Slashdot Mirror


Intel Unveils 6-Core Xeon 7400

JagsLive recommends CNet coverage that begins "Intel officially unveiled its six-core 'Dunnington' Xeon 7400 processor Monday ... As expected, Intel launched the Dunnington chip for high-end servers ... The Xeon 7400 is also one of the first Intel chips to have a monolithic design. In other words, all six cores will be on one piece of silicon. To date, for any processor having more than two cores, Intel has put two separate pieces of silicon ... inside one chip package."

235 comments

  1. Monolithic? by HungSoLow · · Score: 0

    Intel, quit living in the stone age monolithic and get with modern times! I mean 6 cores? How about 8!

    1. Re:Monolithic? by Anonymous Coward · · Score: 0

      I think they were aiming for 1, 4, or 9 cores, but ended up with 6 thanks to the yields.

    2. Re:Monolithic? by renegadesx · · Score: 1

      I heard from someone from Dell that Intel had plans for 8 by the end of the year and 12 by June 09.
      And we are in mid-September and only deliver 6? I guess thats what I deserve for trusting Dell rep's

      --
      Make SELinux enforcing again!
    3. Re:Monolithic? by Anonymous Coward · · Score: 0

      Why do you suppose it would be limited to only three dimensions?

    4. Re:Monolithic? by Cygfrydd · · Score: 3, Funny

      My god... it’s full of stars...

    5. Re:Monolithic? by GooberToo · · Score: 1, Funny

      Thankfully the core Python developers have been telling us that continued hardware development of adding more cores is simply not happening. Furthermore, this evolution of continued development is simply wrong, bad, and is silly. To make matters worse, we are all delusional and no one is running more than one core and anyone leveraging more than one core is using their computer poorly and inefficiently.

      Thankfully, here very soon, we'll all reason that Intel, AMD, ATI, and NVIDIA are all doing the wrong thing and making use of additional cores (and especially SMP) is always the worst way of increasing concurrency.

      In all seriousness, hopefully these guys will realize they are dreaming and actually bother to increase scalability with sane, proper, scalable, and programmer friendly methods for doing so.

  2. And we're now tuesday by Yvan256 · · Score: 4, Informative

    I'm betting new Mac Pros will be launched today.

    1. Re:And we're now tuesday by sgbett · · Score: 5, Interesting

      http://www.apple.com/uk/imac/

      Hmm, the page you're looking for can't be found.

      interesting.

      --
      Invaders must die
    2. Re:And we're now tuesday by Anonymous Coward · · Score: 1, Informative

      Dunnington is the wrong socket for the current Mac Pros. They would have to rearchitect everything to put a processor designed for 4-way systems into a 2-way box. Apple are almost certainly waiting for the DP versions of Nehalem to come out and jump for that.

    3. Re:And we're now tuesday by Yvan256 · · Score: 1

      Weird indeed (iMac page is there for the Canadian website, and the UK Mac mini is also present).

      Somebody's gonna get in trouble real soon now(TM).

    4. Re:And we're now tuesday by tyler.lee · · Score: 1

      I would think this is just coincidence. The Mac Pros would get the first introduction. Anyone know anything about power consumption/heat, as compared to the quad?

    5. Re:And we're now tuesday by Trashman · · Score: 5, Informative

      The article from Ars technica says:

      "Unlike the 65nm, quad-core Tukwila, Dunnington is produced on Intel's 45nm process. This means that Dunnington uses less power, and indeed, the top-end, 2.66GHz SKU has a 130W TDP (compare Tukwila's 170W TDP). The 2.4GHz part boasts a 90W TDP, and there's a 2.13GHz part that runs at a relatively cool 65W."

      --
      Do not read this .sig
  3. Base 2 by daveime · · Score: 3, Interesting

    Is it just me, or does 6 seem like a counter intuitive number of cores ?

    2,4,8,16 ... we've been using binary since the start, now we have to start in trinary ?

    1. Re:Base 2 by Anonymous Coward · · Score: 5, Funny

      6 = 8 - 2 broken cores ?

    2. Re:Base 2 by houghi · · Score: 2, Informative

      There is no need for a base two if you are adding. You add cores, you do not multiply them.

      2, 3 (yes, triple code do exist), 4, 6. I guess the next step will be 8 and perhaps even skip that and make it 9 (3x3).

      --
      Don't fight for your country, if your country does not fight for you.
    3. Re:Base 2 by morgan_greywolf · · Score: 0

      It doesn't actually matter if it's base 2. All that matters for SMP is that it is an even number of cores.

    4. Re:Base 2 by zeridon · · Score: 2, Informative

      see amd ... they have 3 cores in one chip and the shit fares prety well

      --
      In fire we trust http://www.getoto.net
    5. Re:Base 2 by davidbrit2 · · Score: 5, Funny

      Hey, 6 is a power of 2. It's 2^2.585, to be inexact.

    6. Re:Base 2 by Anonymous+Conrad · · Score: 3, Informative

      Is it just me, or does 6 seem like a counter intuitive number of cores ?

      Remember they need to put other stuff on the silicon too. The XBox 360's CPU uses three quarters of the die for three processors and puts the shared cache etc. in the fourth quarter. Six + support circuitry probably fits a square die better than eight + support.

    7. Re:Base 2 by tgd · · Score: 4, Informative

      No, it just matters that you have more than one.

    8. Re:Base 2 by Anonymous Coward · · Score: 5, Funny

      2^(log2(6)) to be exact.

    9. Re:Base 2 by morgan_greywolf · · Score: 1

      Come to think of it, you're right. ;)

    10. Re:Base 2 by oldhack · · Score: 1

      Is it just me, or does 6 seem like a counter intuitive number of cores ?

      Yeah, especially with the new motherboard that fits three of these together...

      --
      Fuck systemd. Fuck Redhat. Fuck Soylent, too. Wait, scratch the last one.
    11. Re:Base 2 by blind+biker · · Score: 2, Informative

      Sun had 8-core server CPUs since several years now. They didn't have any problems allocating the die's surface.

      --
      "The agriculture ministry is not in charge of Gundam" - Japanese ministry official.
    12. Re:Base 2 by Yvan256 · · Score: 5, Funny

      Pentium 1 user, aren't you?

    13. Re:Base 2 by Yvan256 · · Score: 1

      Well, if it can run on souls it means it will also lower my electricity bill.

    14. Re:Base 2 by Macrat · · Score: 3, Informative

      Of course their die surface is 8 times bigger too.

    15. Re:Base 2 by telchine · · Score: 1

      3 (yes, triple code do exist)

      The only three core processors I know of are effectively defective quad core processors.

      The 4th core is defective so, rather than disposing of them, they are sold as tri-core processors.

      Whilst there's no requirement for base two, there is usually a requirement for an even number of cores in SMP (symmetric multi processing)

    16. Re:Base 2 by Anonymous Coward · · Score: 0

      I thought the 3-core AMD chips were low bin FOUR core processors with one turned off?

