclusive deals, so they give them just enough to please them.

      They don't have to win the speed race. They don't have to make it better than AMD in any way. They just need something to fill the "dual core server processor" space in Dell's lineup. They delivered it. Job done.

      This would also explain why they didn't make a big deal about the release. The customers that count would get the word directly, not through a press release. So why spend the money? (Of course having a piss poor performance does not help either.)

      --
      There is nothing so silly as other peoples traditions, and nothing so sacred as our own.
    15. Re:I'm kinda shocked... by slipnslidemaster · · Score: 1

      ...and those braindead brand buyers that buy from braindead manufacturers that have exclusive deals with Intel that don't even offer AMD chips! So basically, Dell will subsidize Intel until Intel catches up to the AMD offerings (if).

      --


      "What the hell is an aluminum falcon?"
    16. Re:I'm kinda shocked... by wpmegee · · Score: 1

      I believe the word you're looking for is "Itanic".

    17. Re:I'm kinda shocked... by diegocgteleline.es · · Score: 1

      Itanic is for servers; I can't see how Intel could make desktops CPUs from Itanic, I wasn't talking about itanic

    18. Re:I'm kinda shocked... by gytterberg · · Score: 1

      ZOMG! A Berkely MBA with decades of experience as Chief Executive Officer of a tech company! They're headed straight down the toilet, I tell you, just like all those other tech businesses administered by people with business degrees.

    19. Re:I'm kinda shocked... by Anonymous Coward · · Score: 0

      do people really think that intel didn't planned nothing after pentium4 and that they were going to keep releasing faster & hotter pentium4's forever?

      Yes. That was Intel's plan. The P4 was supposed to go to 10GHz. Intel had counted on a smooth transition to 90nm. It was a shock to the whole industry that 90nm was harder then expected. AMD and IBM had the same problems with 90nm. I don't think it was a mistake of Intel's to bet on the P4. Most of the industry believed Intel could pull it off. But it was a gamble, and Intel lost. Intel did make a mistake underestimating the demand for x86-64. Although it is hard to tell if that is demand for the 64bit extentions, or demand for the AMD processors. Another mistake was not planning for the transistion to dual core. AMD's x86-64 core was designed from the beginning to support dual cores. It is probably better to look at what AMD did right instead of what Intel did wrong.

    20. Re:I'm kinda shocked... by Anonymous Coward · · Score: 0

      Intel knew what they were up against and somehow didn't cut it? Intel has been the masters of their domain for a long time and I'm rather astounded that they couldn't come up with something to 1-up the competition this go-around.

      Masters of their domain? Maybe in corporate contracts with places like Dell.

      But on the street, AMD has had Intel's tech on the ropes for the past 2-3 years. Lower power for better performance, a 64bit chip that speeds up 32bit operations while allowing for future migration to 64bit operations. Not to mention the heat issues with the P4 line, requiring noisier cooling systems while delivering the same performance (roughly) as the AMD solutions.

      Intel made two big mistakes in the last 10 years.

      1) Itanium - making a 64bit chip that was supposed to be the "future", but not making it x86 compatible. (Or at least, not compatible enough to run without a penalty.) As an end-user, why would I buy into an unproven architecture that might meet my needs in a few years when I can buy an Opteron/AMD64 which meets my needs today (seamlessly) and eases the transition.

      2) Pushing the P4 architecture and trumpeting Mhz > everything. Everything I've seen over the years indicates that something went awry in this. Either marketing got involved in the decision making process, or they were trying to market their way out of a bad decision. As a result, their processors are now derisively referred to as "space heaters" because they didn't pay attention to users who are starting to pay more attention to ergonomics of the systems.

      Their mobile Pentium line (based off the P3 architecture?) is promising. Lower power, lower frequencies, better performance. The question is whether they can do anything with it.

    21. Re:I'm kinda shocked... by RustyTaco · · Score: 1

      FYI, the P4M still blows, you're thinking of the Pentium-M, aka, Centrino.

      - RustyTaco

    22. Re:I'm kinda shocked... by Worminater · · Score: 1
      fx51 was the first "desktop" amd64; and that was on 940 chipset (ecc ram, etc)

      who is to say that intel wouldn't ahve dropped itanium down to desktop usage if it had recieved a better reception?

    23. Re:I'm kinda shocked... by Anonymous Coward · · Score: 0

      Shocked? Why? AMD had the opportunity to build a new chip with newer ideas. It had nothing to
      loose. Much like Linux, there were no expectations because everyone thought it would fail.

      Intel are still using the same ideas/materials so to speak. AMD looked at it a different way, a better
      way, and made it work.

      Didn't want to use this analogy but it fits: Like a dyson vacuum, over time normal vacuums (intel) loose
      suction.

    24. Re:I'm kinda shocked... by styrotech · · Score: 1

      Itanic is for servers; I can't see how Intel could make desktops CPUs from Itanic, I wasn't talking about itanic


      It might be only for servers now, but nevertheless that was what they were originally planning for. But long delays and the fact that noone really wanted IA64 anyway meant it wouldn't happen how Intel wanted it to. And Intels hubris was responsible for not realising this in time, and having no alternatives ready apart from quickly scramblimg to implement AMD64, quickly scrambling to base a whole new architecture on Pentium M tecnologies, quickly scramblimg to implement dual cores (once the P4s fabled scalability up to 10GHz proved wishful thinking) etc.

    25. Re:I'm kinda shocked... by leathered · · Score: 2, Interesting

      Exactly. And PHBs everywhere will lap them up because 'no one ever got fired for buying Intel'.

      But the PHBs don't have to work with the shit like their techies do. I work in in an all Dell shop and it's staggering how the quality of their desktops and more recently their servers has declined lately. And Intel has to partly shoulder the blame because these machines run hot. So hot that our air-con in the server rooom can't cope with the flames our new racks throw out.

      But it would be a brave techie to stand up in a management meeting and suggest buying AMD kit. As you said, Dell have filled the hole in their line-up and care little if the thing actually performs.

      --
      For all intensive porpoises your a bunch of rediculous loosers
    26. Re:I'm kinda shocked... by 32771 · · Score: 1

      Good point, and look at Dr. Barrett instead (the previous CEO): ...

      Dr. Barrett joined Intel Corporation in 1974 as a technology development manager. He was named a vice president of the corporation in 1984, promoted to senior vice president in 1987, and executive vice president in 1990. Dr. Barrett was elected to Intel Corporation's Board of Directors in 1992 and was named the company's chief operating officer in 1993. He became Intel's fourth president in May 1997, chief executive officer in 1998 and chairman of the Board on May 18, 2005.

      Dr. Barrett is the author of over 40 technical papers dealing with the influence of microstructure on the properties of materials, and a textbook on materials science, Principles of Engineering Materials. ...

      There is a little bit more in the brain department he has to offer. One may wonder though, how much influence a CEO has on technological decisions.

      --
      Je me souviens.
    27. Re:I'm kinda shocked... by Michael+Hunt · · Score: 1

      Well, Merced was out (with delay) but for sure it wasn't 64-bit or based on RISC core.

      Merced was the first generation of Itanium, which was definitely 64-bit, and arguably RISC (it used the basic principles of VLIW, which Intel bastardised and renamed EPIC.)

    28. Re:I'm kinda shocked... by sjames · · Score: 1

      They don't have to win the speed race. They don't have to make it better than AMD in any way. They just need something to fill the "dual core server processor" space in Dell's lineup. They delivered it. Job done.

      Agreed. The dual core Intel line is a marketing rather than an engineering achievement. AMD produces two tightly coupled cache sharing cores on a single die, Intel glues two single cores together with minimal glue logic and no more coupling than two seperate chips on a MB and calls it dual core (knowing well that it only dual core in the same way that a dog is an automobile because it moves on it's own).

  3. AMD's dual cores are great by jarich · · Score: 5, Informative
    I just bought my wife a dual core (3800 model) and it's just as responsive as my dual Opteron. I'm seriously considering selling my dual CPU box and getting a dual core myself just to have fewer fans in the box and generate less heat.

    I had been considering an Intel dual core but it sounds like I need to aim for an AMD instead.

    1. Re:AMD's dual cores are great by master_p · · Score: 3, Funny

      I just bought my wife a dual core

      Lucky you...she asked me to buy her a diamond core...

    2. Re:AMD's dual cores are great by jarich · · Score: 1

      I got her using Gimp for some basic graphics and she was not longer happy with her "slow" 1700+ box. :) She's also wanting to get Photoshop and I told her it needed the power. heh...

    3. Re:AMD's dual cores are great by js3 · · Score: 2, Insightful

      The only reason to get an intel dual core is price. They aren't real dual-cores hence the abysmal performance when stacked against the amd versions, but the amd ones also cost an arm and an leg.

      --
      did you forget to take your meds?
    4. Re:AMD's dual cores are great by The+Tyro · · Score: 1

      Agreed... there is nothing like working on a dual-processor box. I'm using a dual-core 4200, and it's as responsive as my old dual-athlon workstation.

      Many claim that there is no real difference between dual and single processor machines for most common applications... but subjectively (and I'll allow that it could be psychological), dual-processor machines simply feel snappier.

      Programs seem to open more quickly, and there is none of that barely-perceptible "lag" that seems to happen when you have a bunch of windows open, and a full system tray.

      --
      Even if a man chops off your hand with a sword, you still have two nice, sharp bones to stick in his eyes.
    5. Re:AMD's dual cores are great by DrSkwid · · Score: 4, Funny

      A *real* geek would get a dual dual core ;)

      --
      There are places where the networks are not touching,and there are places where they are-Boeing's Lori Gunter
    6. Re:AMD's dual cores are great by Anonymous Coward · · Score: 0

      I have an Athlon 64 X2 4800 (fastest available at the time) for just £360, cheaper than the fastest Intel CPU (which was only single core too).

      I am not sure why Intel CPUs are soooo much more expensive, but I am glad I decided to go for an AMD this time. Up till now, I have always bought Intel, but this purchase has convinced me that Intel is no longer top-dog for consumer CPUs.

    7. Re:AMD's dual cores are great by Michalson · · Score: 1

      The main reason for that seems to be that AMD isn't releasing "low end" dual cores like Intel is (they partially relented by offering one as low as 3800+, but that's in comparison to Intel making the Pentium D range from 2800mhz to just 3200mhz).

      Most likely they don't want to have their dual cores competing/overlapping with their regular Athlon 64 line (the "high value for low money" group). They'd rather have all their processors targeted at seperate groups - 64 for joe consumer and budget gamer, FX for extreme gamer, X2 for media creation and other heavy data processing, and the Opteron for high performance 2 way/4 way servers.

    8. Re:AMD's dual cores are great by Jherek+Carnelian · · Score: 4, Informative

      They aren't real dual-cores hence the abysmal performance

      No, they are honest-to-goodness real dual cores. Two fully functional cpus in a single socket.

      The problem is that the socket only has enough memory bandwidth for one cpu's worth of work. So, even if you double the number of cpus, you still can't shovel the data in and out fast enough to keep up with the work being done. Thus one of the two cores is almost always stalled out waiting on memory.

      The AMD chips have got more memory bandwidth, so they can keep both cpus fed with data reasonably well.

    9. Re:AMD's dual cores are great by ender- · · Score: 1

      No, a REAL real geek would get a Tyan Thunder K8QW with the M881 expansion board for a total of 8 sockets, populated with 8 dual core procs for a happy grand total of 16 processor cores! [droooool].

      This of course assumes that the real-real geek is also independantly wealthy.

    10. Re:AMD's dual cores are great by OverlordQ · · Score: 1

      Yowza, 8 opterons? Might as well finance a small country instead.

      --
      Your hair look like poop, Bob! - Wanker.
    11. Re:AMD's dual cores are great by Anonymous Coward · · Score: 0

      A real geek wouldn't buy a dual core AMD for his wife, he would marry a dual core AMD.

    12. Re:AMD's dual cores are great by geekee · · Score: 1

      "I just bought my wife a dual core (3800 model) and it's just as responsive as my dual Opteron. I'm seriously considering selling my dual CPU box and getting a dual core myself just to have fewer fans in the box and generate less heat.

      I had been considering an Intel dual core but it sounds like I need to aim for an AMD instead."

      We replaced the pocessors in our dual-cpu boxes, with dual core chips, effectively giving us quad processor machines.

      --
      Vote for Pedro
    13. Re:AMD's dual cores are great by Eukariote · · Score: 5, Insightful
      The AMD chips have got more memory bandwidth, so they can keep both cpus fed with data reasonably well.

      Not just that. The AMD dualcore chips have an on-chip connection between the cores: both cores share a crossbar fronting the memory controllers and have the on-chip equivalent of a coherent HyperTransport connection. So, you see, the AMD design is in fact a real dual-core design. The current Intel dual-cores, on the other hand, share nothing on-chip.

    14. Re:AMD's dual cores are great by ender- · · Score: 1

      Sorry to reply to my own post, but just for kicks, I spec'd out the ULTIMATE system using that board.
      8 dual-core Opterons, 128GB RAM, 8 500GB SATA2 HD's with HW RAID...
      Final price [NOT including monitor/lcd]: $95,000!
      Yeah, definitely need to be an independantly wealthy geek.

    15. Re:AMD's dual cores are great by GuidoW · · Score: 1

      If you're going for "best money can buy", then why use SATA disks and not SCSI (maybe in the form of SAS) ones?

      --
      If it's so secret, then how come I've never heard of it?
    16. Re:AMD's dual cores are great by FluffyWithTeeth · · Score: 1

      Geez, I've got a pile of those in my basement.

    17. Re:AMD's dual cores are great by quarkzone · · Score: 4, Insightful
      The problem is that the socket only has enough memory bandwidth for one cpu's worth of work.

      This is exactly right. It is really surprising that Intel has focussed so completely, almost obessively, and for so long, on the problem of supplying the maximum number of work-cycles per unit of time (GHZ, Pipelining, Itanium's EPIC design) while seemingly paying so little attention to supply-of-work-to-do (FSB speed and architecture)

      AMD has paid quite a bit of attention to the work-supply and has a much more efficiently balanced work-cycle-supply/ data-for-work design. http://www.hypertransport.org/ gives AMD a big leg-up over Intel.

      If Intel fails to do something spectacular to FSB speeds, AMD is sure to continue to pull away from Intel. The more cores and threads per CPU, the greater AMD's lead over Intel will become (at least from a performance point of view), until Intel addresses this problem.

    18. Re:AMD's dual cores are great by CyricZ · · Score: 1

      I think that's a great testament to the amount of power you can get for a mere $100000 these days. I wouldn't be surprised if a system like that were more powerful than all of the systems of the 1970s combined.

      And remember a dollar today is worth a whole lot less than it was in the 1970s.

      --
      Cyric Zndovzny at your service.
    19. Re:AMD's dual cores are great by markdesign · · Score: 1

      you mean this?

      http://www.apple.com/powermac/

      ~mark

    20. Re:AMD's dual cores are great by pyrrhonist · · Score: 1
      but subjectively (and I'll allow that it could be psychological), dual-processor machines simply feel snappier.

      *** WHOA THERE!!! ***

      Your post is trying to invoke "Teh Snappy" outside of an OS X article.
      The recommended value for $teh_snappy on this architecture was "undef"!

      Turn in Geek Card now? [y]

      --
      Show me on the doll where his noodly appendage touched you.
    21. Re:AMD's dual cores are great by WuphonsReach · · Score: 1

      Prices on the AMD dual-core stuff isn't all that bad. I happened to be shopping around for dual-core chips this week.

      Opteron 165 (2x1.8Ghz, 2x1MB cache, 939pin) - $475
      Opteron 170 (2x2.0Ghz, 2x1MB cache, 939pin) - $540

      Opteron 244 (single core, 1.8Ghz, 1MB cache, 940pin) - $240
      Opteron 246 (single core, 2.0Ghz, 1MB cache, 940pin) - $235
      Opteron 248 (single core, 2.2Ghz, 1MB cache, 940pin) - $340

      So for the Opterons, the 165 and 170 chips are roughly the same price as a dual-CPU configuration. You just get the advantage of getting that performance (roughly) in a single chip instead of 2 chips. The dual-core / dual-CPU capable chips (265 / 270 / 275) are more expensive (but easier to obtain).

      Opteron 265 (2x1.8Ghz, 2x1MB cache, 940pin) - $725
      Opteron 270 (2x2.0Ghz, 2x1MB cache, 940pin) - $900
      Opteron 275 (2x2.2Ghz, 2x1MB cache, 940pin) - $1100

      Figure you're paying for both performance (more power in a smaller package) and being able to put 4 cores in places where you could only fit 2 cores before. Definitely a bit of a price premium for these since they're on the leading edge. The 270/275s are priced higher then what I'm comfortable spending for a home machine, but not that bad if I was building a dual-CPU / dual-core server.

      --
      Wolde you bothe eate your cake, and have your cake?
    22. Re:AMD's dual cores are great by Jherek+Carnelian · · Score: 1

      So, you see, the AMD design is in fact a real dual-core design. The current Intel dual-cores, on the other hand, share nothing on-chip.

      Uh yeah, both AMD and Intel are true dual core. I never said otherwise. However, you seem to be implying that since AMD has an xbar and intel just has a bus that somehow means something relevant to being a dual core or not. It doesn't.

      In fact, if you want to be picky about it, since a single core AMD64 chip has a single memory controller onboard, a completely dual implementation would involve 2 memory controllers instead of just one behind a xbar. Since Intel's chips have no onboard memory controller, it doesn't matter since 0*2 is still 0.

      Not that I would make that argument, but it makes just as much sense as saying "since AMD designs share a memory controller and Intel designs share nothing, the AMD designs are true dual core and Intel is not."

    23. Re:AMD's dual cores are great by bill_mcgonigle · · Score: 1

      Don't worry - it applies to OSX too.

      I regularly work on two Macs in the same office - 1 is a 2x500MHz and the other is a 1x1.2GHz. The dualie 500 always finishes booting, installing updates, whatever faster than the 1.2. They both have the same amount of RAM, same apps, same OS, A-OK directory structure, and the 1.2 has a faster hard drive.

      --
      My God, it's Full of Source!
      OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
    24. Re:AMD's dual cores are great by Fweeky · · Score: 1

      You probably get more performance, if anything, since you're using faster unbuffered memory.. but that makes it tougher to add lots of memory to a system. Every S939 motherboard I've seen tops out at 4G (4*1G), dual sockets generally support up to 16G (8*2G); some even do 16*2G or more if you're willing to drop the memory speed and remortgage your house.

      This seems to be the way AMD are balancing single socket dual core with dual socket configurations; drop the registered memory and max out at 4G so you can't just go build a 16G 165 or so.

      One thing I haven't worked out yet is what makes an Opteron 175 any way different from an AMD64 X2 4400. The only distinction seems to come in the low power models such as those used by Sun; anyone noticed anything else?

    25. Re:AMD's dual cores are great by Anonymous Coward · · Score: 0

      I think he meant a dual dual core "in a real computer".

    26. Re:AMD's dual cores are great by ender- · · Score: 1

      If you're going for "best money can buy", then why use SATA disks and not SCSI (maybe in the form of SAS) ones?

      You're right. I'm so used to discounting SCSI due to its cost, that it didn't even cross my mind.
      In that case, subtract the 8 500GB SATA HD's @ $373.50ea and replace them with 8 300GB U320 HD's @ $985.00each.

      $99,355... wheeee :)
      Then again, you are losing 1.6TB of raw space by doing that so I guess it depends on if you're going for speed or space with the HD's.

      A drool-worthy system either way you go.

    27. Re:AMD's dual cores are great by toddestan · · Score: 1

      Yeah, definitely need to be an independantly wealthy geek.

      Or patient. In 15 years, systems with that kind of power will be sitting on the curb, free for the taking.

    28. Re:AMD's dual cores are great by Anonymous Coward · · Score: 0

      Do the X2's support ECC? I'm assuming that the 939 Opterons support ECC... (still digging).

  4. Stupid pre-retail release by dada21 · · Score: 5, Interesting



    This release seems dumb for Intel. No optimized motherboards, outrageous power requirements and a really inefficient core? It isn't even alpha-release worthy. Why would Intel release a product that is just waiting for a poor review? Is the high end market that hungry?

    The article didn't need 15 pages to explain Intel's mistakes. Intel will lose more customers to AMD than if they had waited until they had a viable and competitive product.

    400W while idling? For sub-standard performance? Yay.

    1. Re:Stupid pre-retail release by Ihlosi · · Score: 4, Interesting

      Is the high end market that hungry?

      No, the high-end market is waiting for something that has "Intel" and "Dual Core" written all over it. Everything else is irrelevant.

    2. Re:Stupid pre-retail release by flazz · · Score: 0

      They wont lose anything as long as the we keep seeing Intel adverts, and as long as we don't keep seeing AMD adverts. Until AMD starts selling the image of AMD they will always be the 'dirty chip' in the minds of PHBs and fanboys.

      Who knows, they will probably market higher power consumption as being a good thing because its working harder than other chips.

  5. Wow by Canadian_Daemon · · Score: 3, Interesting

    From the article... 4 cores with 4 Virtual CPU's. What a beast. And they even talk about licensing issues
    we were curious if having eight processors (four physical cores + four virtual processors) would cause operating system-related licensing issues. After all, even multi-threaded operating systems like Windows XP Professional are sold with a "2 Processor" limitation. While technically the system still only has two physical processors, dual-core and Hyper-Threading technologies are certainly pushing this limitation further than Microsoft originally intended.
    I find it interesting how, in a world of IP, somebody out there ( Intel ) can still 'cheat' the system by creating dual core CPU's which still count as a single processor, thus allowing for a system like this.

    --
    This sig is definitive. Reality is frequently inaccurate.
    1. Re:Wow by Hado · · Score: 1
      Anyone care to explain the relevance of a virtual processor for performance issues? Four physical cores means at most four processes running parallel, no?

      This is not intended as a sarcastical remark; I'd really like to know... :)

    2. Re:Wow by BlogPope · · Score: 1
      I find it interesting how, in a world of IP, somebody out there ( Intel ) can still 'cheat' the system by creating dual core CPU's which still count as a single processor, thus allowing for a system like this.

      This isn't cheating. Microsoft & others must update their licensing to accomodate. And its not as clear as the Hyperthreading issue that they will. On the bright side, you can usually turn off Hyperthreading in the short term, to get it down to a "managable" 4 CPU's

      --
      My other car is a Popemobile
    3. Re:Wow by Homology · · Score: 1
      I find it interesting how, in a world of IP, somebody out there ( Intel ) can still 'cheat' the system by creating dual core CPU's which still count as a single processor, thus allowing for a system like this.

      Time changes: One upon a time multi-CPU was high-end and expensive. But now you'll find them on consumer PC very soon (in the form of dual core CPU), and Microsoft along with others will steadily relax the CPU count requirements. Of course, Intel is not "cheating" the system: they just make CPUs....

    4. Re:Wow by nahpets77 · · Score: 1

      I'm just guessing here, but maybe they added an extra set of registers so that context switches are almost instantaneous?

    5. Re:Wow by Jerrry · · Score: 1

      Microsoft has been saying for some time now that it licenses XP Pro by socket, not core. So a system with two dual-core Xeons with hyperthreading turned on still counts as only two sockets.

    6. Re:Wow by Anonymous Coward · · Score: 0

      Each physical core has Hyperthreading, which doubles up enough of the units in the CPU to execute 2 instructions in parallel.

    7. Re:Wow by Mercano · · Score: 2, Informative

      Extra set of registers, yes, but no context switching. CPUs have a few different operational units, one or two dedicated to integer math, a seperate one for floats, one for memory I\O and mabey a unit for vector operations (SSE). A proccess isn't going to be using every resource at once. The whole thing can sit idle if it has to wait on something to get pulled from memory. Hyperthreading takes advantage of this by using a fancy scheduler that can juggle the needs of two proccesses at once. Only needs but extra silicon for a second register set and the advanced scheduling unit, but you get a performance gain similar to adding an entire extra core.

      Obligitory wikipedia link

      --
      #include <signature.h>
    8. Re:Wow by Trepalium · · Score: 1
      Microsoft has said that they license based on physical CPU, not virtual or cores. IBM and Oracle, on the other hand, intend to ding you for every core. Red Hat and SuSE also charge per physical CPU rather than by core.

      Multi-core chips and virtualization are starting to challenge the way software vendors license their products.

      --
      I used up all my sick days, so I'm calling in dead.
    9. Re:Wow by Anonymous Coward · · Score: 0

      W00t! My Athlon K7 Slot doesn't require a Windows XP license!

    10. Re:Wow by Vancorps · · Score: 1
      This would be assuming the two processes don't have similar requirements which works fine in workstations where you are likely multitasking different apps. But in the server world you are probably multithreading a single app with the same characteristics. As a result the two threads end up fighting for control which is a common problem among machines with HT that are maxed out. The video streaming and encoding servers here at my office are an example of that. Shut off HT and have two dedicated threads since they are both dual processor and you end up with better performance than with HT. Database side I've seen similar results.

      Compare that to the dual core Opterons and well, they don't even compare.

      I don't understand how Intel is lagging so far behind here. Shared bus for SMP? Are they insane? 8-way Xeon vs 8-way Opteron. Watch the Xeon choke while the Opteron performs at its peak. Intel needs to take a few steps back and rethink this if they want to start competing again. As of right now I can't think of any server I would want an Intel chip in. Workstations are indeed a different story, then they at least sort of compete. Amazing to me.
    11. Re:Wow by Anonymous Coward · · Score: 0
      This would be assuming the two processes don't have similar requirements which works fine in workstations where you are likely multitasking different apps.

      Even with two exactly similar (code-wise) threads, there will be many periods when one thread will hang waiting to read data from RAM -- this wait will be hundreds of CPU cycles. The other thread will now execute its instructions.

      There are some downsides as well. Turning on HT reduces resources, ex. L1 cache is probably halved, one HT thread a half. This will reduce single-thread performance.

  6. Redheaded stepchild? by Holi · · Score: 2, Interesting

    How can you call the most prevalent x86 server cpu the redheaded step child. I would say the itanium was the redheaded stepchild not the popular xeon.

    --
    Sorry, teleporters just kill you and then make a copy. A perfect, soul-less copy.
    1. Re:Redheaded stepchild? by Nom+du+Keyboard · · Score: 1
      I would say the itanium was the redheaded stepchild not the popular xeon.

      The glowing cherry red on top of the chip packaging stepchild.

      --
      "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  7. Re:Dual Core Apples by 0110011001110101 · · Score: 3, Funny

    mmmm.. an apple with dual cores.. I'll have to get a new apple corer of course...

    --
    Don't anthropomorphize computers: they hate that.
  8. Power Consumption by matr0x_x · · Score: 5, Funny

    This is the 21st century in North America, since when do we care how much power a CPU uses. *Drives away in Hummer*

    --
    LINUX ONLINE POKER: Linux Poker
    1. Re:Power Consumption by OverlordQ · · Score: 2, Funny

      Well I assume it's not due to the mistaken belief that having a large power hungry computer is safer.

      --
      Your hair look like poop, Bob! - Wanker.
    2. Re:Power Consumption by Martin+Blank · · Score: 1

      Says you. My CPU runs so hot that it executes every virus it sees.

      Now I just need to hope that no one lets loose one of those extremophiles...

      --
      You can never go home again... but I guess you can shop there.
    3. Re:Power Consumption by walt-sjc · · Score: 2, Insightful

      We care when we have our servers at a colo, and end up only being able to fill our racks 1/3 full due to the massive heat output and power usage. Most colo's are built for somewhere around 300W per square foot. If your servers are more efficient, you pay less for power and less for rackspace.

    4. Re:Power Consumption by Jozer99 · · Score: 1

      Since about August 30th. (Pedals away on solar powered scooter)

    5. Re:Power Consumption by FidelCatsro · · Score: 1

      I would rather my CPU didn't execute any viruses , chmod 000 virus

      --
      The only things certain in war are Propaganda and Death. You can never be sure which is which though
    6. Re:Power Consumption by fossa · · Score: 1

      Sorry... a scooter with pedals? And why pedal if it's solar powered?

      On a different note, I'm curious as to the energy efficiency of a human on a bicycle as compared to a car (with one or four human riders)... but I'm not really sure where to start.

      I guess you could say a car gets 25 miles per gallon or so, and calculate miles per input energy given that a gallon of gas stores X joules of energy... then somehow calculate the energy spent to pedal a bicycle a mile... surely someone has done this?

    7. Re:Power Consumption by Fulcrum+of+Evil · · Score: 1

      Well I assume it's not due to the mistaken belief that having a large power hungry computer is safer.

      Well, I have electric heat, so it really doesn't matter how much power my computer uses.

      --
      "We returned the General to El Salvador, or maybe Guatemala, it's difficult to tell from 10,000 feet"
    8. Re:Power Consumption by Martin+Blank · · Score: 1

      It was two jokes in one. I'll make a note to make them less subtle next time.

      --
      You can never go home again... but I guess you can shop there.
    9. Re:Power Consumption by FidelCatsro · · Score: 1

      I had thought that at first , It did come through .. but then I thought about it again .
      The Apology is mine to make

      --
      The only things certain in war are Propaganda and Death. You can never be sure which is which though
    10. Re:Power Consumption by Jozer99 · · Score: 1

      I think so. I haven't seen it, but I'm pretty sure that a human on a bike is still more efficient. For instance, you can go on a 25 mile bikeride and use much less chemical energy than is in a gallon of gas (a lot more than is in the equivalent sized serving of pasta). You have to figure that the majority of people in cars are carrying less than 4 people. A bus makes much more polution than a car, but is cleaner because it caries 30 people. If everyone drove around with no less than 4 people at all times, we wouldn't be in the environmental tight spot we are today. Also, you can figure that a bicycle is about 90% efficient in delivering power from the pedals to the road (losses due to friction in axle, chain, tires, ect... A car can never be, by the nature of internal combustion engines, more than about 35% efficient. This is why electric cars could be a better mode of transportation. Powerplants generate electricity at much better than 35% efficiency, so if high efficiency electric motors and batteries developed, cars could potentially be a lot cleaner than now.

    11. Re:Power Consumption by WalksOnDirt · · Score: 1

      You are ignoring the low chemical efficiency of the human body in converting chemical energy into work. I believe the bicycle is more efficient in terms of people miles per calorie, but mostly due to not moving a multi-thousand pound car around.

      --
      a,e,i,o,u and sometimes w and y (at be if of up cwm by)
    12. Re:Power Consumption by Jozer99 · · Score: 1

      But the human body, or any other living thing, is orders of magnitude better at processing chemical energy than a car.

    13. Re:Power Consumption by WalksOnDirt · · Score: 1

      How can the human body be "orders of magnitude better" than a car when the car is already more than 10% efficient? Anyway, from http://www.uic.edu/aa/college/gallery400/notions/h uman%20energy.htm

      "We can view that 90 watts in yet another context. At best, only about one-fourth of the energy in food emerges as useful mechanical work. Thus, laboring on the treadmill--sustaining 90 watts for ten hours--itself requires more than 3,000 Calories. So Bellevue's inmates worked hard enough and long enough to require double the food intake of a normally active adult male."

      Not an easy question answer through Google, but http://www.cptips.com/energy.htm also claims 25%.

      So it appears that cars are about the same at processing chemical energy as the human body.

      --
      a,e,i,o,u and sometimes w and y (at be if of up cwm by)
    14. Re:Power Consumption by sjames · · Score: 1

      Well I assume it's not due to the mistaken belief that having a large power hungry computer is safer.

      I'm guessing it;s the new heatsinks with built-in crack pipe.

  9. Bah by Red+Flayer · · Score: 5, Insightful

    Got through several pages of the benchmarking before it appeared /.ed.

    First concern is that though the chip has been released, motherboards configured for it aren't close to release yet. I'd rather see it benchmarked as distributed, since that's what really matters to the end user.

    Second concern is power usage and heat production. If you can't make a chip as powerful as your competitors, you better make sure it is not as expensive to operate. Really, why would someone choose to use a chip that is less powerful, intrinsically costs more to operate, and costs more to cool? Chips are cheap enough that the operating costs are often now more expensive than initial cost.

    --
    "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    1. Re:Bah by amazon10x · · Score: 1

      why would someone choose to use a chip that is less powerful, intrinsically costs more to operate, and costs more to cool?

      Because there are MANY companies that have exclusive contracts with certain companies, specifically Dell. This forces themt o buy whatever solution Dell provides, in this case, power consuming low performance dual-core machines.

    2. Re:Bah by MrNemesis · · Score: 2, Informative

      Really, why would someone choose to use a chip that is less powerful, intrinsically costs more to operate, and costs more to cool?

      Regrettably, because it has the Intel logo on it. I'm lucky working in a company where if I say I want AMD, I get AMD. I'm sure there's plenty of hardware geeks on /. who've asked for a shiny new Opteron server and been smacked back by either a company "Intel-only" policy, or their reseller's "Intel only" policy.

      FWIW, AMD recently launched the new single-core Opteron 254 and it utterly trounces the Intel competition. Even in benchmarks that have been traditional strongholds for the Netburst architecture.

      --
      Moderation Total: -1 Troll, +3 Goat
    3. Re:Bah by Red+Flayer · · Score: 1

      In the long run, Dell is going to lose customer base if they do not offer better solutions. Evenutally, demonstrable cost savings for using AMD chips will convince companies to leave Dell.

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    4. Re:Bah by Red+Flayer · · Score: 2, Insightful

      Part of that will just take time to change. Demonstrable cost savings mean something to the PHBs... especially if they can present it to their PHBs.

      Although, I do think AMD could do a better job of advertising to the masses... which would definitely help with mindshare.

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    5. Re:Bah by MrNemesis · · Score: 1

      Indeed, as much as I like their chips, their marketing is abysmal, and a great part of me believes that their recent success has been due in no small part to grassroots geeks raving on about how great the chips are for server and workstation workloads. Pre-AMD64/x86-64, AMD were hampered in the server/workstation segment by poor chipset support (IIRC only the AMD 760 chipsets were available for Athlon MP's) which kept the MP's stuck on slow RAM for the majority of their lifetime. In the desktop sector, poor chipset support was another bugbear until nVidia came along and raised the bar considerably. Now that the memory controller is embedded in the CPU, there's alot less to go wrong in the chipset(s) - but the stigma of "AMD = slow and unreliable" still remains with some.

      The cost/benefit analysis is a great one (and how I originally got my boss to replace the 1.*GHz Willamette P4's he was buying with AXP's which gave about 30% more performance for the same system cost), but I don't think it's as easy to convince larger companies so quickly - like you say, it just takes time.

      And as much as I'd like to see Intel brought to justice for what I see are fairly clear antitrust violations (most notably the intentionally crippled compiler), I can't help but wonder if it would have helped AMD's bottom line if they'd spent their legal budget on a quality marketing campaign instead.

      --
      Moderation Total: -1 Troll, +3 Goat
    6. Re:Bah by Anonymous Coward · · Score: 0

      Chips are cheap enough that the operating costs are often now more expensive than initial cost.

      True, but hardware operating costs aren't being considered. I can't think of a single company that I worked for that even gave power consumption and operating costs a second thought. (Actually the facilities guys probably cared alot, but the IT guys didn't care.) Thankfully there are some signs that companies are starting to take notice. A year ago there was the announcement of the low power multi cpu cluster that fit under a desk (using VIA or Transmeta cpus, I don't recall). One of the ads for the new Sun opteron servers lists "cooler then Dell" as one of the selling features.