    17. Re:Base 2 by Anonymous Coward · · Score: 1, Informative

      > there is usually a requirement for an even number
      > of cores in SMP (symmetric multi processing)

      Why?

      You have tasks [A, B, ... I], and you run task A on first core, task B on 2nd, ... task I on ninth. What kind of black magic could possibly hold me back from scheduling nine tasks to run on nine cores? CPU scheduling is CPU scheduling, isn't it? The last time I've checked, you can build a Linux kernel with support for anywhere from 1 to 255 CPUs. Or should I insert "assert((num_cpus%2)==0)" everywhere in my hypothetical homebrew hobby OS?

      I think the "symmetric" in SMP means more like "parallel".

    18. Re:Base 2 by adrianwn · · Score: 2, Informative

      The "symmetric" in SMP refers to all CPUs being identical, not to the actual number of processors.

    19. Re:Base 2 by dumael · · Score: 2, Informative

      Symmetric multi-processing refers either the generally the type of cpus, i.e. all processors have the same capabilities, or to their relationship with memory. SMP is generally shared memory systems with a set of uniform processors.
      http://en.wikipedia.org/wiki/Symmetric_multiprocessing

    20. Re:Base 2 by Meumeu · · Score: 1

      Pentium 1 user, aren't you?

      Don't know anything about exp and log, do you?

    21. Re:Base 2 by telchine · · Score: 1

      The "symmetric" in SMP refers to all CPUs being identical, not to the actual number of processors.

      I stand corrected. Thanks

    22. Re:Base 2 by arktemplar · · Score: 1

      Niagra as those are called, aren't very good at individual core performance. There was a study by Berkley some time back that did rate them above the others in terms of scaling. However, this is mostly with respect to memory bandwidth, in my opinion with Intels move from FSB to their as yet unreleased QuickPath Interconnect, which if I understood is closer to the AMD hyper transport. This may be challenged.

      FYI the benchmarks were against clovertowns and opterons, and the cell performed best.

      --
      blog plug -> The Darker Side of Light
    23. Re:Base 2 by Ngarrang · · Score: 1

      see amd ... they have 3 cores in one chip and the shit fares prety well

      AMD once said there was a greater efficiency in interconnecting 3 cores, compared to 4.

      --
      Bearded Dragon
    24. Re:Base 2 by Anonymous Coward · · Score: 0

      Perhaps our esteemed colleague was thinking of bi-lateral symmetric multi processing (BLSMP).

      Me, I prefer my Phenom 8650 triple-core as the geometrically superior basis for a stable system.

    25. Re:Base 2 by mr_mischief · · Score: 3, Informative

      That has nothing to do with symmetric multiprocessing. SMP means that all the chips can make memory accesses to all the memory at the same speed. It is the opposite of Non-Uniform Memory Access, or NUMA, in which certain processors (some or all of them) take longer to talk to certain parts of main memory than others or systems in which processors have a faster path to some private off-chip memory in addition to the main shared memory.

    26. Re:Base 2 by Narishma · · Score: 1

      The Xbox 360 has a 3 core CPU.

      --
      Mada mada dane.
    27. Re:Base 2 by confused+one · · Score: 1

      we've been using binary since the start, now we have to start in trinary ?

      You need to be more flexible. I seem to recall from my Number Theory class that the base you choose can be somewhat arbitrary. In fact, I've heard that a lot of people use a Base 10 system!

      The AMD Phenom comes in a 3 core variety (which may or may not be a "broken" 4 core chip). The Xbox 360 has a 3 core processor. The cell processor used in the Sony Playstation 3 and IBM blade servers is a 9 core (granted only 1 is a full core). There's no good reason for limiting yourself to powers of 2...

    28. Re:Base 2 by mr_mischief · · Score: 1

      They are, but they still work pretty well. They're careful to turn off the core that doesn't work rather than one that does. They could dedicate themselves to only shipping processors with all four cores working, but that would make the quad-core chips much more expensive. This way, they can sell three working cores for part of the four-core price and save lots of cash on wasting chips that work fine as three-core parts.

    29. Re:Base 2 by Anonymous Coward · · Score: 0

      That has nothing to do with symmetric multiprocessing. SMP means that all the chips can make memory accesses to all the memory at the same speed.

      I wouldn't say "nothing". I've never heard of an SMP system that wasn't also a symmetric multiprocessor. I know it's possible, so someone has probably don't it, but I doubt it's done very often.

    30. Re:Base 2 by jacquesm · · Score: 1

      Sperry Univac actually had a machine with 9 bit bytes... those were the days ! Just think about what you could do with that extra bit...

    31. Re:Base 2 by Anonymous Coward · · Score: 0

      or...

      2^(log(6)/log(2))

      for those of us with calculators without a log2 button.

      You insensitive clod!

    32. Re:Base 2 by Cyberax · · Score: 1

      No, they are designed to be 3-core. That way you only need 3 interconnects to connect each core with all other cores.

      You need 6 interconnects to do the same for 4-core CPU.

    33. Re:Base 2 by dubbreak · · Score: 3, Interesting

      AMD once said there was a greater efficiency in interconnecting 3 cores, compared to 4.

      Anyone with simple graph theory can see that. 3 nodes only need 3 edges(or interconnects in this case) so that they are only one hop away from each other. With 4 nodes you need 6 edges for a complete graph / clique (each node is adjacent). Now whether that is applicable to the amd chip is a whole other question. I don't have the time (nor do I care to) look up the implementation of the chips.

      --
      "If you are going through hell, keep going." - Winston Churchill
    34. Re:Base 2 by hedwards · · Score: 1

      You need to be more flexible. I seem to recall from my Number Theory class that the base you choose can be somewhat arbitrary. In fact, I've heard that a lot of people use a Base 10 system!

      That would be correct, the main issue with some bases like binary is that they're difficult for humans to read and take up a huge amount of space on paper. There isn't any inherent reason why we could be using hexadecimal or larger base.

    35. Re:Base 2 by Spatial · · Score: 1

      Faring pretty well my arse. I still don't have a worthwhile upgrade to my X2 6000 and it's almost two years old. Right now all the AMD CPUs available are downgrades or trade-offs. I want an upgrade. Even the priciest, most powerful Phenom they have to offer is slower than the X2 6000 in every application except ones which fully utilise three or more cores. (almost none)

    36. Re:Base 2 by Anonymous Coward · · Score: 0

      Ah, like the Commodore 64?

    37. Re:Base 2 by Just+Some+Guy · · Score: 1

      I had an Amiga with a 68060 at 50MHz and a PowerPC 604e at 200MHz. They ran in parallel, with the PPC often used for CPU-intensive parts of programs.

      --
      Dewey, what part of this looks like authorities should be involved?
    38. Re:Base 2 by BOFHelsinki · · Score: 1

      Bingo, young man! Exactly like 6 is a power of three. After reading dear GP's comment about "why trinary?" I've been trying large values of 3^1 and small values of 3^2, but still not quite comphrehending the comment...

    39. Re:Base 2 by Kjella · · Score: 1

      Good point but to the wrong part of the bolded statement, the symmetric part refers to all processors/cores being identical and not to memory access. You could in principle have asymmetric (specialized) cores both in a MP and NUMA setup. It doesn't matter how many you have though, it's whether each core acts the same or not that matters.

      --
      Live today, because you never know what tomorrow brings
    40. Re:Base 2 by HoldenCaulfield · · Score: 1

      If we were using base 3, we'd have 3, 9, 27 (as these are the corresponding values for 10, 100, and 1000 - which would be 2, 4, and 8 in binary). Note that 3 in trinary would be 20 (which wouldn't exist in binary)

      Maybe we're switching to base 6 ;)

    41. Re:Base 2 by flyingfsck · · Score: 1

      Oh man, I wanted to try my slide rule, but I think its battery is flat.

      --
      Excuse me, but please get off my Pennisetum Clandestinum, eh!
  4. Yes! It should totally be a power of two. by Joce640k · · Score: 5, Funny

    I think they're really making 8-core chips but their factories are primitive so normally only about six of them work.

    These chips are all defective. I wouldn't buy one and neither should you.

    --
    No sig today...
    1. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 1

      I think they're really making 8-core chips but their factories are primitive so normally only about six of them work.

      These chips are all defective. I wouldn't buy one and neither should you.

      At least the cores won't be trapped behind a hypervisor like another cool, yet restricted cpu.

      IIRC, Isn't that also what big blue did to increase the yield on the Cell? I agree, it's pretty dirty to sell what is essentially partially damaged hardware as something new.

    2. Re:Yes! It should totally be a power of two. by larry+bagina · · Score: 0

      The PS3's cell chip is 8 core with 1 turned off (or defective) to increase yield. If they have to turn off 2 cores, that's not very reassuring.

      --
      Do you even lift?

      These aren't the 'roids you're looking for.

    3. Re:Yes! It should totally be a power of two. by ShadowRangerRIT · · Score: 2, Funny

      Why are you responding to speculation/a joke as if it were fact? This is a native six core chip, not an eight core with two disabled.

      --
      $_ = "wftedskaebjgdpjgidbsmnjgcdwatb"; tr/a-z/oh, turtleneck Phrase Jar!/; print
    4. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 0

      That's the funniest thing about those jokes. When some twit shows up and becomes the punchline without even knowing it.

    5. Re:Yes! It should totally be a power of two. by larry+bagina · · Score: 3, Funny

      Why are you responding to a fact as if it's speculation or a joke?

      --
      Do you even lift?

      These aren't the 'roids you're looking for.

    6. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 0

      When they get 8 working cores it will be released as the DX model, this will be rebadged the SX model.

    7. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 0

      Actually its likely that two cores we disabled because of faults. Thats how AMD ended up selling 3-core chips...

    8. Re:Yes! It should totally be a power of two. by jacquesm · · Score: 1

      you'd hope that out of 8 fpu's they'd get at least one to work ?

    9. Re:Yes! It should totally be a power of two. by Gilmoure · · Score: 4, Funny

      I steal my computers from really rich orphans. 'Course, if they have parents, it takes just a little work and they're soon orphans.

      --
      I drank what? -- Socrates
    10. Re:Yes! It should totally be a power of two. by rugatero · · Score: 4, Funny

      Why the hell am I responding at all?

      --
      This comment is for entertainment purposes only. Any similarity to real insight or information is purely coincidental.
    11. Re:Yes! It should totally be a power of two. by daedae · · Score: 3, Interesting

      The AMD point is true (useless side note: I actually just got a machine with a Phenom tri-core a few weeks ago), but if you look at the die photo you can see that there's nowhere for a pair of disabled cores. It's possible that they're just making native 6-core dies until they get the manufacturing process stable enough to make 8s though. /me is okay with the fact he's probably just feeding trolls

    12. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 0

      You are it!

    13. Re:Yes! It should totally be a power of two. by cc_pirate · · Score: 1

      Did you actually RTA?

      From the die image on the foils it is clear there are 6 cores BY DESIGN. There aren't any of them that are defective.

      Next time RTA.

      --

      "There are laws that enslave men, and laws that set them free. " - Sean Connery as King Arthur

    14. Re:Yes! It should totally be a power of two. by Anonymous Coward · · Score: 0

      Seems to me that it would be a good idea to have 9 cores then, they should be able to get 7 of them working.
      I am sure a chip called '7 of 9' wiukd sell well especially if they could get Jeri Ryan to advertise it.

    15. Re:Yes! It should totally be a power of two. by adisakp · · Score: 1

      I think they're really making 8-core chips but their factories are primitive so normally only about six of them work.

      You're confusing them with IBM and Sony.

      On May 17, 2005, Sony Computer Entertainment confirmed some specifications of the Cell processor that would be shipping in the forthcoming PlayStation 3 console.[17][18][19] This Cell configuration will have one Power processing element (PPE) on the core, with eight physical SPEs in silicon.[19] In the PlayStation 3, one SPE is locked-out during the test process, a practice which helps to improve manufacturing yields, and another one is reserved for the OS, leaving 6 free SPEs to be used by games' code.[20]

    16. Re:Yes! It should totally be a power of two. by kayditty · · Score: 0

      Six isn't a power of two? Maybe you meant perfect power.

      log2 (6) = 2.5849624

    17. Re:Yes! It should totally be a power of two. by toddestan · · Score: 1

      If that's the case, I wonder if some of the new quad core chips might be this six core chip with two of the cores disabled? It seems like it would be a way for them to recover some of their costs when 1 or 2 of the cores don't work, since I imagine this is an expensive piece of silicon.

    18. Re:Yes! It should totally be a power of two. by Michael+Hunt · · Score: 1

      You can all but bet that once two things have happened:

        - Existing inventory of Q9x00 and Q6x00 parts is all but depleted
      and
        - Dunnington's desktop-equivalent part has debuted

      that this will indeed be the case. I mean, the yields on such a die would be absolutely shiteful, especially since this is the first monolithic design that intel have fabbed with more than two physical cores on it. If you can disable 2 cores and sell it as a Q9990 XXXXTREME edition, why wouldn't you?

      To my mind, the interesting question will be whether we (a-la AMD) see 5-core dunnington-alikes show up. It'll come down to whether intel figure that the extra effort involved in isolating and binning two different sorts of quasi-defective parts (versus doing it once) would be rewarded by having a 5-core part on the market (which would, natch, sell for more than the equivalent, but differently binned, 4 core part.)