    7. Re:Bah by Red+Flayer · · Score: 2, Insightful

      Absolutely. Although one of the nice side effects of the legal campaign has been "free" marketing... the perception that they couldn't compete due to unfair trade practices, rather than inferior products, helps them with public perception.

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    8. Re:Bah by drsmithy · · Score: 1
      Really, why would someone choose to use a chip that is less powerful, intrinsically costs more to operate, and costs more to cool?

      Because "computers" consist of more than just CPUs.

  10. Don't worry by dsginter · · Score: 3, Insightful

    Intel is notorious for "Unnouncements". They will simply unnounce some strange new technology that is "coming real soon now" but they will leave out all of the details. This might just keep Dell from leaving them.

    --
    More
    1. Re:Don't worry by Anonymous Coward · · Score: 0

      WTF.. the mods are on crack "Unnouncements"? "unnounce"? I can't even read this post and it gets +4 insightful? There is zero insightfulness in the entire post...

  11. Is GamePC really Intel's target here? by hal2814 · · Score: 4, Insightful

    Is GamePC the best place to read benchmarks on a dual core Intel Xeon chip? The article appears to be /.ed already (or just REAAALY slow at my end) so I can't read the results, but I can't help but think somewhere called GamePC isn't exactly Intel's target audience here.

    1. Re:Is GamePC really Intel's target here? by manno · · Score: 1

      GamePC is a great place for server chip benchmarks, the guys their know their stuff. I havn't read this article yet, but I know I'll expect it to be good, as the rest of their reviews are.

    2. Re:Is GamePC really Intel's target here? by Anonymous Coward · · Score: 0

      Well, you *could* run the Quicktime trailer of Natalie Portman V for vendetta trailer at that insane 1920xsomething hi-rez if you prefer. But I'd bet you get similar results anyhoo. More entertaining.

    3. Re:Is GamePC really Intel's target here? by lithandie · · Score: 1

      Game PC: "Thanks manno, here's your check and keep up the good work."

    4. Re:Is GamePC really Intel's target here? by Anonymous Coward · · Score: 0

      Your right.

      Intel's target market is firms with decision makers who don't care (or even know) about what makes a chip better or worse.

      Outside of that, chip performence is fairly easy to benchmark using a wide variety of common applications. There is no reason to assume just because the place is named GamePC that the benchmarking will be primarily fps. GamePC sells (or at least the last time I was there) dual cpu machines using server class chips and has done quite a few reviews of server class hardware in the past.

    5. Re:Is GamePC really Intel's target here? by Anonymous Coward · · Score: 0

      Rumsfeld: Manno, I've heard good things about you. Would you be interested in a Iraq war Public Relations position for the DoD? Ari Fleischer is busy writing a book

    6. Re:Is GamePC really Intel's target here? by manno · · Score: 1

      What!? This is only half of what we negotiated!

    7. Re:Is GamePC really Intel's target here? by Mr+Z · · Score: 1

      They're paying by socket, not by core.

  12. Who would be suprised? by cybrthng · · Score: 3, Interesting

    Intel is engineering for it's next gen chips that are still vaporware as far as i'm concerned. AMD put out some great technology that works today.

    The big question will be who is the leader next year! As far as i'm concerned the opteron/amd64 has already proven intself against p4/xeon arch and it's up to the next gen chips to see who will stomp on who.

    Will AMD pull some new tech? Will Intel be able to deliver or will sun come around and smack everyone with the new Niagra chips?

    1. Re:Who would be suprised? by Anonymous Coward · · Score: 0

      The big question will be who is the leader next year!

      Not if you're buying servers this year.

    2. Re:Who would be suprised? by Anonymous Coward · · Score: 0

      AMD Opterons rock for sure (all the Althons suck as they have no heat protection) but you can't get any good motherboards for them.

      AMD: suck motherboards, Opteron is good

      Intel: good motherboards, suck-ass Prescott based CPU's

      It's a lose-lose situation for all of us us.

  13. Coral cache link by Freggy · · Score: 5, Informative

    http://www.gamepc.com.nyud.net:8090/labs/view_cont ent.asp?id=paxville&page=1

    Seems it's slashdotted already after 8 posts. Finally when will all slashdot-links be coralized automatically?

    1. Re:Coral cache link by MyLongNickName · · Score: 0, Flamebait

      Right after folks RTFFAQ and realize there are reasons that they don't auto-corralize.

      --
      See my journal for slashdot ID's by year. Mine created in 2005. http://slashdot.org/journal/289875/slashdot-ids-by-year
    2. Re:Coral cache link by hkb · · Score: 1

      It took Slashdot like 8 years to finally move to CSS, don't expect this any time soon.

      --
      /* Moderating all non-anonymous trolls up since 2004 */
    3. Re:Coral cache link by Spy+der+Mann · · Score: 1

      Seems it's slashdotted already after 8 posts. Finally when will all slashdot-links be coralized automatically?

      When Microsoft opensources Windows, probably. And that's because it would be the most read link in slashdot history EVER, so it would HAVE to be coralized. And then again, only maybe.

    4. Re:Coral cache link by Anonymous Coward · · Score: 0
      Right after folks RTFFAQ and realize there are reasons that they don't auto-corralize.

      Note that the FAQ does not even mention that some corporate firewalls and proxies block access to the coral cache and similar services. My employer blocks any access to nyud.net:8090 because it could be used as an anonymizing proxy. So if all links were coralized, I would not be able to view them.

    5. Re:Coral cache link by mrtroy · · Score: 1

      Error: 500 Internal Server Error

      Server CoralWebPrx/0.1.14 (See http://coralcdn.org/)

      Maybe because Coral Cache would become Coral Crash?

      --
      [I can picture a world without war, without hate. I can picture us attacking that world, because they'd never expect it]
    6. Re:Coral cache link by Quince+alPillan · · Score: 1

      Like maybe corporate firewalls that don't allow coral cache links.

  14. Stock market by 13bPower · · Score: 5, Funny

    Hello, Stock market? Please read slashdot. I need to sell my AMD stock and buy a new amp.

    1. Re:Stock market by alfrin · · Score: 1

      But does it go to eleven?

  15. Re:Nothing to see, move along. by ergo98 · · Score: 3, Insightful

    We all know AMD's dual core lineup trashes intel.

    I'm seeing Intel dual-core processors appearing in devastates AMD, as somehow their dual-cores are far less expensive.

    I've yet to see a mainstream PC with a dual-core AMD on the other hand.

  16. strange. by CDPatten · · Score: 4, Insightful

    You would think with all their resources intel could start to make a chip to compete with AMD.

    Its really surprising to think AMD blind-sided intel this badly (multi-core/x64), but I guess they really did. Good for them, and great for us. Once again supply and demand in the free market prevails.

    1. Re:strange. by Sir_Cockalot · · Score: 1

      Not so Strange...

      AMD and IBM have been sharing technology for some time. They both cam around with desktop 64s around the same time. IBM has been using dual core's on their servers for some time and I'm sure AMD benefited from IBM's experience while Intel has not.

    2. Re:strange. by Anonymous Coward · · Score: 0

      You would think with all their resources intel could start to make a chip to compete with AMD.

      Its really surprising to think AMD blind-sided intel this badly (multi-core/x64), but I guess they really did. Good for them, and great for us. Once again supply and demand in the free market prevails.


      It's not about being blindsided, it's about having a poor architecture, pure and simple. SMP Opteron systems were faster than SMP Xeons because each CPU had it's own memory, memory controller, and path to the memory. SMP Xeons have to share the same memory controller, memory, and FSB. Because of this a dual CPU Xeon server doesn't have any more memory bandwidth available than a single CPU Xeon, except now it has to split that memory between two CPUs.

      The same is only slightly less true for dual core. In the test setup they had the equivalent of 4 Xeon cores, all sharing the same memory, memory controller, and path to the memory. So now each core gets 1/4 of the memory bandwidth available for a single CPU Xeon server. You have far more processing power but you begin to starve your CPUs when it comes to supplying them data. Intel's answer to this has been to keep increasing the size of the onboard cache, which helps as long as your data fits in the cache. But it also tends to drive up costs, and at any rate is not nearly as effective as making more memory bandwidth available (which for Intel means upping the FSB speed).

      Generally speaking, if you are looking at dual core or SMP systems for memory intensive applicaitons, AMD will smoke Intel every time.

    3. Re:strange. by corngrower · · Score: 1
      Well, Intel wasn't exactly blindsided. They knew what AMD had set out for a roadmap. Intel had a roadmap too. That roadmap was increasing the processor speed of the Xeon's to beyond 4GHz and developing the 64 bit Itanium solution. Only thing is, the roads on Intel's map were rather bumpy and rough. The Itanium took longer than anticipated to get into production plus it hasn't been all that well received. Pushing the GHz on the pentium also ran into problems. To increase the clock speed, they went to longer pipelines. Only thing was that their branch prediction logic wasn't good enough to keep those long pipelines from stalling and the performance improvement wasn't what they had hoped for. They realized then that they were kind of in a hard place and have been frantically struglling to overcome these missteps. They've got a start now with the dual core Xeons, and I'm sure they'll be back in the lead in the not too distant future.

      The one thing they did do right was the Pentium-M. Their Israeli design team did a good job with this one. Because of the great success they've had with the Pentium-M chips in notebooks, they're not really struggling financially.

  17. Dude, you're getting whatever we sell you! by Wesley+Felter · · Score: 5, Insightful

    Dell is locked into Intel and they really needed dual core, so there it is.

    1. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 5, Insightful

      Yes, I think this is exactly why. Other big vendors - IBM, HP, Sun - they all have Opteron/Athlon machines in their line-ups. When I asked a Dell rep why Dell had zero, and no intentions to ever have any AMD, he said it was because AMD wouldn't be able to supply them enough CPU's. I call bullshit. AMD has a great deal of production capacity, and adding more all the time. Dell wouldn't have to all of a sudden convert 100% of it's line up with AMD. But, therein may lie the problem. They very-well might have to, or lose some insane deals with Intel. I think that's why they stay Intel - and mention it on every single Dell ad.

      If I could upgrade my existing 2P dell servers to even inefficient dual cores that run too hot, I'd do it. But I doubt my existing servers would be able to cool them, so it's probably not going to happen anywyas. If we could get 2x dual-Opteron servers, we'd jump on it for all our ESX servers - especially with ESX3 and native x64 memory support. SWEET! But no, we'll be stuck with Xeon "EMT64" bastardized x64 CPU's because we're locked into Dell.

      --
      - It's not the Macs I hate. It's Digg users. -
    2. Re:Dude, you're getting whatever we sell you! by Jeff+DeMaagd · · Score: 1

      Dell is locked into Intel and they really needed dual core, so there it is.

      If you need a big name company, then HP and SUN would be good alternatives, both offer Opteron-based servers and workstations.

    3. Re:Dude, you're getting whatever we sell you! by Bert64 · · Score: 1

      Dell claim that AMD couldn`t supply enough CPUs, so they sell none atall?
      The least they could do is supply some of their customers instead of none at all. They could also price the systems higher to keep demand lower until supply increased...
      On the other hand, the fact that dell claims AMD couldn`t meet supply suggests that dell knows the AMD systems would sell like hotcakes.

      As for being locked in to dell, how come? Hardware isn`t such a lockin scheme as software is, you can easily drop in a sun or hp server in place of a dell..
      And, the superior performance and lower power consumption of AMD processors is a valid business case for dropping dell and switching to another vendor.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    4. Re:Dude, you're getting whatever we sell you! by devaldez · · Score: 2, Informative

      I'm sorry, but you aren't listening to AMD very well if you call BS...in their own lawsuit they said they were selling every processor they could make...and adding several hundred-thousand Dell systems would completely burst them, even with the new fab.

      So, which current AMD vendor(s) would you like to sacrifice to all-mighty Dell, praytell?

      --
      "... but you can love completely without complete understanding." - Norman Maclean, "A River Runs Through It"
    5. Re:Dude, you're getting whatever we sell you! by Clover_Kicker · · Score: 2, Insightful

      > As for being locked in to dell, how come?

      He probably works for a big company with a list of approved vendors.

      His CIO probably plays golf with the Dell rep.

    6. Re:Dude, you're getting whatever we sell you! by truesaer · · Score: 0
      adding several hundred-thousand Dell systems would completely burst them, even with the new fab.


      This is flat out wrong.

    7. Re:Dude, you're getting whatever we sell you! by 99BottlesOfBeerInMyF · · Score: 1

      If we could get 2x dual-Opteron servers, we'd jump on it for all our ESX servers - especially with ESX3 and native x64 memory support. SWEET! But no, we'll be stuck with Xeon "EMT64" bastardized x64 CPU's because we're locked into Dell.

      If you have chosen a single vendor to supply all your systems, well you are getting what you deserve. Here's an idea, ask for bids from multiple vendors and let them compete, you get much better deals and you don't have to worry if one won't supply you with what you want.

    8. Re:Dude, you're getting whatever we sell you! by Loopy · · Score: 1

      You do understand that even Intel has had chip supply problems the last couple of years, right? This means that AMD is probably going to be in an even or worse boat than them, just from a purely market/supply brute strength perspective. It's disappointing, but it makes sense from Dell's perspective. Other companies are adopting what I consider to be a better strategy: fold in AMD gradually and see what happens re: supply ability.

      It isn't personal...just business.

    9. Re:Dude, you're getting whatever we sell you! by krakrjak · · Score: 1

      I call BS on the BS calling BS. AMD does have extra capacity. The good news for AMD is that the extra capacity doesn't cost them any extra money, because it's in the form of on-demand production from 3rd parties. The AMD reps I talk to really don't care about the Dell piece of the business right now. They prefere where they are, because they get to compete against Dell in the server/workstation space using HP, IBM and Sun together. They don't care which integrator get's the sell as long as AMD CPUs power the boxes.

      However, if Dell and AMD were to work out a deal it would be fantastic if Dell would replace Intel in some space for the AMD products. Otherwise there is a possibility that Dell might stick AMD into a not very well supported configuration or sell it without any marketing behind it, or any other way that could hurt AMD. I don't think AMD loses sleep at night worrying about Dell. There will be a point where Dell will give them a fair shake and feature AMD products. When that day comes AMD will be able to ramp production extremely quickly.

      Remember you don't have to fab everything yourself.

    10. Re:Dude, you're getting whatever we sell you! by Ryan+Amos · · Score: 1

      IBM too.

    11. Re:Dude, you're getting whatever we sell you! by frank_adrian314159 · · Score: 1
      So, which current AMD vendor(s) would you like to sacrifice to all-mighty Dell, praytell?

      Easy. HP. I've hated them ever since Carly...

      --
      That is all.
    12. Re:Dude, you're getting whatever we sell you! by Anonymous Coward · · Score: 0

      For small business techs, Dell's website allows you to play around with configurations, see how it balances against price, see how much a single option is going to cost. Lots of information to take to the person who signs the checks next door. Plus, you get power over the customization. You're not spending hours trying to find some pre-configured monster from the other shops, only to find out that it's not available and would you like to buy configuration Y instead.

      Do they make the best machines? Probably not. But for purchasing a single server every 6-18 months, their website is what seals the deal.

      (And yes, I wish they sold Opteron machines.)

    13. Re:Dude, you're getting whatever we sell you! by toddestan · · Score: 1

      I'm sorry, but you aren't listening to AMD very well if you call BS...in their own lawsuit they said they were selling every processor they could make

      That's a dumb statement. What else is AMD going to do with the processors they make? Well of course they sell them! What do you think they do, dump half of their output into the ocean or something?

    14. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 1

      I work for the State of Rhode Island, so no golf with the CIO. It's more like, they're the cheapest, and it was easier for them to work out a 'no bid needed' pre-approved system with Dell then any other vendor. Otherwise, every time we wanted to buy a server we'd have to get bids from three vendors.

      Personally, I hate the Dell servers. They're cheaper for a reason.

      --
      - It's not the Macs I hate. It's Digg users. -
    15. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 1

      I work for the state (RI) and we have a pre-approved setup with Dell. It means that we don't have to get bids/quotes from three vendors every time we need a new server, desktop, or mouse. They are cheaper almost every time, so that's what they set up.

      I don't like the Dell servers. The chrep price comes at the price of cheap stuff. And by cheap stuff I mean it sucks. We don't have too many servers; we've virtualized a lot of them with ESX. But the servers we do have have all had strange unexplained problems. Whereas at my last contract we ran 40 Exchange servers with pretty much zero oddball issues, we've had a bunch of problems with just the two at this place. And the DC's. And file servers.

      And let's not mention that the metal casing for a lot of Dell servers isn't finished very well. There's a lot of sharp edges that cut your skin too easily. Open up an HP (Compaq) or IBM server and you can tell there's more quality in the build.

      Fortunately, Linux seems to be able to handle the servers better then Windows. We've got a farm of ESX servers that seem to run very well - but they've only been online for less then 6 months so we'll see.

      --
      - It's not the Macs I hate. It's Digg users. -
    16. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 1

      Ohh - good idea. Then we'd have six different management consoles for remove recovery, six vendors for service and support, and no volume discount to speak of.

      You ever work at a data center? No?

      Plus, we're the state, and they chose to go with Dell. They're cheaper. Try to convince the director of corrections that they should go with IBM because .. umm, "it's better!"

      We have to do three bids on everything we buy, but not with vendors on the pre-approved list. Dell is on the list.

      --
      - It's not the Macs I hate. It's Digg users. -
    17. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 1

      I agree with your sediments about not wanting a half-assed product just to have one. Right now, Opteron servers are pretty high end. You see Opteron chips in heavy duty applications in very expensive and very sweet servers. This isn't always the case, but it is quite often. AMD chips are good - I've always liked them. What I like even more, however, is what it's forced Intel to do. With real competition on all x86 fronts, it's really made Intel release at a much faster rate then they did back in the day before the K6.

      In truth, Dell stuff isn't very good. I don't like it at all, especially since I've cut my hands on the sharp edges of quite a few dell server chassis. They can't even get that smoothed out a little? Talk about cheap. Hell, even a $50 home PC case can easily have better quality then that. Dell assembles systems, they don't manufacture. IBM manufactures their systems. The effect is obvious just by handling a few IBM servers versus Dell servers. But Dell is cheap..

      The one good thing about Dell, though, is that if you are a "Gold" or higher support customer, you do get decent support. That's been my experience anyways. Easy to get in touch with them, and they are responsive. I guess this is the case for most vendors with a premium support contract, but you'd figure with the cheap servers you'd also get cheap support.

      --
      - It's not the Macs I hate. It's Digg users. -
    18. Re:Dude, you're getting whatever we sell you! by Anonymous Coward · · Score: 0

      Unforuntately you'r wrong about this-- AMD's fab partner, Chartered Semiconductor, is still a long way from being able to produce CPUs to help AMD meet demand. It's going to be about a year, from what I read, before Chartered can begin to make parts for AMD, assuming all goes well-- and AMD has a history of things not going well with foundries (though with Chartered, they seem to be ready to share the crown jewels of their fab technology in the name of having the extra capacity on a "variable cost" basis, where they're not stuck sinking multibillions into a mega-fab before the first chip comes out). http://www.extremetech.com/article2/0,1697,1826658 ,00.asp reports that Chartered can make maybe 10M CPUs in 2006, 30M in 2007. Not insignificant but a while off.

      Dell is not the be-all and end-all of the marketplace anyway-- my thinking: Sun, HP, Fujitsu-Siemens (who just announced product) and IBM (especially Sun, being exclusive and having some really clever server designs Dell can't touch) can move as much Opteron as AMD can make, at wonderfully plump prices. Dell would get AMD into certain accounts they're not in now, but there's time enough for that later-- possibly much later.

    19. Re:Dude, you're getting whatever we sell you! by ccp · · Score: 1

      Yes, I think this is exactly why. Other big vendors - IBM, HP, Sun - they all have Opteron/Athlon machines in their line-ups.

      And now, with Fujitsu announcing their Opteron line, its everybody except one.

    20. Re:Dude, you're getting whatever we sell you! by Bert64 · · Score: 1

      Well maybe it`s time to reassess the situation, these new opteron based machines sun has been putting out are not only cheaper than comparable dell boxes, but considerably faster, smaller and more power efficient..
      Plus sun are a well known and established vendor.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    21. Re:Dude, you're getting whatever we sell you! by 99BottlesOfBeerInMyF · · Score: 1

      Then we'd have six different management consoles for remove recovery, six vendors for service and support, and no volume discount to speak of.

      You can't deal with different vendors recovery setups? Their are products, free products that solve this problem. Hardware support should be "ship us a replacement" it does not matter how many vendors there are for it. Software support from Dell is worse than useless and if you are going to bother with it you should go with another vendor anyway. Volume discounts are a scam, you get better deals by getting multiple vendor bids, those prices will come down.

      ...we're the state, and they chose to go with Dell.

      We're the government so it is OK to make stupid decisions and lock ourselves into a single vendor. Stupid is stupid.

      We have to do three bids on everything we buy, but not with vendors on the pre-approved list. Dell is on the list.

      This sounds to me like, "we have a procedure to prevent having a vendor take us in the rear either by bribing purchase agents or through predatory business practices, but then we implemented a bypass for it so we can still be screwed." Here's an idea, instead of just going with Dell because they are on a list, why don't you actually take multiple bids and see what happens. Why is it that people who have to make purchasing decisions are not required by their employers to take a basic business course on subject?

    22. Re:Dude, you're getting whatever we sell you! by cbreaker · · Score: 1

      First of all, I'm not the boss. Never said I was. So all this "why don't you just do this" is pretty easy for you to say, but it's not easy to get anything done quickly when you work for the state. I push, but there's only so much I can do, and only so much I *want* to do. I'm a technical person, not a business person. While I would prefer a different vendor then Dell, I'm not going to spend hours a day trying to get something else. I'd rather just get on to the work I was paid to do.

      It's not that I "can't deal with different vendor recovery setups" it's that I just don't have the time to deal with it. I'm one of a very few people working the IT infrastructure, and the help desk guys help me out. While I'm good with documentation and try to stay on top of it, if someone calls me it's a lot easier to have a centralized single point of recovery, contact, etc then saying "Ohh, RIDOCP04, that's an HP. You have to login to the ILO board for that one, and use these images, and do this, and do that. Call this guy, he's the HP rep. Ohh, you said RIDOCP05? That's a Dell. Login to the DRAC, it's a completely different system. Follow the 10 page document I had to draw up for that, and the images are here, and the drivers are there. The number for them is xyz."

      When you are overworked and understaffed, you need all the help you can get. It would be counter productive to have a whole different server every time, one that I can't just use my working ghost images for, and one I can't use my existing management tools for. ESX Server does help the situation a lot, and who knows, maybe the next ESX server could be a beefy Opteron Sun box because a VM is a VM. But for now, we buy server for server according to need - we can't buy a 10 pack in case we need more in the future. Would you rather me waste tax payer dollars working on the quote/bid process all day instead of just getting the job done with what I have? Especially when the benefits are mostly technical and inconsequential to most people?

      And no, it's not as insidious as you make the pre-approved list to be. There's a lot of vendors on that list because it can take months to go through the bid/quote process. Sometimes we just need that new switch NOW. Just like how they might need that new roof on one of the facilities NOW. You find vendors that you can trust, and you go through the process of adding them to the list - which isn't an easy process either. Dell servers aren't the best, and they have no AMD boxes. They work for the most part and they aren't expensive. My Dell rep gets me a very fair price on everything we order - I'm not a newbie that doesn't know market value on these things. There's nothing specifically that says we HAVE to go with Dell, but we currently have no other server vendors on the list. I should also mention that every purchase over $5000 needs to be approved by another department, whether it be on the list or not.

      Why is it that people who no government or data center experience believe they are the only ones to have ever thought of these things?

      --
      - It's not the Macs I hate. It's Digg users. -
  18. Nice, but.... by Bullfish · · Score: 2, Insightful

    Amd has thrashed intel for a few years now in terms of cpu performance so this is no surprise. What they really need to do is become more marking savvy. Most people don't know amd even makes chips. That includes many computer literate people as well, whereas even the luddites know who intel is

  19. < $700 - correction by ergo98 · · Score: 1

    Geez, I didn't preview so I suffer.

    "I'm seeing Intel dual-core processors appearing in < $700 PCs. From that angle Intel absolutely devastates AMD, as somehow their dual-cores are far less expensive."

  20. Re:Nothing to see, move along. by shamer · · Score: 1

    Is dual core the same as Intels Hyper Thread ? sorry for the noob question.

  21. Microsoft licensing by Anonymous Coward · · Score: 2, Informative

    If you get an older version of Windows, that machine will count as having eight processors. With Windows XP, Microsoft has clarified their view, namely that they count sockets, not cores or virtual cores. So Intel isn't cheating on this, they are doing exactly what Microsoft wants.

    1. Re:Microsoft licensing by vincecate · · Score: 1

      Microsoft told me that multi-chip-modules count as more than one processor. Paxville really is a multi-chip-module. I showed them a picture and asked, is Paxville a multi-chip-module (you can see the 2 die in the picture mind you) and if not, what is their definition of a multi-chip-module. They said they were reviewing their policy and could not answer at this time.

  22. Duke Nukem Being Rewritten by Anonymous Coward · · Score: 0

    No.

    Duke Nukem Forever is being rewritten to run on XFORMs. Thought that was sorta funny.

  23. Re:Dual Core Apples by Saven+Marek · · Score: 1

    > see http://211.28.70.211:1337/?page_id=23

    thank you thank you I been looking for a live update site for ages. looks apple banned such updates.

  24. Star Trek by jcr · · Score: 1, Offtopic

    Why is it that every time I see a story about this processor, I keep thinking about the Star Trek Nazi episode?

    -jcr

    --
    The only title of honor that a tyrant can grant is "Enemy of the State."
    1. Re:Star Trek by Anonymous Coward · · Score: 0

      Because you're insane?

  25. Intel is all about the Mhz by mahdi13 · · Score: 4, Interesting

    Intel has been really slacking more and more since AMD beat them in the 1GHz race. After that Intel has seemingly been focusing on making the 'fastest processor' and not improving on the design much.

    It seems to me that Intel procs these days are more of the same but overclocked; while AMD has been making their procs more efficient, by running cooler and streamlining the instructions.

    Faster isn't better these days and Intel needs to realize this before it's too late.
    I just picked up a +3200 AMD Sempron which is clocked at 1.8Ghz and compre that to the AthlonXP +1600 at 1.4Ghz I had before, it has well over double the perfomance in almost every application. From doubling the fps in Doom3 to cutting compile times down by half. For a 400Mhz difference there is a lot more going on then just 'speed'

    --
    "Some things have to be believed to be seen." - Ralph Hodgson
    1. Re:Intel is all about the Mhz by mahdi13 · · Score: 1

      Correction:
      I have a +3100 AMD Sempron not a +3200 AMD Sempron ;)

      --
      "Some things have to be believed to be seen." - Ralph Hodgson
    2. Re:Intel is all about the Mhz by diegocgteleline.es · · Score: 1

      After that Intel has seemingly been focusing on making the 'fastest processor' and not improving on the design much.

      Yeah, Intel is stupid. Their engineers didn't realize that their obviously-old netburst architecture couldn't compete against amd. How idiots they were.

      They probably should have hired you - It's clear that there's nobody in that multi-million company knew what you know!

      I wonder: if Intel would have been designing a complete revamp of their architecture supporting dual core and 64-bit instructions, and suddenly amd would have figured out a very crappy way of extending the 20-years-old x86 instruction set (you call that "improved design"?) to 64 bits (which had been previosly extended to support 32 bits) and AMD would have released it sooner than Intel, and the whole computer world would have supported AMD and operative system makers would have ported their OS to AMD's architecture, and the success of AMD's architecture would mean that the industry wouldn't accept future Intel's 64-bit designs because they're not compatible with AMD's architecture; would have Intel delayed their "architecture revamp" and would have Intel continue speeding up their old netburst architecture as a extreme measure meanwhile they redesign their roadmap?

    3. Re:Intel is all about the Mhz by dpilot · · Score: 4, Interesting

      Both parent post and grandparent post are making the mistake of assuming Intel's current problems are technical, and the result of engineering. That's utterly wrong, the problem is higher up - a product of corporate culture, management, and myopia.

      Since you brought up IA64...
      While I'd be one of the last to argue against the ugliness of the x86 instruction set, that does not mean that IA64 is necessarily better. From an instruction architecture point of view, IMHO IA64 looks like an academic exercise got sold to the executives well before it was really ready for prime time. Look at the sheer amount of money Intel and HP have dumped into IA64, Sure, they can get some impressive results, but I suspect that given THAT amount of cash, time, and engineering, x86, Alpha, Power, etc all could have reached at least the same performance level.

      It's necessary to realize that the number 1 problem it was designed for had nothing whatsoever to do with performance. IMHO, the prime purpose of IA64 was to prevent cloning. Neither Intel nor HP hold any of the IP on IA64 - it's all held by a third company, and Intel and HP are the licensees. That's because both Intel and HP are extensively cross-licensed with others in the business, including AMD. Had Intel and HP owned the IP for IA64, it would have come in under those cross-licensing agreements. By setting up the third company, there is no cross-licensing involved, and ONLY Intel and HP can product IA64.

      So IA64 is a product of "corporate myopia," of Intel being more concerned about it's internal problem of cloning than customers' external problems of power and performance, and I once heard it was another attempt by Carly Fiorina to "reset the clock" on her tenure by announcing a grand new strategy that needed her at the helm. Both are driven by internal politics, not the marketplace. It's a classic problem of big companies

      --
      The living have better things to do than to continue hating the dead.
    4. Re:Intel is all about the Mhz by Eukariote · · Score: 2, Interesting
      Yeah, Intel is stupid. Their engineers didn't realize that their obviously-old netburst architecture couldn't compete against amd. How idiots they were.

      Aside from the feeble attempt at sarcasm, the above does raise a serious question: were their engineers really that dumb? No, but they were not given a voice

      Intel's troubles were caused by hubris and marketing-driven decisions on the part of management. They went for the NetBurst/P4 design because MHz sells. They ignored warnings by the process specialists about the risks of such a high-frequency design. They assumed they had the monopoly power to move the market over to Itanium, and thus did not start planning an 80x86 design beyond NetBurst/P4 until AMD scared the shit out of them with Opteron/K8.

      It could have been much worse, even. The Pentium-M was a semi-skunkworks project by their Israeli design team. It is an evolution of the old PIII architecture. Without it, they would have been trounced in the mobile space, and would have had nothing to plug the gap between now and their wholly new architecture which is expected late 2006.

    5. Re:Intel is all about the Mhz by diegocgteleline.es · · Score: 1

      I didn't brought up IA64. Good or bad, Itanium is targetted for servers, no matter what POV you take. 128 GPRs? Huge amounts of cache? It's possible to sell a desktop CPUs based in itanium? I don't think so....but releasing another 64-bit architecture for desktops? Doesn't have sense either. God knows

      I don't know what intel was preparing before AMD's opteron was released, but it's clear to me that prescotts weren't in their roadmap - they KNEW presscots weren't suitable for that. There was something, and Intel had to stop it because the x86-64 acceptance ruined it.

    6. Re:Intel is all about the Mhz by raftpeople · · Score: 1

      Look at the sheer amount of money Intel and HP have dumped into IA64, Sure, they can get some impressive results, but I suspect that given THAT amount of cash, time, and engineering, x86, Alpha, Power, etc all could have reached at least the same performance level.

      I agree with your post but would also point out that Power5 already exceeds Itanium2 (significantly) (benchmarks TPC, SAP, etc.)

    7. Re:Intel is all about the Mhz by Anonymous Coward · · Score: 0

      Neither Intel nor HP hold any of the IP on IA64 - it's all held by a third company, and Intel and HP are the licensees.

      Do you know what this third company is called? Not that I think you're wrong, I just want to learn more. (I wouldn't be surprised if Intel did their best to hide it, but if it is a legit business, it must have a name at least...)

      just curious... (tia!)

    8. Re:Intel is all about the Mhz by dpilot · · Score: 1

      Now that you mention it, I don't. You might try asking on comp.sys.ibm.pc.hardware.chips, and for that matter I might, now that you've called me on it.

      --
      The living have better things to do than to continue hating the dead.
  26. Re:Yet strangly... by PygmySurfer · · Score: 4, Informative

    Intel's sales will again beat AMD's by several fold. The reason seems to be that most PC and server purchases are not intended for games, beyond Solitare of course, and people prefer the reliability, power savings and lower temperatures of the Intel chips.

    Did you miss the part where they said this chip consumes more power and runs hotter than Opterons?

  27. Why always gaming? by tomstdenis · · Score: 3, Insightful

    Why do they always do gaming as the benchmark? It's a server processor!!! Do some crypto!

    Check this out image where "nocona" is a Pentium 820D [dual-core 64-bit P4].

    Those are cycle counts for RSA-x private key operations [with padding] on various processors.

    TFM == tomsfastmath
    LTM == libtommath
    DC == dual-core [two threaded] tomsfastmath :-) Shameless plug but also good numbers when doing RSA work I guess.

    Tom

    --
    Someday, I'll have a real sig.
    1. Re:Why always gaming? by Anonymous Coward · · Score: 2, Informative

      Bad form replying to my own post [hence the AC]

      ops per second.

      FWIW, the AMD64 is at 2.2Ghz, AMD32 [Athlon-XP-M] @1.8Ghz, P4 @3.2Ghz, Nocona @2.8Ghz.

      So yes, a 3.2Ghz P4 Prescott gets roughly the same number of RSA/sec as a 1.8Ghz Athlon-XP ... :-) There is a slight power consumption difference [one of them tops out at 110W the other 45W ... I'll let you do the math].

      Tom

    2. Re:Why always gaming? by galaxyboy · · Score: 1
      This is /. No pro-Microsoft or pro-Intel posts are allowed here.

      I am always very skeptical of all benchmarking. I did work in neural networks. One of the things that you can't do is overtrain a network to a sample data set. It kills the ability of the network to accurately predict values on real data. The same can be said of benchmarking. If you spend too much time tuning to the benchmarks, you will hurt general performance....not to mention the other factors involved that are unrelated to the processor (like the chipset, cards, etc).

      Does anyone have a link to more server benchmarks. I don't have money to blow on a really expensive gaming machine anyway.

    3. Re:Why always gaming? by tomstdenis · · Score: 1

      My trick was to get a decent paying job and then buy a lot of gear [well lot for a private citizen, I own three high end desktops :-)] then do the testing.

      Generally the P4 is crap compared to the AMD64. In crypto [ciphers and hashes] it always takes more cycles to complete the same work and even with the clock advantage it rarely beats the AMD64 in walltime. Basically to reliably beat an AMD64 in cipher operations [w.r.t. walltime] you'd need to pit a 3.6Ghz or 3.8Ghz P4 against a 2.2Ghz AMD64. Below that and AMD wins. Not only that but it takes less power at the same time.

      The 'xeon' series of processors are no better, they're just P4s with more cache and the same core. So you pay a premium for what ammounts to window dressing.

      Tom

      --
      Someday, I'll have a real sig.
    4. Re:Why always gaming? by ip_fired · · Score: 1

      I don't think his post is pro-intel :).