  5. Specs? by sanosuke001 · · Score: 4, Insightful

    There wasn't much in terms of technical specs in TFA. 6 cores, 16MB cache, anything else? Clock speed? 16MB of L2? L3? FSB? DDR(n)? (Though this is probably more up to the MB manufacturer) Why are they moving the memory controller off silicon? That in itself seems like a step backwards.

    I would like to see them pushing consumer multi-core computing more personally. Get MS and other application manufacturers to support more cores. Servers have been doing it for ages and with pretty much all consumer level chips being dual core they should be pushing this angle more.

    Though, them incorporating all of the cores on a single piece of silicon is definitely a step forward; the lack of additional specs and the notion of moving the memory controller make this seem like not as big of an announcement...

    --
    -SaNo
    1. Re:Specs? by morgan_greywolf · · Score: 5, Insightful

      I would like to see them pushing consumer multi-core computing more personally. Get MS and other application manufacturers to support more cores. Servers have been doing it for ages and with pretty much all consumer level chips being dual core they should be pushing this angle more.

      And before anyone says...."yeah, but Linux/Mac OS X supports multi-cores out of the box".... Yes, yes it does. However, most of the applications don't actually benefit much from SMP by themselves. A few things like video conversion, but, for the most part, office suites, e-mail user agents, etc., do not actually benefit directly from SMP.

      OTOH, why should they? Any processor made within the last five years is good enough for that stuff.

    2. Re:Specs? by Anonymous Coward · · Score: 0

      Intel don't have memory controller onboard yet. So they're not moving it anywhere in comparison to their existing processors.
      It's an incremental update to their existing 4-way platform while they wait to get their shiny new architecture ready for that space.

    3. Re:Specs? by RiotingPacifist · · Score: 2, Funny

      OFC if your dealing with server, then it does make a difference for example Unisys 96 core offering (*nix & possible mac only) would be able to hold 256 SQL server databases ... or vista pro

      --
      IranAir Flight 655 never forget!
    4. Re:Specs? by Anonymous Coward · · Score: 0

      click on the product link on this page
      http://www.intel.com/products/processor/xeon7000/index.htm?iid=servproc+body_xeon7400badge

    5. Re:Specs? by Macrat · · Score: 1

      Wow, if you need your e-mail and office suite to be processor aware, maybe you should stop using Windows.

    6. Re:Specs? by morgan_greywolf · · Score: 1

      Right. Except you can't run SQL Server on a Unisys (or Sun -- yes, Sun makes such servers, too) 96 core box directly, since, as you state, they only run Unix. Oracle, Postgres, MySQL, DB2, etc., yeah, SQL Server, no. (Unless you're running under virtualization....)

      But we're not talking about on the server. My comment and my comments' parent were discussing consumer multi-core setups. Most consumers aren't exactly running 256 SQL databases on their 96-CPU E20K.

    7. Re:Specs? by Anonymous Coward · · Score: 0

      6 cores
      1066 fsb
      16mb cache
      2.4ghz and 2.66 for the extreme model

    8. Re:Specs? by Veetox · · Score: 1

      I would like to see them pushing consumer multi-core computing more...

      I disagree. Consumers don't need more cores; they need more balls. Once SSD usage becomes more proliferative in the server sector, the bottleneck to computing looks to exist primarily in information delivery, i.e. internet/cable. The average consumer spends most of his/her time on the internet now. And more users need to get up and start demanding better/faster connectivity for their money.

      morgan_greywolf, up there, attacks the other issue: programs need to make better use of multiple cores AND (I'll add) 64-bit technology.

    9. Re:Specs? by mr_mischief · · Score: 1

      Notice "SQL server" with a small "s". Just because Microsoft goes and trademarks a common phrase doesn't mean that servers which run SQL queries aren't SQL database servers.

    10. Re:Specs? by mr_mischief · · Score: 1

      You can, on most operating systems, actually run more than one application at a time now.

    11. Re:Specs? by Anonymous Coward · · Score: 0

      Bump up the SQL to 512 and Vista down to Home Edition and you'd be closer to correct.

    12. Re:Specs? by jacquesm · · Score: 1

      I thought that mysql innodb supported multi-core cpus ?

    13. Re:Specs? by morgan_greywolf · · Score: 1

      Notice I said 'directly' benefit.

    14. Re:Specs? by morgan_greywolf · · Score: 1

      Yes, it does, and, yes, I specifically mentioned it (though not specifically innodb).

    15. Re:Specs? by sanosuke001 · · Score: 1

      I very much agree with 64-bit support. However, I don't see SSD as a viable alternative yet. Yes, the performance is a step up but the finite life of flash memory makes me not want to get one just yet. When the lifetime of a drive is comparable to platters then it will be ready for mainstream. Though, it is a great idea for OS/App drives with a conventional HDD for storage. If the OS/Apps crap out you can always reinstall.

      --
      -SaNo
    16. Re:Specs? by sanosuke001 · · Score: 1

      But the Nahalem core is moving it on-silicon. Why would they start working on a new chip that moves it off again? Yes, it'll definitely save them money. But, for a server, does the nominal cost really matter that much? They're already using enough silicon for 6 cores, whats a bit more for the memory controller?

      --
      -SaNo
    17. Re:Specs? by daniel_gustafsson · · Score: 2, Informative

      "Why would they start working on a new chip that moves it off again?" Please! They are not moving it off again! Please understand! This is an upgrade to their exististing Xeon MP server design and these chips can fit into _existing_ servers. There will be new Xeon MP chips based on Nehalem ready late next year. Xeon MP chips takes much more time to validate that desktop chips.

    18. Re:Specs? by Anonymous Coward · · Score: 0

      yeh, well learn to multitask then. who'd'a thought?

    19. Re:Specs? by billcopc · · Score: 2, Informative

      There wasn't much in terms of technical specs in TFA. 6 cores, 16MB cache, anything else? Clock speed? 16MB of L2? L3? FSB? DDR(n)? (Though this is probably more up to the MB manufacturer) Why are they moving the memory controller off silicon? That in itself seems like a step backwards.

      Pentiums have never had an on-die MMU in the first place, they're actually doing that for the upcoming Nehalem. AMD has used an on-die MMU since the Athlon 64, and while it certainly helps squeeze more efficiency out of the system, the faster clocked bus on Intel rigs often made up for the theoretical performance gap.

      The Clock speed was omitted from the article, but the Xeon 7400 is clocked at 2.6ghz. That's actually pretty decent for a Xeon, they don't go as high as the mainstream processors because they're made to be installed in a puny rack chassis with piss-poor airflow.

      --
      -Billco, Fnarg.com
    20. Re:Specs? by ChrisA90278 · · Score: 1

      "but, for the most part, office suites, e-mail user agents, etc., do not actually benefit directly from SMP."

      I think you've got that slightly wrong. Office SUITES do use multicores while word processors and spread sheets don't. With today's software multi cores don't do much for you unless you are multitasking.