      If I'm reading it right, the graph is measuring the number of cycles it takes to perform the encryption operation. The Intel P4 takes an insane number of cycles, and the new Nocona processors are substantially better. But then the AMD64 blows them all away.

      --

      Unrelated to the above posts, I've been impressed with my new AMD64 Cool and Quiet technology. In Linux (I'm not sure if Windows does this, I hope it does) it scales the processor's frequency based on it's load.

      Whem I'm browsing the web, the processor is clocked at 1.0Ghz, and when I go to compile something it shoots up to 2.2Ghz. It's great! less power consumption, less heat, quieter fans. As far as I can tell, my Pentium D at work doesn't do this, and boy do I wish it did, it gets hot in my office by mid-afternoon.

      --
      Don't count your messages before they ACK.
    5. Re:Why always gaming? by Anonymous Coward · · Score: 0

      You might like to learn that a single Itanium2 manages the 1,024-bit RSA moduli private key operation in less than 260,000 cycles.

    6. Re:Why always gaming? by dj245 · · Score: 1

      I'd love to see where a recent Via processor falls on that graph. According to some folks in the know, their hardware encrypting engine makes the recent Via chips cruise right through encrypting/decrypting tasks. They suck for anything else, but apparently they do excel at one thing and do it well.

      --
      Even those who arrange and design shrubberies are under considerable economic stress at this period in history.
    7. Re:Why always gaming? by tomstdenis · · Score: 1

      Granted, but find me off the shell PUBLIC DOMAIN software that will achieve that.

      TFM, LTM and LTC are freely accessible public domain libraries.

      And besides that, custom hardware [re: MUCH SMALLER] can do it with less latency.

      Tom

      --
      Someday, I'll have a real sig.
    8. Re:Why always gaming? by tomstdenis · · Score: 1

      VIA processors only accelerate AES [in ECB, CFB and CBC mode I think]. Not bignum math.

      As for where it falls? VIA processors are *less* efficient than a P4. Sure they take no power to run but they also take many times the cycles to do anything.

      Tom

      --
      Someday, I'll have a real sig.
    9. Re:Why always gaming? by Sebastopol · · Score: 1

      Dude, this is an ANTI-INTEL website. They'd never post stuff that makes their darlin' AMD look like a pile of puke.

      --
      https://www.accountkiller.com/removal-requested
    10. Re:Why always gaming? by tomstdenis · · Score: 2, Interesting

      Um, it isn't hard to make Intel look bad.

      Go to the store, buy two boxes, one an Intel Pentium 620, another an AMD Athlon64 3200+ or so [roughly price compariable I think].

      Grab two blank hard disks, two gentoo cds and one local distfile mirror. Start from stage1 and build a good 700 or so packages. Tell me how many ***hours*** of work you can complete on the AMD box before the Intel box is even finished.

      Not fair enough? Ok, try measuring the latency of ECC P-256 and RSA-2048 operations with the fastest code you can write for both [include the time it takes to write both as a cost].

      Not fair enough? Compare the energy consumed in doing these tasks.

      etc...

      Tom

      --
      Someday, I'll have a real sig.
    11. Re:Why always gaming? by Anonymous Coward · · Score: 0

      Nice axis labels on that graph... really helps to clarify the data!

    12. Re:Why always gaming? by Sebastopol · · Score: 1


      Any metric involving "how much work you do" and includes development time is worthy of a slap to the head with yardstick.

      Talking energy, yes P4 energy usage sucks ass.

      Now try doing any of benchmark with a Centrino. Now try one of the new dual core centrinos.

      Still want to talk about energy?

      Didn't think so.

      --
      https://www.accountkiller.com/removal-requested
    13. Re:Why always gaming? by Anonymous Coward · · Score: 0

      That word you use, I don't think it means what you think it means.

      http://www.intel.com/products/centrino/

    14. Re:Why always gaming? by Mr+Z · · Score: 1

      One thing working against the P4 is that in order to get to higher clock rates, they dumped their barrel rotators. Now rotates and shifts could take multiple cycles. That'll hurt you, since many crypto algorithms live on shifts and rotates.

    15. Re:Why always gaming? by Fulcrum+of+Evil · · Score: 1

      Granted, but find me off the shell PUBLIC DOMAIN software that will achieve that.

      Would you settle for something that's GPLed?

      --
      "We returned the General to El Salvador, or maybe Guatemala, it's difficult to tell from 10,000 feet"
    16. Re:Why always gaming? by Anonymous Coward · · Score: 0

      In case you didn't know, p-m sucks even more than p4 in these types of benches, and a dual p-m isn't around yet. The energy efficiency of AMD64 isn't much worse than p-m, BTW.

    17. Re:Why always gaming? by dcam · · Score: 1

      This is the ridiculous thing about intel. Why haven't they dumped the netburst architecture and gone with the Pentium M? The performance is there. It scales well. I've seen an article where a Pentium M was taken and OCed somewhat. Despite the fact that the CPU socket less then optimal (they needed some translation board), the chip compared very well to the AMD chips.

      --
      meh
  28. HORUS by Anonymous Coward · · Score: 5, Interesting

    These have been availible in Dell servers for a while now according to the online store. Intel are truly screwed for at least the next 6-12 months by the looks of things unless they are hiding something seriously good. I had thought that perhaps they had been based on Apple's decision to switch, it looks like they might just be pretending to be better than they really are though.

    AMD looks like it's going to continue to be the winner on performance for the foreseeable future, especially with it's totally awesome HORUS chipset on the horizon which might just hail the beginning of commodity super computing.

    For anyone wondering what HORUS is, it's an SMP system that can link 4 Opteron's together over HTT. The real killer is that it can it's self be linked to 4 other HORUS chips over InfiniBand. A HORUS SMP system appears as another Opteron chip to the other HORUS groups. AMDs current plans are for HORUS to scale to 32 CPUs in a hot swappable configuration. It's going to be great.

    1. Re:HORUS by Wesley+Felter · · Score: 1

      Commodity supercomputing arrived a few years ago with Beowulf clusters, which happen to be much cheaper than ccNUMA machines. I'm sure SGI and Newisys would be happy to see the HPC world suddenly drop MPI and switch to OpenMP, but I don't think it's going to happen. I see Horus being used for commercial servers (e.g. databases, server consolidation, etc.), not supercomputing.

      BTW, Horus doesn't use Infiniband. Maybe it uses IB cables.

    2. Re:HORUS by Anonymous Coward · · Score: 0

      Wow, imagine a Beowulf cluster of those!

      Holy mixed mythologies Batman!

    3. Re:HORUS by MojoStan · · Score: 1
      Intel are truly screwed for at least the next 6-12 months by the looks of things unless they are hiding something seriously good.

      Intel's not really hiding them, but they do have some pretty good, lesser-known 65nm things coming out in about 3-6 months. These won't beat AMD's Opterons, but I think Intel will be less screwed than you think. Intel will be able to lessen the screwing by beating AMD (by a long time) to a mature 65nm manufacturing capability. Some reviewers (like Tom's Hardware) have already benchmarked some 65nm Pentium Ds and the power savings are significant.

      According to Intel's roadmap, Dempsey (65nm dual-core Xeon) will launch in Q1 2006 at higher clock/bus speeds and lower TDP than the Xeon reviewed in the article (2.8GHz, 667MHz, 135W TDP). At launch, Dempsey will offer a 3.2GHz (1066MHz bus) at 95W TDP.

      Another interesting server CPU due in Q1 2006 is Sossaman, which is a server version of Yonah (dual-core, 2GHz, 31W TDP). Since Yonah is a 32-bit architecture, it's not really comparable to Opteron and Xeon, but it should rule the market for low-power 32-bit servers.

      --
      TO START
      PRESS ANY KEY

      Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...

  29. Re: $700 - correction by Anonymous Coward · · Score: 0

    a $700 PC where it costs you $45 a month in electricity just to run the chip isnt cheap anymore.

  30. Re:Nothing to see, move along. by Anonymous Coward · · Score: 0

    No. Dual core puts two processor cores on the same chip. Each of these cores may have hyperthreading, which essentially splits up the core into a big powerful section for high-power processing and a smaller section for simpler stuff which will just help keep things chugging along while the powerful section is working out a hard SIMD vector multiplication problem or something...

  31. Re:Yet strangly... by $RANDOMLUSER · · Score: 2, Insightful
    > and people prefer the reliability, power savings and lower temperatures of the Intel chips

    WTF??? We're talking about servers, not laptops.

    --
    No folly is more costly than the folly of intolerant idealism. - Winston Churchill
  32. Re: $700 - correction by FidelCatsro · · Score: 1

    The article is dead but there are a few more things to take into account bar base cost .
    The electricity costs , (Can't see how much more hungry it is ) but the Summary says a lot more so i can only assume a difference of 50W which over the course of a year can really add up if it's a server and/or always on.
    how valuable is your processing time ,This is another major issue .Again no benchmarks , but the term " thoroughly thrashed" is not promising.
    All of these things can really add up over a servers life span . Plus many things I have not accounted for.

    A short term saving perhaps , but long term .. well I surmise you may not be saving that much if anything . Perhaps it may even turn out to be more expensive .

    --
    The only things certain in war are Propaganda and Death. You can never be sure which is which though
  33. Re:Yet strangly... by Karzz1 · · Score: 2

    ...and people prefer the reliability, power savings and lower temperatures of the Intel chips.

    I know this is /. and all, but next time you might want to try and RTFA.

    --
    Beware of he who would deny you access to information, for in his heart he dreams himself your master.
  34. Re:Yet strangly... by Glock27 · · Score: 5, Insightful
    OK, troll...I'll bite.

    Intel's sales will again beat AMD's by several fold.

    Perhaps, although AMD has made impressive inroads into the server/enterprise marketplace and there's no sign of it slowing down.

    The reason seems to be that most PC and server purchases are not intended for games, beyond Solitare of course,

    Non sequitur, Opterons smoke Xeons at enterprise tasks like web serving, database hosting and so on, in almost every benchmark. Especially in the more enterprise-relevant 2-way and 4-way (4 or 8 core) configurations.

    and people prefer the reliability, power savings and lower temperatures of the Intel chips.

    RTFA. For several YEARS AMD's chips have been lower power and cooler than Intel's - a combination of doing more work at lower clock frequencies, and SOI. You're recalling something from the K6 days that is totally backwards today.

    AMD should be happy they ran Cyrix out of the business but, they should have realized by now that they will not impact Intel sales no matter how vocal their fanboys might be.

    AMD has already impacted Intel's sales in a big way. Did you hear about Intel's disappointing earnings today? Even worse for Intel, AMD has *creamed* the Itanium. Now 90% of what were potential Itanium customers (big bucks for Intel) are now going to do AMD64 instead...even if it happens to run on Intel silicon. Itanium is a financial and technical disaster for Intel.

    Remember the days when AMD cloned Intel's instruction sets, not vice versa?

    BTW, could I borrow your Opteron, I need to fry an egg for breakfast.

    Wow, how...witty. At any rate, looks like Xeons are the hot ticket there... ;-)

    --
    Galileo: "The Earth revolves around the Sun!"
    Score: -1 100% Flamebait
  35. A good example of marketing management by amcdiarmid · · Score: 1

    Without reading the article, I'm going to make some assumptions. (Like "thrashed" means 10% faster.) In which case, this is a case of market management.

    Intel can release an underpreforming platform in the server area because "it's validated for a server environent." Otherwise, people can purchase a P4 based server from IBM or some such. By not making noise that the unit has been released, people will assume that it has been on the market for a while - and that's why it is slightly less preforming. It's a case of perception more than fact.

    At some point, Intel will have to start preforming. For now, they can get away with promising that they will preform in the near future, and have a competing (not competative) product in the area. AMD may have started taking the consumer chip crown, but the office environment is still aways off.

    $.02

    1. Re:A good example of marketing management by poszi · · Score: 1
      Without reading the article, I'm going to make some assumptions. (Like "thrashed" means 10% faster.)

      Well, I RTFM and it seems the difference is definetely more than 10%. There are some benchmarks like, MPEG to WMV encode where the fasters Opteron is 100% faster than the fastest Xeon. In MP3 encode, Opteron is 50% faster.

      --

      Save the bandwidth. Don't use sigs!

    2. Re:A good example of marketing management by amcdiarmid · · Score: 1

      Open mouth, insert foot. (Stupid slashdot effect. Even the coral cache was down.) Still, a lot of pointy head types won't beleive that this applies to *business* programs.

      mmmmmm, fungus - ahhhhhh

    3. Re:A good example of marketing management by Anonymous Coward · · Score: 2, Insightful

      Actually, you are wrong and you would not even have to read the article to check that. Both the dual-core Intel Xeon and the dual-core AMD Opteron are designed to work in a server environment. These are the chips that you find in the latest blade systems from several vendors (IBM, HP, Sun, Dell, etc.) and they are targetting big businesses, not the average consumer as you imply.

      And the results are actually not good at all for Intel. "trashed" is not about 10% faster, but about a significant gap: 2 or 3 times faster in some tests for comparable chips. For other tests, the difference is smaller but still significant. Note that I am not talking specifically about the GamePC tests reported here, but also about other independant tests made with these new processors and focusing on server performance.

      As I was involved in the decision process for purchasing several rather big blade systems for my company, I had meetings with all the big vendors (IBM, HP, Sun) and several smaller ones. In our meeting with Dell, they had invited a technical expert from Intel who was there to defend their dual-core CPUs and present the roadmap for their future chips. Well, after I asked some technical questions about the memory management and the performance of the Intel Xeons compared to AMD Opterons in dual-core dual-CPU environments, the statement from the Intel guy was memorable: "I think that we are more or less on par with AMD now." Coming from the incumbent and knowing that the vendors always exagerate their claims, this very weak statement was really telling a lot about where Intel stands today in the server market. They are lagging behind and they know it. For the 64-bit area, they bet the ship on Itanium/Itanium2 but AMD blew them away with the Opteron and they still haven't been able to catch up in terms of performance and power consumption. Needless to say, in the end we ditched Dell (even if they had good prices) because the Xeon-based systems did not match our performance requirements. We picked another vendor instead, and went with dual-core Opterons.

    4. Re:A good example of marketing management by Anonymous Coward · · Score: 0

      So ... who did you end out going with?

  36. Intel Dual Core: Worse Perfomance, Better Pricing by adisakp · · Score: 2, Informative

    This is just about Intel Dual Core in general.

    Intel knows AMD Opteron Dual Cores are faster. That's why this generation dual cores (at least P4D's) from Intel are so cheap aside from the ridiculous "Extreme Editions".

    I recently bought a Dell computer. I had a choice of getting a dual core for $50 more. Now I can rip a CD to MP3's using EAC/LAME in about 3 minutes when it used to take 15 on my old computer. I'm happy with my $50 doubling my performance for MP3's and xVID (DivX) creation.

    I really wanted a higher-performance dual core AMD computer but when I was pricing those out, the price of the upgrade to a dual core AMD *ALONE* was around the price of my entire Dell computer.

  37. Re:Nothing to see, move along. by LWATCDR · · Score: 1

    These are server class cpus that where bench-marked not PC class. You are not likely to see them in a "mainstream" PC. Your right Intel is selling a lot of lower end dual core cpus. AMD is selling all the high end chips it can make. If you want the fastest right now you buy AMD. Let's not forget the 64 bit line of single CPUs as well. At this very moment only the Pentium M line is a bright spot for Intel.
    Intel used to own the X86 server market now you are seeing AMD making big strides in the servers. This looks like it will only increase for the time being.
    Intel better get moving. Finally

    --
    See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
  38. I blame the drivers by Anonymous Coward · · Score: 0

    Of Intel, maybe.

  39. Darn by presidentbeef · · Score: 1

    These would have been sweet for my dual Xeon workstation :(

    Anyone know if they are supposed to work with existing motherboards?

    --
    Everything I need to know about copyrights I learned from Slashdot.
    1. Re:Darn by Anonymous Coward · · Score: 0

      Yes, I do know. No, they won't work with existing Intel dual-Xeon boards.

      Posting as AC 'coz I work at Intel.

  40. As an AMD enthusiast... by Spy+der+Mann · · Score: 3, Funny

    allow me to share my excitement.

    (points at intel)
    MWA HA HA! HA HA!
    MWA HA HA! HA HA!

    Ah... felt so good. Thanks :)

  41. Page load speed by poeidon1 · · Score: 1

    Firefox loaded the page in few seconds and I am finished reading the article but internet explorer is still struggling to load the main page. Looks like wintel days will get over sooner than anybody thinks!

    --
    They called me mad, and I called them mad, and damn them, they outvoted me. -Nathaniel Lee
  42. xeon has no chance vs opteron.. by aachrisg · · Score: 3, Interesting

    ..as long as opteron has seperate ram (chips+bus) for each CPU and xeon doesn't. I assume intel knows this.

  43. Re:Yet strangly... by Anonymous Coward · · Score: 0

    And if you can put in a whole rack of new servers and not have to upgrade your airhandler or your UPS, wouldn't that be a good thing?

  44. P/W by Nom+du+Keyboard · · Score: 1
    Intel's new chip gets thoroughly thrashed, losing out in terms of raw performance while eating a lot more power.

    AMD should be touting its own Performance per Watt figures right now, rather than waiting for Intel to eventually catch up.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
    1. Re:P/W by Sebastopol · · Score: 1

      Except AMD would be completely obliterated in the perf/watt benchmark in the vast majority of the market. Just look at Intel's new cores they released.

      AMD knows better. They don't brag where they can't.

      --
      https://www.accountkiller.com/removal-requested
    2. Re:P/W by raitchison · · Score: 1

      AMD should be touting its own Performance per Watt figures right now, rather than waiting for Intel to eventually catch up.