      If you are just running a word processor or a browser you don't need much computer power

    21. Re:Specs? by Anonymous Coward · · Score: 0

      OTOH, why should they? Any processor made within the last five years is good enough for that stuff.

      We are not designing a single-core processor from the last five years to run a word processor. Consumers are going to use multi-core processors to run systems. You can do more with your computer like e-mail, instant messaging, word processing, encrypted p2p, music, and then some.

    22. Re:Specs? by BOFHelsinki · · Score: 1

      Why are they moving the memory controller off silicon? That in itself seems like a step backwards.

      Obviously it's better to run it on air than on silicon.

    23. Re:Specs? by Anonymous Coward · · Score: 0

      I find all the OS's Win/Linux/Mac retarded when it comes to mulit processing. Not the program level but the OS should give new processes a new Processor ... what a concept instead of a new damn thread on the same Processor. Keep track of wtf is going in the system if one Processor is encoding leave it the fuck alone and use another one if some new program that gets open. But I guess thats too much to expect from a computer.

    24. Re:Specs? by default+luser · · Score: 1

      There wasn't much in terms of technical specs in TFA. 6 cores, 16MB cache, anything else? Clock speed? 16MB of L2? L3? FSB? DDR(n)? (Though this is probably more up to the MB manufacturer) Why are they moving the memory controller off silicon? That in itself seems like a step backwards.

      I think you are confused. This core is NOT based off of the new Intel Core i7 architecture, it is based off of the existing Intel Penryn Core2. This means that it does not have an L3 cache or integrated memory controller. Please note from the linked page: all the i7 processors to be introduced next month are 4-core.

      So, specs:
      16MB dynamically shared L2 cache
      Memory: whatever the manufacturers feel like, although it will probably be FBDIMM DDR2.
      FSB: as high as they can make it. This processor has SIX hungry cores to feed. Id's say 1333 minimum.

      --

      Man is the animal that laughs.
      And occasionally whores for Karma.

    25. Re:Specs? by default+luser · · Score: 1

      Pentiums have never had an on-die MMU in the first place, they're actually doing that for the upcoming Nehalem. AMD has used an on-die MMU since the Athlon 64.

      You are confusing the memory management unit (MMU) with the memory controller.

      Intel's first chip with a built-in MMU was the 286, and every AMD-designed x86 chip has one too. Just thought you might like to know.

      --

      Man is the animal that laughs.
      And occasionally whores for Karma.

    26. Re:Specs? by Anonymous Coward · · Score: 0

      "However, most of the applications don't actually benefit much from SMP by themselves. A few things like video conversion, but, for the most part, office suites, e-mail user agents, etc., do not actually benefit directly from SMP." - by morgan_greywolf (835522) on Tuesday September 16, @08:25AM (#25023701) Homepage

      That depends largely on the user & if he is a multitasker too, as well as an application being programmed for multiple core/SMP!

      That's done either via EXPLICIT multicore coding (where you have to do the processor detections yourself) & then sending the subsequent child threads of execution other than the parent thread, off to other cores/cpus you detected!

      That's done explicitly via API calls (in Win32 for this example) like SetThreadAffinity...

      OR

      Just by using multithreaded design in your code, & letting the OS kernel level subsystem of the Process Scheduler account for thread-to-CPU/core scheduling for executions!

      (Effectively too, & that's NOT simple + not a lot lends itself to it, especially for "fine grained multithreading designs" (where the multiple threads of execution stay on the SAME set of data (can be a recipe for disaster @ times if done wrong, race conditions result etc.))

      The EASIEST method for that?

      Just don't have your multiple threads 'touch the exact same data' & work on the exact same dataset concurrently!

      (This is called "coarse multithreaded design" as of late)

      It's simpler to design for, plus, the chances to use it are fairly common for a multitasking user...

      E.G. #1-> In the case of say, an Office Suite, you have a user that does a spellcheck on 1 thread in a spreadsheet or document, & then also reformats it in yet another thread, + prints it in say yet another (not the greatest examples, but point's there))

      E.G. #2-> In gaming, put the animation loop on 1 thread, networking code on another thread, sound code on yet another thread, etc. et al (better example imo)

      It's doable, practical, & yes... VERY possible, & not as hard as one would think (and, does lend itself to apps you mention also, & depending on if the user is a "multitasking user"? Folks CAN see gains, depending on if they are accustomed to doing more than 1 thing @ a time to say, a spreadsheet or document etc. et al, even in Office Suites)

      APK

      P.S.=> Then, of course, there is the gains realized by the OS itself using multiple cores to send off threads of its OWN execution (as well as entire child processes also) off to least used/saturated cores/cpus present also... freeing up the "main cpu" (or other less saturated to nearing or hitting 100% usage), for other processes/appplications also... & the kernel level subsystem (in Windows @ least) of the Process Scheduler assures this happens as needed also (& modern OS' of the Linux/*NIX variety can do this also, not just Windows, & they get better ALL THE TIME @ it, + will continue to do so, as this becomes "more & more the norm")... apk

  6. I want one.... by Anonymous Coward · · Score: 0, Funny

    I would love to get a new mobo and one of these chips and install it in my Mac.....oh wait, nevermind.

  7. It has six cores... by halcyon1234 · · Score: 5, Funny

    ... and a moisturizer strip for a cool, refreshing finish.

    1. Re:It has six cores... by shams42 · · Score: 3, Funny

      Did Intel partner with Gillette on this CPU? http://www.theonion.com/content/node/33930

    2. Re:It has six cores... by hansamurai · · Score: 1, Funny

      Would someone tell me how this happened? We were the fucking vanguard of processors in this country. The Core 2 Duo was the processor to own. Then the other guy came out with a three-core processor. Were we scared? Hell, no. Because we hit back with a little thing called the Quad Core. That's four processors and an aloe heatsink. For cooling. But you know what happened next? Shut up, I'm telling you what happenedâ"the bastards went to five cores. Now we're standing around with our cocks in our hands, selling four cores and a heatsink. Cooling or no, suddenly we're the chumps. Well, fuck it. We're going to six cores.

      Sure, we could go to five cores next, like the competition. That seems like the logical thing to do. After all, four worked out pretty well, and five is the next number after four. So let's play it safe. Let's make a thicker aloe heatsink and call it the QuadCoreSuperHeatsinkTurbo. Why innovate when we can follow? Oh, I know why: Because we're a business, that's why!

      You think it's crazy? It is crazy. But I don't give a shit. From now on, we're the ones who have the edge in the multi-core game. Are they the best a man can get? Fuck, no. Intel is the best a man can get.

      What part of this don't you understand? If two cores is good, and three cores is better, obviously six cores would make us the best fucking processor that ever existed. Comprende? We didn't claw our way to the top of the processor game by clinging to the two-core industry standard. We got here by taking chances. Well, five core is the biggest chance of all.