      Maybe, though I wonder if the Pentium M (AKA Pentium 3 but they can't call it that anymore) still holds the title for P/W. The mobile stuff seems to be Intels last technological lead over AMD.

      Intel's problem is that the Pentium 4 architecture isn't very good, they had a really great chip design in the Pentium Pro, then when downhill with the Pentium II, when the Pentium 3 came out it fixed most of the PIIs shortcomings and was a very good chip (which is why it's at the heart of the Pentium M today). The Pentium 4 was a huge leap backwards. I wonder if Intel thought that the world would have switched to Itanium by now and so didn't put resources into fixing the P4s shortcomings like they fixed the PIIs shortcomings. Now they are playing catchup trying to implement what is effectively AMDs 64 bit architecture, I'm guessing they still aren't working on fixing the P4, figuring that the world is going 64 bit (probably true).

    3. Re:P/W by Zemplar · · Score: 1

      AMD is apparently content with having Sun do it for them.

  45. Enough with the politics! by Medievalist · · Score: 1
    losing out in terms of raw performance while eating a lot more power.
    Look, Bill Clinton can't be president anymore, OK? Not even if you run Hillary!
  46. Ecology by Spy+der+Mann · · Score: 0, Redundant

    Do you have any idea how much it costs to have a computer in every house, each one consuming about 300 Watts*hour?

    Only when the world's oil supplies are limited, researchers are struggling to find alternative energy sources (fuel cells, flexible solar cells, etc.). But right now the majority of energy plants burn fuel to generate electricity.

    By making CPUs save power, the chip manufacturers are indirectly fighting against the greenhouse effect.

    1. Re:Ecology by Anonymous Coward · · Score: 0

      Dude, electricity comes from coal, not oil. what does oil have to do with electricity?

    2. Re:Ecology by m0rph3us0 · · Score: 2, Funny

      Does anyone realize that when fossil fuels are burnt to supply electricity it is usually coal and not oil/natural gas?

      Next point, instead of no one being able to use electricity why don't we tell a few hippies to shut up and build a nuke or build a hydroelectric dam.

      Everyone switching to a Pentium M won't do shit to oil consumption. The solution is to tell the hippies to shut up and start building some nukes.

      We don't need to find alternative energy sources, we just need to get rid of the red tape and let the power infrastructure be built. When gas prices go high enough the market will signal that the time is right for the change.

      The irony of global warming is that a few degrees increase in heat would probably dramatically lower the oil consumption in the US. Plus, I live in Canada, to tell you the truth I'd be pretty happy if it was 10 degrees warmer in the winter. The only countries that really need to worry are countries that are starving to death anyways. For Europe and North America warming will be a big boon.

    3. Re:Ecology by ab8ten · · Score: 1

      Or, pretty soon, you could cover your roof with PV cells and get all your power needs that way. Then you get:
      1. No massive capital outlay - it's small scale and responsive to your needs, not the modelled needs from 5-10 years ago when they started designing the nuclear plant
      2. Security (of both types). It's much harder to make a mess with solar cells, plus it's impossible to wipe out an area's power. Massive decentralisation makes the power network secure (sound familiar?)
      3. No problem of storing nuclear waste (which is a problem, and not just for us but for our grandkids)

      --
      I have no .sig
    4. Re:Ecology by Tim+Doran · · Score: 1

      I suppose it makes sense that someone who would hold up "the hippes" as some kind of villain would also hold such a brain-dead view of global warming.

      This is not a Good Thing. I live in Canada too - I'd love to have a warmer climate but it's just not that simple. Do you really think the climate will move up a few degrees on a global scale and just stop? It's a positive feedback loop - global warming is going to accelerate and so will its effects. As for effects, if nothing else, our First World economy could very well come crashing down, especially when you consider the coming decline in worldwide oil consumption too.

      And you may not be bothered by the prospect of a few hundred million or a few billion brown and black people starving to death or dying of thirst but you really should be.

    5. Re:Ecology by civilizedINTENSITY · · Score: 1

      The melting of the polar icecaps is doing wonders for canadian trade routes, too. To say nothing of petroleum reserves that are opening up, "up there".

    6. Re:Ecology by Woody77 · · Score: 1

      That's my plan (getting quote very soon for a big PV array, inverter, batteries, generator).

      Soon we won't be hostage to PG&Es insanely slow response times in the mtns during a storm. 3 days without power makes the baby jesus cry.

  47. Re:Nothing to see, move along. by DanielNS84 · · Score: 1

    I work at best buy and last I checked we have a 3800+ X2 Athlon64 for less than $900 sitting right next to the other HP's. I'm on Geek Squad and all of us make the sales people convince the customers to go AMD because about 1/10 of the Pentium D's overheat out of the box or are dead already. The amount of heat coming out of those things are ridiculous. Also an "Advanced Security" (NAV2K5, Spysweeper, and Critical Updates install) takes far less time on our AMD systems so we prefer to work on them.

  48. Re: $700 - correction by Glock27 · · Score: 4, Interesting
    I'm seeing Intel dual-core processors appearing in ~$700 PCs. From that angle Intel absolutely devastates AMD, as somehow their dual-cores are far less expensive.

    You're talking about Pentium-D of course, not Xeon...

    At any rate, that is actually bad for Intel. AMD brought out enterprise-class dual core CPUs that have obvious applications on workstations/servers, which run lots of tasks and threads, and can always use more horsepower for higher throughput. Intel brought out, at about the same time, the Pentium-D for consumers. Not only is it clocked at about 1 GHz. slower than the fastest single-core Pentium, but desktop PCs don't typically run large thread and process workloads like servers. In fact, the Pentium D runs games substantially slower than cheaper, single-core Pentia. So, I expect a lot of consumers are out there scratching there heads over whether or not to buy Pentium-D.

    AMD's dual core chips, on the other hand, only run 200 MHz. slower than the corresponding single core chip. Game performance suffers hardly at all. AMD will ramp up production of dual-core consumer chips once it feels it has a firm hold on the workstation/server side. Then we'll see the prices drop, and dual core will become mainstream. Maybe game developers will even start programming multithreaded games. ;-)

    In summary, AMD is laughing all the way to the bank, while Intel has to content itself with low consumer product profit margins. It seems this new Xeon won't change that dynamic much.

    --
    Galileo: "The Earth revolves around the Sun!"
    Score: -1 100% Flamebait
  49. signote by crabpeople · · Score: 1


    --
    Submitters: Use Coral Cache!
    Before: website.com/path
    After: website.com.nyud.net:8090/path


    just a note on your sig,
    as you can see the following link
    http://www.gamepc.com.nyud.net:8090/labs/view_cont ent.asp?id=paxville&page=1

    is also slashdotted. why do people think that mirrors can handle the load when the main site cant? you do realize if everyone started linking ALL their stories to coral cache, coral cache would have to bare the load of every slashdot story right? how long do you think they would foot the bill for that. 1 maybe 2 days?

    Its just funny how everyone thinks "USE TEH MIRRARS!!!!!1" is the solution to slashdotting, when really there is no defence.

    --
    I'll just use my special getting high powers one more time...
    1. Re:signote by Yaotzin · · Score: 1

      Well, the best solution would be to disperse the load over a number of different mirrors. That way the mirrors won't crap out since they'd only get what they can handle and the mirrored site as well.

      --
      Error: No error occurred
    2. Re:signote by Spy+der+Mann · · Score: 1

      Alright, i'll have to answer your little-off topic complain.

      The main point for the Coral link is to help the SERVER. If even the coral caches are slashdotted, nothing will happen to the server they got the info from. Which is a win-win situation.

      Your question could as well be rephrased into "why use P2P when i can FTP? It's really slow anyway".

  50. Re:Dual Core Apples by chrish · · Score: 1

    Yeah, c'mon Steve, I want that dual-core OS X/x86 monster! And a pony!

    --
    - chrish
  51. Re: $700 - correction by TheGavster · · Score: 2, Informative

    The reason that Intel's dual core processors can sell for less than AMD's is the same reason they get thrashed; Intel dual cores are simply a normal Intel dual proc setup in one package, while AMD's dual cores have a single die. The Intel offerings use the woefully slow FSB for intercore communication, whilst AMD uses a dedicated, full-speed bus.

    --
    "Because Science" is one step from "Because old book". Try "Because of my experiment testing my falsifiable assertion".
  52. Re:Intel Dual Core: Worse Perfomance, Better Prici by Nom+du+Keyboard · · Score: 1
    I recently bought a Dell computer. I had a choice of getting a dual core for $50 more. Now I can rip a CD to MP3's using EAC/LAME in about 3 minutes when it used to take 15 on my old computer. I'm happy with my $50 doubling my performance for MP3's and xVID (DivX) creation.

    RIAA lists Dell and Intel as major contributors to Internet piracy -- subpoenas to follow...

    I only wish.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  53. AMD and motheboard issues by ChicagoArea · · Score: 0, Offtopic

    I built two AMD computers using the MSI Platinum board, with SLI running two Ge Force 6800 video cards. Now I have been building computers since I was 18, and I am 35 now. I am not sure if it's me, or the MSI motherboard, but the USB2 interfaces only work as USB1. I get an error with all devices that I am plugging in a USB 2 device into a USB 1 spot. When I shut down the PC, it automatically reboots. I have to physically turn off the power supply. And this is with Both PCs. Just last weekend, one of them completely crapped out. I am going to diagnose the issue, but I can't even turn it on. I am so ready to just buy an AMD PC, but Dell doesn't carry them, I guess I can do Falcon or something. I remember the good old days when AMD made their own chipset on motherboards. Now you are stuck with VIA, and I never had much luck with them. I really wish Dell would wake up and start selling AMD PCs. I am ready to retire building PCs and focus on different things in life.

    1. Re:AMD and motheboard issues by Anonymous Coward · · Score: 0

      ummm have you ever heard of nvidia nforce 4 ultra chipset? nvidia now makes the best motherboard chipsets

    2. Re:AMD and motheboard issues by ip_fired · · Score: 1

      Yes, he knows. He's running a SLI board, which is the nForce chip.

      In response to the GP, I've been experiencing quality problems with my MSI board as well, so I switched to a Biostar. I have similar problems with that as well. It could just be the drivers though.

      --
      Don't count your messages before they ACK.
    3. Re:AMD and motheboard issues by bunco · · Score: 1

      Similar MSI setup here.. but no significant problems. Due to problems with nForce chipset drivers (specifically the IDE and NIC drivers), I will be avoiding nForce based boards for awhile.

    4. Re:AMD and motheboard issues by fork420 · · Score: 2, Informative

      I came to the same point a few years ago, then I bought a Mac. Fortunately for you, this was just announced today. They'll even assemble it for you.

    5. Re:AMD and motheboard issues by Anonymous Coward · · Score: 0

      Or you could just get real ASUS SLI setup for $65 refurbished from chiefvalue...

      The asus has no problems for me so far.

    6. Re:AMD and motheboard issues by crabpeople · · Score: 1

      i have dual opteron 244s , alot of drives (about 7) geforce 6800gt etc. I had similar problems with stability. What helped me was adding another 400watt ps to my already installed 600watt. I just wired it up with a toggle switch and let it sit on the outside of the pc. I then use that to power all my drives, leaving the mobo and addon cards to the 600watt.

      I have no stability problems anymore. Since the GP mentioned USB was switching to 1.1, i would say its most DEFINATAELY a power problem, as USB feeds power to devices. Not enough power in, its probably gonna downclock the ports. If i were a usb subsystem thats what i would do.

      just to add, and what made me respond is that i have a MSI k8t master2. works beautifully. 600watts is not enough power for an opteron system with fancy things. gotta go 1+Kw to be absolutely sure.

      --
      I'll just use my special getting high powers one more time...
    7. Re:AMD and motheboard issues by toddestan · · Score: 1

      Let me guess, VIA chipset? I've known many people who have had VIA based AMD systems to have problems with the USB. If you are using some cheapo power supplies, that could be suspect too.

      That is one thing Intel has on its side. When it comes to stability, nothing can touch Intel's chipsets.

  54. Not so fast... by CCW · · Score: 1

    The HP A1250N (X2 3800) is in all the big box retailers at $849 after rebate, and I haven't seeing anything with an Intel dual core with equivalent specs cheaper. If BestBuy, Circuit City, and Frys all carry it I'm thinking that qualifies as "mainstream PC"

  55. Intel - Itanium and r&d resources vs. x86 by acomj · · Score: 3, Interesting

    Its pretty clear that intel is sliding in the x86 race. The reason has to do with development cycles and all the work and money Intel spent on that risky itanium venture. Itanium diverted R&D funds from x86 and when Itanium failed in the market place, intel wasn't working hard enough on x86 and fell behind.

    The next generation of chips may be different. Competetion is good.

      I'm pretty chip agnostic, although a while back I had an cyrix 486 chip in a notebook and didn't even know it wasn't an intel.

  56. Re:Intel Dual Core: Worse Perfomance, Better Prici by Bert64 · · Score: 2, Informative

    Only they're not quite double the performance, because they share the memory bus. Any memory intensive application will hit contention between the 2 cores...
    AMD have a faster memory interface to begin with, and in a multiprocessor system each processor has it`s own connection to memory...
    Although the 2 cores on a single AMD processor share their connection to memory, they dont share with other chips in the same machine and their connection to memory is still faster than intel`s. Also AMD have an internal connection between the 2 cores on a single chip whereas intel`s chips need to go via the processor bus.

    --
    http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  57. Re:Nothing to see, move along. by Jozer99 · · Score: 1

    No it isn't. Dual core means two processors on chip. Hyperthreading is an interesting but not incredibly useful technology intel uses that makes one processor look like two slower processors, for instance, 1 3.0GHz processor turns into 2 1.5 GHz processors. I won't go over how it works. In fact, the new Xeons support both, so when you boot, it looks like you have four processors, two actual ones each pertending to be two more.

  58. Re:Intel Dual Core: Worse Perfomance, Better Prici by rjstanford · · Score: 1

    Likewise - I got a Dell (mainly for the sweet deal on the 24" LCD) and went with the dual core Pentium D, just the 2.8ghz version. Its a remarkably responsive machine, for not a huge amount of money. Powerful, quiet, and cheap. I'd like to have gone AMD, but on the (relatively speaking) low end, Intel's pricing just spanked theirs for dual core.

    --
    You're special forces then? That's great! I just love your olympics!
  59. Re:Well, DUH by Anonymous Coward · · Score: 0

    wow!

    seriously though, I'd rather save $400 and just go for the intel

  60. Re:Nothing to see, move along. by lateralus_1024 · · Score: 1

    HyperThreading is a cheesy Intel hack that lets Windows see two logical processors. For the apps i've run on Windows, there has been absolutely no gain in performance under heavy load. Maybe someone else can share a different experience...

    --
    If you think /. comments are bad, check out Digg.
  61. Please mod parent up. by woginuk · · Score: 0, Offtopic

    +5 Insightful should be good

  62. Re:Yet strangly... by ak3ldama · · Score: 1

    well, although you're pretty much right on, even the 32 bit athlon xp/mp processors were quite warm. my 3200+ and 1900+ both ran about 130 degrees farenheit (with the right fans temps would drop 10-15 degrees), whereas my 3200+ amd 64 runs about 90 degrees with a stock/retail-box fan. if anything, an amd64 is worth buying for the low cost, low temp, low fan noise, high output nature of it.

    --
    "but money is the God of Algiers & Mahomet their prophet." - Rich. O'Bryen June 8th 1786
  63. Counter-Wow by DrYak · · Score: 1
    I find it interesting how, in a world of IP, somebody out there ( Intel ) can still 'cheat' the system by creating dual core CPU's which still count as a single processor, thus allowing for a system like this.


    And I can find it interesting how one can give a meaningful and valid explanation of why the hell should an OS have different license prices based on number of physical processors ? (Specialy when taking in account that the different versions (1/2/4/8/... CPUs) are basically all the same technology only locked to different maxima !)

    OTH, providing different prices & licenses for different support schemes, ranging from Ultra-Cheap for students and developping world You've got what you bought - don't blame us if you have difficulties booting it whith your weird computer license, up-to Maxi premium ultra 'sell your organs on black-market to pay it' Deluxe 24h/7days on-site availability to assist using it on your beowulf cluster, that's something I'ld understand.

    -----

    Note that Microsoft has said that, in part because of the high requirement (dual core almost required) of next-gen bloat^H^H^H^H^H Vista Windows, their reconsidering the way they handle per CPU/license. So Intel isn't actually cheating, just following the trends.

    Note also that I use almost only Linux (despite that fact that i'm not in computer science at all. Did study old languages and then medecine), so maybe there's a perfectly normal and morally acceptable reason for this stuff that I'm unaware of. (I mean other than "ripping more money from the customers").

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
    1. Re:Counter-Wow by Anonymous Coward · · Score: 0
      And I can find it interesting how one can give a meaningful and valid explanation of why the hell should an OS have different license prices based on number of physical processors ?

      Because it allows people with smaller needs to be charged less. You are focused on the physical world, its the same CD, same code, etc (usually controlled by a license file), why charge differently? But heck, how much did that CD cost to make? Why charge more than $5 if you're fixated on the physical?

  64. Mod parent up by TibbonZero · · Score: 1

    This guy isn't trolling, he's putting out a valid point. Apple is releaseing Dual Cores to the public in a way that intel certainly won't. Do you think that ALL intel towers will have dual core xeon chips? Nope. But all full sized apples will. I'd like to see a performance comparison of them.

    --
    Tibbon
    tibbon.com
  65. Xeon, Opteron, Chipsets and the Busses by hirschma · · Score: 1, Interesting

    I'm a huge AMD fan, and almost all of my machines are running either A64's or Opterons. But when it was time to build a file server, I went Xeon.