      Here's the report from Engineering. Someone put it in the bathroom: I want to wipe my ass with it. They don't tell me what to inventâ"I tell them. And I'm telling them to stick two more cores in there. I don't care how. Make the cores so thin they're invisible. Put some on the handle. I don't care if they have to cram the sixth core in perpendicular to the other five, just do it!

      You're taking the "safety" part of "safety processor" too literally, grandma. Cut the strings and soar. Let's hit it. Let's roll. This is our chance to make processor history. Let's dream big. All you have to do is say that six cores can happen, and it will happen. If you aren't on board, then fuck you. And if you're on the board, then fuck you and your father. Hey, if I'm the only one who'll take risks, I'm sure as hell happy to hog all the glory when the six-core processor becomes the shaving tool for the U.S. of "this is how we compute now" A.

      People said we couldn't go to four. It'll cost a fortune to manufacture, they said. Well, we did it. Now some egghead in a lab is screaming "Six's crazy?" Well, perhaps he'd be more comfortable in the labs at IBM, working on fucking PowerPCs. RISC architecture, my white ass!

      Maybe I'm wrong. Maybe we should just ride in AMD's wake and make pens. Ha! Not on your fucking life! The day I shadow a penny-ante outfit like AMD is the day I leave the processor game for good, and that won't happen until the day I die!

      The market? Listen, we make the market. All we have to do is put her out there with a little jingle. It's as easy as, "Hey, computing with anything less than six cores is like folding your proteins by hand." Or "You'll be so fast, you'll be finding Mersenne primes like a guy on speed." Try "You'll have so many cores, there won't be enough space radio signals for you to pretend to find aliens out of."

      I know what you're thinking now: What'll people say? Mew mew mew. Oh, no, what will people say?! Grow the fuck up. When you're on top, people talk. That's the price you pay for being on top. Which Intel is, always has been, and forever shall be, Amen, six cores, sweet Jesus in heaven.

      Stop. I just had a stroke of genius. Are you ready? Open your mouth, baby birds, cause Mama's about to drop you one sweet, fat nightcrawler. Here she comes: Put another aloe heatsink on that fucker, too. That's right. Six cores, two heatsinks, and make the second one lather. You heard meâ"the second heatsink lathers. It's a whole new way to think about processing. Don't question it. Don't say a word. Just key the music, and call the chorus girls, because we're on the edgeâ"the Moore's edgeâ"and I feel like dancing.

    3. Re:It has six cores... by arotenbe · · Score: 1

      Don't you have something better to do with your life than post redundant copies of Onion stories with cheap find-and-replace jobs run on them?

      Oh, wait... this is Slashdot. Never mind.

      --
      Tomato wedge sperm darts that are Republican.
    4. Re:It has six cores... by andrikos · · Score: 1

      If you aren't on motherboard,

    5. Re:It has six cores... by mr_mischief · · Score: 1

      Besides this being a not very funny copypasta, AMD is as American as Intel and the Core 2 model lines come from designs done in Israel.

    6. Re:It has six cores... by hansamurai · · Score: 1

      Don't you have something better to do with your life than post redundant copies of Onion stories with cheap find-and-replace jobs run on them?

      I'm at work, so figure it out.

  8. Wattage by locster · · Score: 5, Interesting

    I think server builders these days are less interested in the number of cores per CPU and more interested in improvements in the performance/wattage ratio.

    1. Re:Wattage by gEvil+(beta) · · Score: 1

      Watt you say?

      --
      This guy's the limit!
    2. Re:Wattage by Kjella · · Score: 1

      That depends entirely where those servers are. Many places rack space comes at a huge premium and anything packing more punch into less space is valuable. Of course, if you're talking about your local server room where you could just put in another rack if you needed to it's not that big a deal.

      --
      Live today, because you never know what tomorrow brings
    3. Re:Wattage by Yvan256 · · Score: 1

      Qu'est-ce qu'il dit?

    4. Re:Wattage by Anonymous Coward · · Score: 0

      Somebody set up us the FDIV!

    5. Re:Wattage by Anonymous Coward · · Score: 0

      That's a powerful question!

    6. Re:Wattage by afidel · · Score: 2, Informative

      Any decent host is also going to kill you for bringing more power to your rack so there is definitely a balancing point. The fact is that the datacenter is designed for a certain power density and going beyond that really screws things up. Airflow and cooling densities, percentage of space allocated to UPS and generators, etc. But, looking at the Intel press release, these suckers pack 6 cores into a 65W power envelope, quite impressive. This compares quite favorably with the 45W for the best current generation quad cores, so total system power per computation should improve quite a bit. Now if only we could get Intel to get away from using power hungry FB-DIMMS.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    7. Re:Wattage by andrikos · · Score: 1

      Divide and conquer?

    8. Re:Wattage by mr_mischief · · Score: 1

      Well, considering this 45nm part uses less power for 6 cores than the 65nm parts from the same company use for 4 cores, I'd call that win-win.

    9. Re:Wattage by 427_ci_505 · · Score: 2, Funny

      Watt you say?

      You have no chance to survive make your time.

    10. Re:Wattage by jannesha · · Score: 1

      ...er, no.

      At least, not if you are considering the difference between one server with 6 cores versus two servers....

      I.E. the only relevant performance/wattage ratio includes the wattage of the entire box, not just the processor.

    11. Re:Wattage by An+anonymous+Frank · · Score: 1

      Es-tu au courant?

    12. Re:Wattage by rallymatte · · Score: 1

      That's true for most of us, especially if what you're doing is rendering and such where you just want to make most use of the power, air cooling and rack space that you're given.
      But then again, it usually doesn't take Intel more than a few months before they have a low power version of the previous high end processor.
      I must say that over the last few years the power vs. performance has improved significantly.

    13. Re:Wattage by level4 · · Score: 0, Offtopic

      Maybe you should have posted AC.

      --
      Let my new 7-digit UID be a lesson to all - write down your passwords.
    14. Re:Wattage by Yvan256 · · Score: 1

      Nice reply. :)

    15. Re:Wattage by toddestan · · Score: 1

      They'll probably still be interested in this part. If your server is CPU-bound, then you might be able to use 2 six core servers in place of 3 quad core servers, for a net power savings overall. Of course, most servers I see are I/O bound and don't even get close to stressing the CPU(s).

  9. so this means by nimbius · · Score: 4, Funny

    i might finally be able to play crysis on my vista ultimate machine? i mean, granted, my pc will look more like a LHC when im through with it...but a few black holes are worth it

    --
    Good people go to bed earlier.
  10. Can only Linux and hypervisors use it... by Anonymous Coward · · Score: 0

    Intel's discussion makes lots of mention of hypervisors but nothing about how this will speed up yonder windows box. Is it true that only true multiprocessing operating systems (e.g. Linux) can make use of these multiple cores in a mostly symmetric fashion? Mark

  11. With a catch.... by Ritz_Just_Ritz · · Score: 3, Informative

    "There's an odd catch, however, that will affect the highest of high-end configurations. "Because Microsoft Windows operating system support is limited to a 64-core environment, within a single OS instance, we'll support up to 64 cores," said Colin Lacey, a Unisys marketing vice president."

    Gads, who on earth would run a 64-core Windows box? Unless they want to virtualize out multiple servers on one bit of hardware. Most of the "heavy lifting" I've seen on servers with mucho processor cores are running some flavor of Unix. I'm kinda surprised this hasn't been fixed already given the momentum of multi-core processors.

    Cheers,

    1. Re:With a catch.... by ShadowRangerRIT · · Score: 4, Interesting

      Windows optimizes for the low core case. I believe they use a bit field to keep track of the cores, so the 32 bit flavors of Windows are limited to 32 cores, while the 64 bit versions are limited to 64 cores. There may be a high end server SKU that bypasses that limitation, but I don't know of it.

      --
      $_ = "wftedskaebjgdpjgidbsmnjgcdwatb"; tr/a-z/oh, turtleneck Phrase Jar!/; print
    2. Re:With a catch.... by Macrat · · Score: 1

      Gads, who on earth would run a 64-core Windows box?

      Someone trying to run Microsoft's bloated software?

    3. Re:With a catch.... by afidel · · Score: 1

      There isn't, if Unisys doesn't have it no one does. They basically are billed as the mainframe maker of the x86 market. They were the ones that spurred the development of the Windows Datacenter edition development. There are some VERY large databases running on Unisys hardware.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    4. Re:With a catch.... by Kingrames · · Score: 4, Funny

      64 cores should be enough for anybody.

      --
      If you can read this, I forgot to post anonymously.
    5. Re:With a catch.... by shut_up_man · · Score: 1, Redundant

      64 cores should be enough for anybody.

    6. Re:With a catch.... by Jeremy+Erwin · · Score: 1

      SKU? Do you work in retail?

      At the moment,
      Windows Datacenter supports 32 cores on X86, and 64 cores on x64 and Itanium.

      The implication of "SKU" is that this limitation is trivial, and is imposed purely by marketing considerations.

    7. Re:With a catch.... by Anonymous Coward · · Score: 0

      Windows optimizes for the low core case. I believe they use a bit field to keep track of the cores, so the 32 bit flavors of Windows are limited to 32 cores, while the 64 bit versions are limited to 64 cores.

      ROFTL, that's a hell of a optimization. LOL!

    8. Re:With a catch.... by Anonymous Coward · · Score: 0

      Translation: Anyone running windows on a 96 core box is running the wrong OS -- but you knew that already.

    9. Re:With a catch.... by Anonymous Coward · · Score: 0

      http://www.microsoft.com/hpc/

    10. Re:With a catch.... by Anonymous Coward · · Score: 0

      At the moment,
      Windows Datacenter supports 32 cores on X86, and 64 cores on x64 and Itanium.

      The implication of "SKU" is that this limitation is trivial, and is imposed purely by marketing considerations.

      On the low end products, yes. On Datacenter it's imposed by the bit width of the CPU.

      Windows assumes the CPU bitmask field assumes will fit in a single register. Obviously this can be fixed but it doesn't work just yet.

    11. Re:With a catch.... by Jeremy+Erwin · · Score: 1

      Obviously this can be fixed but it doesn't work just yet.

      I think people who buy large servers with more than 64 cores expect that they'll see a significant performance increase over a mere 64 core device. At this point, Microsoft may have a buggy product, it may have a working product that provides only a marginal increase in performance, or it may have a product that scales well, and is ready for release.

    12. Re:With a catch.... by Pastis · · Score: 1

      That should maybe read "640k cores should be enough for anybody".

      Don't laugh ! Some hundred years and we're there !

    13. Re:With a catch.... by Anonymous Coward · · Score: 0

      Gads, who on earth would run a 64-core Windows box?

      Someone running Hyper-V.

    14. Re:With a catch.... by level4 · · Score: 1

      A hundred years? BlueGene/L has 213k cores - a mere factor of three increase shouldn't take long.

      http://www.top500.org/list/2008/06/100

      --
      Let my new 7-digit UID be a lesson to all - write down your passwords.
    15. Re:With a catch.... by atari2600 · · Score: 1

      SKU is a common acronym used by many in the software industry a lot of time without actually knowing what it stands for. Like RADAR. Like SKU. One need not be in retail to use that acronym.

      SKU you.

    16. Re:With a catch.... by Jeremy+Erwin · · Score: 1

      It's marketing jargon, pure and simple.

      The question shouldn't be

      "Does Microsoft have a product on the shelves that it capable of addressing more than 64 cores?"

      but rather

      "How much reengineering will Microsoft have to do to release a bugfree product capable of efficiently using more than 64 cores?"

      Marketers dream. Engineers do all the work.

      By the way, it's "Radio detection and Ranging". The acronym captures the tactical applications of RADAR quite well, don't you think?

    17. Re:With a catch.... by shutdown+-p+now · · Score: 1

      Gads, who on earth would run a 64-core Windows box?

      Some people do, apparently.

      Also, is Windows actually limited to 64 cores? I had the impression that that's the highest officially supported number (as in, MS has actually tested the OS on that many), not the highest possible.

    18. Re:With a catch.... by pimpimpim · · Score: 1

      For all we know (which is nothing, Windows being closed-core): it could be hard-coded in the kernel. Would it surprise you if it was?

      --
      molmod.com - computing tips from a molecular modeling
    19. Re:With a catch.... by shutdown+-p+now · · Score: 1

      It would, because there's nothing in it for MS - they don't have a more expensive edition of Windows Server to sell to someone who'd need more than 64 cores.

  12. I really want to know... by Cornwallis · · Score: 0

    Really. Why 6 cores? Or 4 or 2 for that matter? Doesn't that just validate the Ever Increasing Bloat (TM) of software. I'm not being a smart a$$. I don't understand these incremental increases for software that only marginally changes...except in size.

    1. Re:I really want to know... by Anonymous Coward · · Score: 1, Insightful

      Really. Why 6 cores? Or 4 or 2 for that matter?

      Doesn't that just validate the Ever Increasing Bloat (TM) of software.

      I'm not being a smart a$$. I don't understand these incremental increases for software that only marginally changes...except in size.

      It's a Xeon. It's for your server. It's not for the Ever Increasing Bloat (TM) of software, it's for the Ever Increasing Server Load (TM) of Successful Business.

    2. Re:I really want to know... by Cornwallis · · Score: 1, Interesting

      But I've got users who are upset they *aren't* getting a dual-core "because I need it". Doesn't matter that they are working on Access databases!

    3. Re:I really want to know... by Narishma · · Score: 1

      640K should be enough for anybody.