    Why? No one offers a motherboard like this on the AMD side of things. The Tyan mobo just sprouts high-speed expansion busses, perfect for a box that will have multiple bonded gigE adatpers, multiple RAID controllers, etc. And everything was recognized by Linux the first time - total piece of cake install. This is because Intel makes **excellent** supporting chipsets that have all of their features well supported by Linux.

    AMD boxes need more attention during install for things like gigE controllers and the like - at least that's been my experience. NVidia chipsets are simply not fully supported, and I'm not going to trust backwards-engineered stuff or binary-only releases over Intel-supplied, in-kernel drivers. VIA doesn't make really high-perfomance stuff, either, or at the very least no one is offering it as such.

    Sorry, AMD, but until you continuously offer your own chipsets that offer all the options under Linux (and not rely on erstwhile partners like VIA and NVidia), Intel is going to continue to dominate. Intel makes motherboards and chipsets for a reason.

    jh

    1. Re:Xeon, Opteron, Chipsets and the Busses by jaylee7877 · · Score: 2

      What's wrong with Tyan's Opteron offerings? I've built two systems now with Tyan S2882 boards and found them extremely powerful. The board includes dual gigabit ethernet ports and 1 10/100 port. It does not have PCI-E but it's got plenty of PCI-X slots. If you absolutely need PCI-E, look at the S2892 boards which still have AMD chipsets but also support a NVIDIA controller in order to provide PCI-E. I've had no trouble with the boards under RHEL3 or RHEL4. So what's missing from these boards that the Intel boards have? Jay

    2. Re:Xeon, Opteron, Chipsets and the Busses by diegocgteleline.es · · Score: 1

      Not to mention that other people (serverworks - serverworks announced a chipset for amd but it's still smoke, IBM )

      That's the reason that Intel still dominates at High-end: serious people doesn't puts a nvidia chipset in a 24h/7d server. The ONE decent chipset for opterons is AMD's one, and not everybody uses it. Amd needs to be backed by "serious" motherboard makers. Microstar did it recently. It'll take a while to have competitive offerings for AMD

      For example, you can buy a IBM Xeon server with this Hurricane chipsets, which features weird features like "bus sniffing" which apparentl no other x86 (amd or intel) chipset has and can make Xeons look good against Opterons.

    3. Re:Xeon, Opteron, Chipsets and the Busses by bajan_on_ice · · Score: 1

      Just buy one of these

      http://store.sun.com/CMTemplate/CEServlet?process= SunStore&cmdViewProduct_CP&catid=138713

      4 GiGE ports
      5 PCI-X slots
      Up to 16GB memory
      4 SAS Channels with RAID 0,1

      Fully suppored on Windows, Solaris, RHES, SUSE

      --
      "The greatest dangers to liberty lurk in insidious encroachment by men of zeal, well-meaning but without understanding."
    4. Re:Xeon, Opteron, Chipsets and the Busses by hirschma · · Score: 1

      I'm talking number of *busses*, not slots. The motherboard I mentioned, if memory serves, has FIVE busses:

      * Three PCI-X
      * One PCIe
      * One PCI ...and that means that it is nearly impossible to I/O saturate this machine. There is no equivalent for the Opteron, sadly.

      jh

    5. Re:Xeon, Opteron, Chipsets and the Busses by hirschma · · Score: 1

      Slot bus. If all those slots and gigE ports are sharing one bus, that isn't terribly impressive.

    6. Re:Xeon, Opteron, Chipsets and the Busses by Anonymous Coward · · Score: 0

      some of these are valid, but not for the reason you offered. cpu+chipset+mb from a single company for trouble-free deployments is FUD. How get sucked in for something like that after all the FUDs you must have gone through in IT?

    7. Re:Xeon, Opteron, Chipsets and the Busses by phoenix_rizzen · · Score: 1

      You obviously did not look very hard, as there is a duplicate of that board available with Opteron support. Uses the AMD 8000-series chipset, and is fully supported under Linux and FreeBSD. We've got several Thunder K8S and Thunder K8SR boards here. Dual-Opteron support, dual-core support (in the K8S-D boards), 16 GB RAM, several 32-bit/33 MHz PCI slots, a couple 64-bit/66/100 MHz PCI-X slots, and 1 64-bit/133 MHz PCI-X slot. Onboard PATA and/or SATA or SCSI support. 10/100 and dual-gigE ports.

      Everything your Xeon board has ... but with better non-Windows support and faster throughput in every way. :) And a cheaper price tag to boot.

      The only thing you have to do when shopping for Opteron motherboards is avoid nVidia and ATI chipsets. Stick to AMD and VIA chipsets, and things work wonderfully.

    8. Re:Xeon, Opteron, Chipsets and the Busses by krakrjak · · Score: 1

      What do you mean there is nothing like this on the AMD side. The one you site has two PCI 2.2, one PCIe (8x) and two PCI-X (one 100/66 the other 66 only). This Opteron board on the otherhand has two PCIe (16x each), one PCI 2.3 and two PCI-X (one 100 and the other 133/100). Or if you want four way board you can try this one.

      Unfortunately your argument does not hold water

    9. Re:Xeon, Opteron, Chipsets and the Busses by Bullfish · · Score: 1

      I agree, vis a vis nvidia chipsets at any rate, with the balkiness of their usb controllers being a prime example

    10. Re:Xeon, Opteron, Chipsets and the Busses by hirschma · · Score: 1

      Sorry to single you out, but this reply and most of the other "this is the same/better" seem to have a reading comprehension issue.

      The motherboard that I went with has the following characteristics:

      THREE individual PCI-X busses.
      ONE PCIe bus.
      One PCI bus.
      Bullet-proof, in-kernel support for everything on the board.

      And, well, look - it only costs about 50% less than Opteron boards that have less features. And it has wide availability.

      Nothing AMD-only has these characteristics. Nvidia solutions are poison to me, as they should be for anyone running Linux in a demanding fashion.

      The fact that you cannot read a block diagram and see that your suggestion is short two busses means that you get to ride on the short bus, along with the rest of the fanboy responses.

      AMD fanboys, you can't use your beloved CPU everywhere, sorry. I really wanted to go AMD myself, but Intel wins sometimes.

      jh

    11. Re:Xeon, Opteron, Chipsets and the Busses by geekoid · · Score: 1

      The fact that the poster didn't catch that makes me hope he isn't getting paid to install/build/ maintain servers..

      --
      The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
    12. Re:Xeon, Opteron, Chipsets and the Busses by Anonymous Coward · · Score: 0
    13. Re:Xeon, Opteron, Chipsets and the Busses by Anonymous Coward · · Score: 0

      Note that you have four buses in the Opteron offering linked downstream; 1 PCI-E, 2 PCI-X, 1 PCI. Delta between 3 major buses and 4 is not that significant.

    14. Re:Xeon, Opteron, Chipsets and the Busses by Mr+Z · · Score: 1

      Uhm, "bus sniffing," aka "bus snooping" is pretty much required on any multiprocessor setup to keep the caches coherent. Either that, or you have software-managed cache coherency across the multiple CPUs, which isn't the norm in x86-land.

    15. Re:Xeon, Opteron, Chipsets and the Busses by diegocgteleline.es · · Score: 1

      no this is not a standard x86 chipset

      http://www.techworld.com/opsys/features/index.cfm? FeatureID=1204

      "We managed the cache to increase performance by introducing what we call XL4 server accelerator cache -- the L4 cache in our 445. Now we've removed the need for it because the chipset helps the processor to run faster. It actually reduces latency -- the L3 cache gets in the way of four-way processing.

      At design time, there was a maniacal focus on latency reduction. When you can cut the time it takes it gets from one point to the next you can increase performance, so chipset latency has been cut by two and half times -- down from 265 nanoseconds to 108 nanoseconds.

      The way we do that is through snoop bus filtering. It looks across to the other bus -- because the system uses two buses, two per CPU -- and the snoop filter does intelligent caching. It can see what's in the other cache without having to send traffic across the FSB to find out. Other chipsets cannot do that and need the L3. And if you don't need L3 cache you shouldn't have to pay the premium to buy it.

      We've done nothing different than others could do, we've just been smarter. It's a technique that's been in other IBM server products for a long time -- its taking mainframe-inspired technology and bringing it down to an industry standard server."

    16. Re:Xeon, Opteron, Chipsets and the Busses by Mr+Z · · Score: 1

      The key word here is filtering. You see, the cache controllers on each CPU have to snoop the bus in order to keep the view of memory coherent and consistent among all the CPUs. The snoop protocol is a broadcast protocol, and as such it does not scale well to large numbers of CPUs unless it's implemented carefully. It sounds as though this chipset tracks what each CPU holds, so that it can short-circuit many of the snoops. Thus, it can provide a negative response to a snoop much earlier than it would if it actually queried all the attached CPUs.

      In the typical case, most data shared among CPUs is read-only, and the rest of the working set is private. Only a handful of data (locks mainly) get shared and ping-pong among the caches. So, it's easy to see the benefit. I just wanted to point out in my original post that bus snooping wasn't the innovation. Bus snooping is what holds back performance in a multi-CPU environment.

      On this point, it'll be interesting how the next generation of dual-core CPUs perform once they start merging the L2 controllers. Current dual-core CPUs have two separate L2s on the die. Intel, at least, has stated their next round will merge the L2s into a single, combined L2. This eliminates on-die L2-to-L2 snoop traffic at a minimum and depending on implementation should eliminate most L1 snoops as well. (Presumably the L2 controller tracks the L1 contents, so it has ample opportunity to filter the core-to-core snoops.)

      I'm not sure what AMD is doing in this space. AMD's recent caches have all had an exclusive policy (meaning, a given line could be in L1D, L1I or L2, but never replicated within the 3) but that could cause real problems for shared read-only pages, whether they are code or data, if the two CPUs merge their L2s into a single, large L2. For it to work cleanly, they almost need to shrink their L2s, keep them separate and sprout a large, merged, non-exclusive L3. Either that, or come up with a semi-exclusive protocol that allows replication between the two CPUs L1s, and a mostly-exclusive L2.

      --Joe

  66. Re:Yet strangly... by greg_barton · · Score: 2, Funny

    BTW, could I borrow your Opteron, I need to fry an egg for breakfast.

    The 90's called. They need their processor bigotry back.

  67. Re:Intel - Itanium and r&d resources vs. x86 by LaughingCoder · · Score: 1

    Amazingly, Intel seems to have forgotten what got them dominance. It's all about the binaries. People will buy new processors if they run their old binaries faster. Period. They won't buy based on the promise of running some new, as yet non-existent, binariese faster in the future. AMD understood this when they came up with the Athlon64 architecture. Not only did it extend the instruction set to add 64-bit instructions, but it also sped up 32-bit applications. Intel completely dropped the ball with the Itanium debacle. It looks to me, from this latest announcement, that they still don't know where the ball is.

    Funny, the same can be said for Microsoft, only they still get it. New OS's must be binary compatible with old OS's. If they aren't, people stay away in droves (phrase credit: Yogi Berra), This is the main weakness, in my opinion, of the whole FOSS movement. Most people don't want to "simply recompile".

    It's the binaries, stupid!

    --
    The more you regulate a company, the worse its products become.
  68. Re:Intel Dual Core: Worse Perfomance, Better Prici by CCW · · Score: 1

    Care to provide more details? A retail HP A1250N is $849 after rebate, the cheapest Dell I can configure with equivalent memory and disk with a much slower 820D processor is at least $200 more. Dell does have some nice 24" LCD deals, but you can get those without buying a computer.

    In my experience support from both Dell and HP is equally bad for their home buyers, so not much to sway the decision there.

  69. Hyper Threading by DrYak · · Score: 3, Informative

    Additionnally to what other have said, I may add :
    - HyperThreading is Intel's name for Simultaneous Multithreading.

    Basically, a CPU isn't always using 100% of all its function.
    The CPU may be waiting for something in the cache.
    Or the application is maybe using only a small portion of the CPU.
    In other words, the CPU waste its time sitting and doing nothing.

    If you manage to use those unused ressource, you can squeeze more performance out of your CPU.
    Before Simultaneous Multithreading, the only way to do so is "Out-of-Order" execution.
    - In plain english : maybe some of the next steps of the programm don't need to wait the curent stuff to finish, and we may already fill unused parts of the CPU with these instruction.

    With Simultaneous Multithreading, this time, you're trying to find something for your CPU to do from *another program*. This program must wait for something from the cache ? Let's run another in the meantime.

    ----

    Alternate explanation :
    Multi tasking/ Multi Multithreading is when several program share the same CPU by quickly alternating between them.
    Simultaneous Multithreading is when 2 program run at the same time so less parts of the CPU are just sitting unused.

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
    1. Re:Hyper Threading by rooksmith · · Score: 1

      There was a similar article in the June issue of MaximumPC - (which is like Dr. Dobbs for Gamers - over simplified, but still it did a benchmark, which you gotta admire). The article basically says that until applications are specifically written for dual-core they wont have the sort of speed up that the designers intended. The Intel Pentium D is like a Duplex House. Moving a box from a closet in house 1 to house 2 involves walking out the front door (bus interfaces) of one onto the sidewalk (the front side bus), walking next door and through the ront door of howse 2 (bus interface for the second core). The AMD Athalon 64 X2 has a has a cross-bar interface that acts like a shared front porch which connects the cpu cored via an on die memory controller. Its better, but not perfect. What they expect will happen over time is someone will come up with a way to communicate directly across the cores, analogous to a shared doorway between the bedrooms. In the dual processor world they think that the AMD Opteron beats the Intel Xeon because it has a shared Chipset and dedicated transport links between each cpu and ram. Bottom line: Intel is getting spanked by AMD... And they deserve it.

  70. Just specced out an AMD system for MHD modeling by Dr.+Zowie · · Score: 4, Informative

    Running a Xeon dual-core is like mounting a Chevy big-block engine under a VW carburetor. The memory access just isn't there. Most of my stuff (modeling the solar corona) is RAM-bound anyway, so there's no win to be had at all by running the dual Intel cores. The Opterons have better RAM latency, which is a win -- but, more importantly, the two cores communicate cache-to-cache at the CPU clock speed, so dual-threaded processes run amazingly fast. If they're sharing memory, you effectively double the L2 cache size of both cores, which is a big win all around.

    So, er, Xeon is teh 5uk and Opteron Pwns.

  71. Re:Intel Dual Core: Worse Perfomance, Better Prici by Red+Flayer · · Score: 1

    "I really wanted a higher-performance dual core AMD computer but when I was pricing those out, the price of the upgrade to a dual core AMD *ALONE* was around the price of my entire Dell computer."

    That's not because of AMD's pricing, that's because of Dell's pricing. Dell's standard configuration templates are based on Intel chips, so subbing in another brand takes it out of the regular production line.

    Try HP for cheaper AMD dual-core processors. I'm sure there are other MFGRs out there, but if you're buying from Dell, then HP should be a good alternative for you.

    --
    "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
  72. Re:Intel - Itanium and r&d resources vs. x86 by DeathPenguin · · Score: 1

    I don't think this is the case. Intel is a behemoth with enough money to fund hundreds of major projects concurrently. They can throw hundreds of man years on a project on a whim. This is not a resource limited start-up we're talking about.

    Now for the tin foil hat part: Their x86 products fell behind not because of lack of R&D funding, but because some idiot(s) up in management decided that they'd rather have everyone migrate to IA64 by buying a new PC rather than migrating to a backwards-compatible EM64T architecture.

  73. Re:Yet strangly... by Locke2005 · · Score: 1

    Intel's sales will again beat AMD's by several fold. Apparently you haven't read AMD beats Intel in September US retail desktop sales What were you saying again? By what math is 46% of the market considered beating 52% of the market "by several fold"???

    --
    I've abandoned my search for truth; now I'm just looking for some useful delusions.
  74. Re:Well, DUH by the+eric+conspiracy · · Score: 1

    save $400 and just go for the intel

    So Intel is selling a dual core Xeon for $75? That's a deal I must agree. You will have to tell me where you can buy one for that price.

  75. In all seriousness... by PCM2 · · Score: 1

    Somebody recently told me ... it may have been Sun or AMD, or an industry analyst, I forget who ... that some of the customers clamoring the loudest for high-performance, low-power systems are on Wall Street. Aside from the heat concerns mentioned elsewhere (and remember, more heat means more air conditioning which means still more power -- AC is always a line-item on any datacenter budget), a lot of customers run into the problem of there simply not being enough power infrastructure to go around. If you're running a datacenter with a whole bunch of systems in the middle of downtown Manhattan, you can't just pull in a few thousand more watts on a whim.

    --
    Breakfast served all day!
  76. Re:Yet strangly... by Anonymous Coward · · Score: 0

    Or replace existing servers and save a ton of money on cooling costs.

    On the topic, Intel is focusing on their power scaling tech for their next generation of cpu's.

  77. Somehow... by Short+Circuit · · Score: 1

    ...I doubt DNF is ever going to come out. If only because Jack Thompson would describe it as, "The game--long-awaited in the gaming community--where police are mutated into hogs and shot."

  78. Dell Xeon Precision vs. Quad PowerMacs by Anonymous Coward · · Score: 0

    My applications require certified or factory built hardware, for support purposes. A Dell dual Xeon Precision workstation was $1500 more than a dual PowerPC PowerMac so I opted for the Apple.

    The new PowerMacs are supposed to sport dual dual-core PowerPC processors and be priced the same as the current dual 2.7 Power chipped machines. Sweet.

  79. Purchase question by Crapshoot · · Score: 0, Offtopic

    I don't really have the time to build my own system or what not, so I was going to pick up a Dell 9100 with the following processor: Pentium® D Processor 820 with Dual Core Technology (2.80GHz, 800FSB) My impression is that for day to day stuff and some gaming (Civ 4, Football Manager- the latter is fairly CPU intensive) that this would be a better bet than say a P4 630 w/HT Technology (3.0GHz,800FSB). Am I off base in this belief ? I admit to knowing nothing about dual-cores, so I'm wondering if its worth paying the 100 bucks or so extra for the former as opposed to the latter

    1. Re:Purchase question by SumDog · · Score: 1

      For a single threaded application, if you have either two 1Ghz processors (or one dual core 1Ghz), your single application will run at the same speed as it does on a uniprocessor 1Ghz. Now if you run two or more applications, the operating system can place them on different processors, but your top speed for either process will be that 1Ghz.

      Some applications (Nero and Quake 3 for example..I think Doom3 too but I'm not too sure) are designed to take advantage of multi-processors and distribute their load between them. You'll get an advantage there.

      Also, the dual core processors may also have different low level designs (cache, data-paths, pipelines, control logic, etc.) that would make them faster.

      Mhz/Ghz speed is a poor rating of performance. There is so much more including the size of the pipeline, number of stages, CPI, # of instructions, branch prediction, etc. etc.

      I've used SMP processors for a while, starting back with dual 300Mhz and now with Dual AthlonMP 1900+. They help a lot with development. As far as games and regular applications go, I couldn't honestly say for sure, but if you placed them side by side I bet you would see a significant difference with the dual core machine.

  80. [OT] your sig by Anonymous Coward · · Score: 0

    It's "too", not "to", as in "This takes too much time."

  81. Re:Yet strangly... by goMac2500 · · Score: 1

    Read your own article. That's retail market. Like you know... It's only counting stores you walk into. It's not counting companies like sayyyyyyyyyyy Dell?

  82. Re:Yet strangly... by Anonymous Coward · · Score: 0

    Yes.. The K7 series ran "hot" in the end of each core model, and the Althon64/Opteron (K8) was a redesign with new technology (die shrink, SOI from IBM).

    Anticipating the latest shrink and move to dual core was sheer genious on the part of AMD. They designed their interconnets, sockets, and power envelopes to support the larger Opteron cores, and the benefits from the shrink allowed them to "drop" dual core onto the existing platforms (very nice).

    What you are seeing from Intel is the end of the road for the P4/Xeon design (evidenced by High heat and cheap tricks like their larger caches, new instructions, and slapping together dual cores at the last minute).

    I'd never count Intel out, but they're definately falling behind in this battle. AMD's only problems are lack of production capacity, and intel "lock-in" of certain teir 1 vendors (it will be interesting to see how the lawsuit goes).

  83. 2 Words by zpeterz63 · · Score: 0

    Beowulf Cluster, my friend. Just imagine a Beowulf Cluster of these. This is a TRUE geek's system.
    Again, a very independantly wealthy geek, that is.

  84. Re:Nothing to see, move along. by QuesarVII · · Score: 1

    Hyperthreading allows 1 thread to use the integer operations and another thread to use the floating point operations simultaneously. The integer and floating point execution areas are separate and can be used independently. Hyperthreading allows 2 paths into the cpu to allow them to be used simultaneously. A properly written program can benefit greatly from hyperthreading. In some application testing I've done in the hpc market, some codes have run ~30% faster with hyperthreading turned on since the physical cpu can be better utilized.

    However.. we still sell >90% opterons, with a growing number of dual core opterons. All the xeon dual core stuff I've seen is garbage and totally wasteful. Their next line of dual core stuff should be better though (from what we've been told).

  85. Also works in windows by Phil+John · · Score: 1

    simply set your power management to "Minimal" for a desktop and it uses C'N'Q, or at least id does on my Athlon64 d'top.

    I've also got an AMD Turion 64 based laptop and for that, the good ol' laptop setting also makes it kick in.

    --
    I am NaN
  86. Re:Yet strangly... by hackstraw · · Score: 1

    gp: and people prefer the reliability, power savings and lower temperatures of the Intel chips

    WTF??? We're talking about servers, not laptop


    When you have one room that is cooled by 20 tons of AC for 10 racks of computers, power and heat dissipation start getting important. It burns your wallet at both ends, the power end and the cooling end. It is really that big of a deal.

  87. Have a look at Tyan K8WE (S2895). by Anonymous Coward · · Score: 0

    The Tyan K8WE is the best board for Opteron I've seen so far.
    2x PCIe
    2x PCI-X 100
    1x PCI-X 133
    1x PCI
    2x Gigabit Ethernet (not on any of the above buses)
    Up to 16 GB memory
    SATA-RAID
    2x U320 SCSI
    Firewire
    USB 2.0
    Audio

    That's pretty much all I want from a fast workstation or server system (well, actually I don't need Audio for that ...)
    Linux support is a tricky issue. It worked for me, but yeah, support could be better. I hope nvidia will listen some day.

    1. Re:Have a look at Tyan K8WE (S2895). by hirschma · · Score: 1

      This actually has more potential throughput than the Intel solution I mentioned, but is totally polluted by the Nvidia stuff. Might as well disable the on-board gigE under Linux and buy a dual port card instead - thus negating any advantage.

      bzzt.

  88. Re:Yet strangly... by un1xl0ser · · Score: 1

    Let me guess, your not in IT. :-)

    Environmentals are VERY important for reasons that are kind of obvious.

    1) It costs money to cool servers.
    2) It costs money to power servers.
    3) Saving money is good.
    4) Intel Xeon chips don't have better environentals than AMD Opterons.

    If you have a computer A that performs better than computer B, and it costs less to power, and it costs more to cool.. It is kind of a no-brainer.

    You essentially throw electricity down the toilet by having anything that isn't as efficient as possible.

    --
    v4sw6PU$hw6ln6pr4F$ck 4/6$ma3+6u7LNS$w2m4l7U$i2e4+7en6a2X h
  89. my dual core dell by Heembo · · Score: 1

    I just picked up a new Dell 9100 2.8 ghz dual-core machine - its not at zippy as I expected in day-2-day operations, but the power of this beast really shines in a "multi-task" enviornment. I trying taking it though its paces when I first set it up, simultaneously installing several pieces of software, backing up the machine, while playing a high end 3-D game, while playing music. Brilliant! And it boots up remarkably fast as well.

    --
    Horns are really just a broken halo.
  90. Something really fishy about this by Anonymous Coward · · Score: 1, Insightful

    Many of the benchmarks show the Opterons being nearly twice the speed.

    When I see such a wide margin when dealing with multiple processors I begin to wonder if the benchmark is using all the CPU's. It just seems like the Xeons weren't using all the cores or something in some of the tests.

    I don't know why that could happen but there is just too wide a margin in many of those tests. Something seems not right. I mean, I know the Opterons are generally faster, but I have never seen them be that much faster.

    1. Re:Something really fishy about this by Anonymous Coward · · Score: 0

      3 things

      1. AMD Opteron processor scale much better than the Intel Xeon processor; the results for 4 core vs 4 core will be farther apart than 2 vs 2 core.

      2. You're used to seeing Dual opteron 252 2.6 Ghz vs Xeon 3.6 Ghz. Intel's dual core chip speeds are reduced dramatically compared go AMD's chips.

      3. It may be that Hyperthreading doesn't help but hinder; 8 threads and little bandwidth is not a good mix

    2. Re:Something really fishy about this by Anonymous Coward · · Score: 0

      ya think? try running your own benchmarks then.

      start with a real os (bsd, linux, beos or os-x86) & run some low level stuff (c or asm, none of those poofda java, php or perl tests)

      most folks with a clue that roll their own will tell you it's even worse than the article implies - AMD is the ONLY way to go these days

      (specially when you consider a sempron 64 on a board can be had for less than $100)

  91. Re: $700 - correction by Anonymous Coward · · Score: 0

    You forgot one thing: the AMDs are much more expensive, the premium to pay for the dual core Opterons over the single core ones is quite a lot higher than for the intel dual cores. You're correct in saying that Intel is targeting the consumer/low end business market with their dual core CPUs, but it's not just in terms of performance, it's more so in terms of price, and I really think that for now, intel is selling orders of magnitude more of dual core CPUs than AMD does.

  92. Re:Intel Dual Core: Worse Perfomance, Better Prici by adisakp · · Score: 1

    That's not because of AMD's pricing, that's because of Dell's pricing. Dell's standard configuration templates are based on Intel chips, so subbing in another brand takes it out of the regular production line.

    Um... no. Dell ONLY ships Intel. So I was comparing Dell with dual core Intel Chips vs others with other brands. You can get DellSB - Dimension 9100 Desktop with 2.8Ghz P4 820 Dual Core, 512MB DDR2 SDRAM, 80GB S-ATA, 48x CD-Rom, 128MB ATI Radeon X300 SE for $679 after Rebate including 19" LCD Monitor. Check out http://www.gotapex.com/ for details.

    A quick check on www.mwave.com shows the cheapest AMD X2 to be nearly $350 and that's the recently released 3800+ X2. When I bought my computer, the cheapest one was the 4200+ X2 which is just shy of $500 range. That's for the BARE CPU. With the DELL, you get the whole computer and a 19" LCD.

  93. Re:Intel Dual Core: Worse Perfomance, Better Prici by adisakp · · Score: 1

    Only they're not quite double the performance, because they share the memory bus. Any memory intensive application will hit contention between the 2 cores...

    I realize that not all applications are 2X faster. For example, non-multithreaded apps see a benefit only when you're multitasking.

    However, I *ONLY* mentioned 2X performance for MP3 and xVID / DivX. These are two extremely CPU intesive applications with much lower memory bandwidth (CPU is bottleneck, not RAM) and are two REAL-WORLD cases where the performance for dual-cores (even on Intel) is VERY close to 2X the speed of a single core.

  94. Re:Intel Dual Core: Worse Perfomance, Better Prici by adisakp · · Score: 1

    Check out www.gotapex.com to see how to configure a Dell dual core for $679 with a 19" LCD. Intel dual core pricing has gotten so ridiculously low at Dell if you know the right deals that it's beginning to compete with their Celeron offerings.

  95. Intel used to be better by dtjohnson · · Score: 1

    Intel used to have the class products and AMD was the inexpensive copy. Now, AMD is selling the classy stuff and Intel sells the cheap, junky stuff. I am amazed at how poorly the Intel dual-core performs compared with the AMD. Even if Intel couldn't replicate the lower power consumption of the AMD product, it seems like they should have been able to at least come a little closer to the performance. It is just embarrassing to see how far Intel has fallen.

  96. Intel is crushing AMD in one thing... by dtjohnson · · Score: 1

    Intel's marketing must be awesome if they can get knowledgable IT pros to buy the dual-core Xeons instead of the dual-core Opterons. I'm thinking the Intel marketing guys could sell sunshine to Hawaiians.

  97. Re:Yet strangly... by $RANDOMLUSER · · Score: 1
    I guess I didn't state it properly. I am in IT, and I recognize the value of Watts & BTUs in a machine room. I was disputing the OPs notion that Intel (server) CPUs use less power and emit less heat than AMD (server) CPUs. In my experience, AMD servers supply better bang per BTU per kWh.

    You're sure about your point 3, are you? ;-)

    --
    No folly is more costly than the folly of intolerant idealism. - Winston Churchill
  98. Re:Dual Core Apples by toddestan · · Score: 1

    speaking of dual core any apple users we have live updates of the apple event in one hour. Dual Dual-Core Powermacs expected.

    And be sure to get them while they are good - that is, before Apple switches over to the power hungry, poor performing Intel dual core chips.

    Or better yet, just get an AMD system.

  99. Re: $700 - correction by Lord+Kano · · Score: 1

    "I'm seeing Intel dual-core processors appearing in

    $746 isn't that bad. Shipping included.

    LK

    --
    "Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
  100. This isn't the real Intel Dual Core Xeon... by Glasswire · · Score: 1

    ...watch for the "Dempsey" in Q1 and the "Woodcrest" low power, high thoughput in Q2.
    The Paxville DC is a stopgap.

  101. Stupid slashdotters? by Anonymous Coward · · Score: 0

    400W while idling?

    Did you notice that the 2.8GHz quad core system, which GamePC claims to consume 393W while idle, only consumes an extra 35 watts when the system is under "full load"? That means the difference in power consumption for each 2.8GHz Pentium 4 core between idle and full load is apparently less than 10 watts, even if you assume that no other component in the system (memory, chipset, video card, hard disks, etc) consumes any more power when the system is fully loaded. This could be true for the video card and hard disks in their test, but highly unlikely for the memory and chipset.

    Am I the only person to have spotted this, despite there being >300 replies already? I sure hope not.

  102. Re: $700 - correction by Fujisawa+Sensei · · Score: 1

    This is really wierd. Intel targeting the Cheap Market and AMD going after the server market. Just remember what AMD's rep was before the beat Intel to the GHz mark.

    --
    If someone is passing you on the right, you are an asshole for driving in the wrong lane.
  103. Re:Yet strangly... by un1xl0ser · · Score: 1

    I personally don't subscribe to point 3, but some people down the hall are big on it.

    The OP had to be teh troll. :-)

    I'm actually the guy who wants all of our workstations to run CentOS/Fedora Core with a yum server instead of shelling out the bucks for RHEL... so yeah. I don't like paying too much for things.

    --
    v4sw6PU$hw6ln6pr4F$ck 4/6$ma3+6u7LNS$w2m4l7U$i2e4+7en6a2X h
  104. Re: Faster by Mr+Z · · Score: 1

    "You keep saying that word. I don't think it means what you think it means."

    How is it Intel has the slower chip and has been slacking if they have been focusing on "faster"? I think you mean "clock speed." As in, "Intel has been focusing on having the highest clock speed, regardless of whether it gives them the faster chip."

  105. VIA and bignum by ^BR · · Score: 1

    They added a Montgomery multiplier on their chip recently. Useful to implement fast RSA.

  106. Re: $700 - correction by Glock27 · · Score: 1
    You forgot one thing: the AMDs are much more expensive, the premium to pay for the dual core Opterons over the single core ones is quite a lot higher than for the intel dual cores. You're correct in saying that Intel is targeting the consumer/low end business market with their dual core CPUs, but it's not just in terms of performance, it's more so in terms of price, and I really think that for now, intel is selling orders of magnitude more of dual core CPUs than AMD does.

    You're looking at it the wrong way. The only question you need to ask is "Is AMD selling all the dual core CPUs it produces?". If the answer is yes, then AMD is making a lot more money PER CHIP than Intel is. Why would AMD want to sell their chips at a lower price? Supply vs. demand, eh?

    Once Fab 36 kicks in, AMD dual cores will drop in price a whole lot. Intel will be hurting even more. Count on it.

    --
    Galileo: "The Earth revolves around the Sun!"
    Score: -1 100% Flamebait
  107. Re: Faster by mahdi13 · · Score: 1

    The grammer nazi strikes again! my bad
    funny that everyone else seamed to 'get it' though...

    You might want to fix your sig, links to parked domains are no fun to view ;-)

    --
    "Some things have to be believed to be seen." - Ralph Hodgson
  108. Re:P/W - Pentium II Shortcomings by Nom+du+Keyboard · · Score: 1
    they had a really great chip design in the Pentium Pro, then when downhill with the Pentium II, when the Pentium 3 came out it fixed most of the PIIs shortcomings

    Just what are the Pentium II shortcomings? IIRC Pentium Pro was a very expensive and difficult chip to manufacture even given that they'd broken it up into two separate dies. In addition they never could get the clock rate up over 200MHz with it, and could not (or it wasn't worth it) include new SSE instructions into it.

    P-II bundled 512KB of half-speed L2 cache into the cartridge that worked pretty well. So well that early P-IIIs with half that amount of full-speed cache on the die itself were outperformed in some areas (e.g. SETI screensaver) by the P-II due to the L2 cache limitations.

    So what parts of the P-II were particularly bad? I wonder, because I'm still running 3 of them.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  109. Re:P/W - Pentium II Shortcomings by raitchison · · Score: 1

    I remember running tests and findiing that 233Mhz and 266Mhz PIIs were noticably slower than a 200Mhz Pentium Pro, the 300Mhz PII's were about the same speed as a 200Mhz Pentium Pro and it wasn't until the PII was at 350Mhz that it was noticably fatser.

    The PII was a design change just to make it so AMD (& Cyrix at the time) had to start reverse engineering all over again. The same thing with the fancy new slot packaging that was such a success. They also wanted to ramp up the clock speed without paying the premium to have full speed cache memory like the Pentium Pro.

  110. Re:P/W - Pentium II Shortcomings by Nom+du+Keyboard · · Score: 1
    I remember running tests and findiing that 233Mhz and 266Mhz PIIs were noticably slower than a 200Mhz Pentium Pro

    That's not unexpected since the P-Pro L2 cache ran at full core speed, while the P-II cache was running at half processor speed. This meant that it took a P-II twice as long to get data from the L2 cache as the P-Pro. P-Pro remained an excellent server chip for long after P-II was running at much higher clock rates.

    But the P-Pro's problem remained that it was both very expensive to produce, and they never could get the clock speed up over 200MHz, perhaps in part because of the distance between the processor die and the L2 cache die. The inability to increase speed along with the high price I believe doomed it from the very beginning.

    As for the P-II 350MHz being noticably faster, it darn well should have been. That was the step, from the P-II 333MHz where they increased the memory bus speed from 33MHz to 66MHz. Literally double the main memory bus bandwidth and of course you are going to see some significant speed increases. In fact, this is the last time Intel actually doubled memory bus speed, since DDR isn't twice as fast in the entire memory transaction as SDRAM.

    But thanks for the answer otherwise.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  111. Pedantics. by Mr+Z · · Score: 1

    Technically, I was being a semantics Nazi as opposed to a grammar Nazi above. :-)

    As for my sig, thanks for the tip. I guess Art of Espresso let their domain registration lapse. That's too bad. It's a nice little coffee shop. I'll have to think up a new sig. Thanks.

    --Joe