      --
      Mada mada dane.
  13. Now you can open six tabs in Chrome... by javilon · · Score: 4, Funny

    ... and each one will have it's own processor core.

    --


    When his defense asked, "Which computer has Jon Johansen trespassed upon?" the answer was: "His own."
    1. Re:Now you can open six tabs in Chrome... by mr_mischief · · Score: 1

      That's actually one of the reasons why Google went with processes for tabs instead of internal threads or trying to use OS-level threads. It's easy to get separate processes onto separate cores.

    2. Re:Now you can open six tabs in Chrome... by TeknoHog · · Score: 1

      Yes, because multiprocessor systems didn't exist until Intel innovated the Core. Which raises the question, how exactly did the earlier processor generations do any work if they didn't have any Cores.

      --
      Escher was the first MC and Giger invented the HR department.
    3. Re:Now you can open six tabs in Chrome... by aaron+alderman · · Score: 1

      I'm using firefox you insensitive clod!

  14. Core Wars III by Anonymous Coward · · Score: 0

    palpatine : 6 cores !?
    yoda : surprized ?

  15. No this a S4 cpu the mac pro is S2 and we need des by Joe+The+Dragon · · Score: 0

    In less you want the mac pro to start at $3000 - $4000.

    we need a 1 cpu desktop mac maybe with a 775 xeon at $800 to $2000. The 1 cpu mac pro starts at $2300.

  16. And how will you power it build your own nuclear p by Joe+The+Dragon · · Score: 3, Funny

    And how will you power it build your own nuclear power plant?

  17. But... by zenulator · · Score: 0, Redundant

    Will it run crysis?

  18. Why buy multi-core? nothing uses it by denis-The-menace · · Score: 1

    Being stuck in a windows world I see no benefit in multi core CPUs since XP does NOTHING with the 2nd core. I have a dual core CPU at work and CPU utilization NEVER goes over 50% meaning only one core is doing the work.

    Does VMware workstation or Ubuntu actually make use of the extra cores?

    --
    Obama's legacy: (N)othing (S)ecure (A)nywhere and (T)error (S)imulation (A)dministration
    1. Re:Why buy multi-core? nothing uses it by Anonymous Coward · · Score: 0

      Browsing slashdot in one or two browsers will not push your utilization over 50%. Try opening 5 or 6 slashdot windows.

    2. Re:Why buy multi-core? nothing uses it by gsgriffin · · Score: 1

      I do. I have a quad coming right now (Q9550). I run CAD design and also rendering and animation of buildings. I can be designing in the CAD (1 CPU) and have a rendering using 3 CPU's at the same time and not effect the response time of the rest of my work (several rednering pograms will use everything you've got to render as quick as possible). I used to have to do one at a time. I could wait for hours for a detailed rendering and not be able to get any other work done. Yes, this is XP I'm talking about and using.

      --
      jsut athnoer menagiensls ltitle psrhae for you to dcoede. Why do we wtsae our tmie dnoig tihs?
    3. Re:Why buy multi-core? nothing uses it by kimvette · · Score: 1

      Then you're running single-threaded applications. Try running multithreaded applications and you can pin both cores at 100%.

      --
      The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
    4. Re:Why buy multi-core? nothing uses it by Anonymous Coward · · Score: 0

      Can always set manual processor affinity to move projects to a single core, so that both cores are running independent software.

      Wasnt this an issue that was brought up a while back, where XP / Vista cycles software between processors too quickly, rather than letting each processor handle its own load for a while?

    5. Re:Why buy multi-core? nothing uses it by squizzar · · Score: 2, Insightful

      In this case, much as it pains me, it has nothing to do with windows, and everything to do with you getting the wrong tool for the job. You have a double garage and two cars, but you can't drive them both.

      I on the other hand have friends I like to let use my spare car: Things like VHDL Simulators and FPGA synthesis tools, that will gladly consume a core and several gigs of memory for a few hours. On a single core machine you might as well go to sleep because the system will be next to unresponsive while it's processing that kind of load (well windows systems, in my experience linux and unix systems maintain an impressive level of responsiveness even when they are being hammered). The core2duo in my machine at the moment means I can carry on using my machine and do the heavy processing (or do two lots of heavy processing and go to sleep).

      For me it's more efficient and convenient than having two PCs, and not as expensive. Which seems like a good solution. At the end of the day it sounds like you don't have any application that will make use of your extra cores.

      I use Ubuntu at home and I'm afraid the same thing applies: Unless you have applications that are designed for parallel processing, or you actually want to do more than one thing at the same time, then you won't see the second core get used. VMware won't magically parallelise your code, so unless you are running two instances that are doing things at the same time you won't see both cores get used.

      That's just the way things are: there aren't too many applications that are easily parallelisable that haven't already been parallelised.

    6. Re:Why buy multi-core? nothing uses it by RightSaidFred99 · · Score: 2, Insightful

      This is a server CPU. Not sure what XP has to do with it, really? People who run servers definitely use multiple cores.

    7. Re:Why buy multi-core? nothing uses it by timeOday · · Score: 1

      This is a server CPU.

      Yes, for the moment, assuming you believe in such a distinction.

      Anyways, desktop CPUs are going the same way. There's nothing else to do with all the transistors. (Kudos to Intel for 45nm btw).

      Besides, the jump from supporting 4 cores to 6 is nonexistent. 1 to 2 was the hard one, really, and admittedly a lot of apps never made that jump and don't need to. But photoshop, nonlinear video editors, etc... anything with fine-grained multithreading will use 6 cores just fine.

  19. That's already the case. by DrYak · · Score: 5, Informative

    6 = 8 - 2 broken cores ?

    You joke but that's already the case with PS3's Cell (7 SPU = 8 - 1 broken), with tripple core Phenom (3 = 4 - 1 broken), and with a very high number of graphic cards (The range segment {pro/mid/low-cost} on which a GPU is used = the number of functional cores they managed to salvage)

    A separate reason may be the number of {quickpath/hypertransport/etc.} interconnects (6 cores require 15 interconnect to communicate, 8 cores require 28 interconnects). 6 to 8 cores isn't such a big increase but keeps the number of inter connect reasonnable.
    (Other processors types like Tilera end up only interconnecting adjacing cores on their 64x chips and you have a strongly *Non*-Uniform Architecture, with not all core able to reach and talk to others at the same speed)

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
    1. Re:That's already the case. by jkenneth24 · · Score: 4, Informative

      i dont think this uses Quick Path Interconnects yet... the article stated this was still Penryn. Theres also a bit at the end where the articles stated AMD chiming in and saying "Intel has taken the old front-side bus architecture and added 6 cores to it,"

    2. Re:That's already the case. by Kjella · · Score: 1

      You joke but that's already the case with PS3's Cell (7 SPU = 8 - 1 broken), with tripple core Phenom (3 = 4 - 1 broken), and with a very high number of graphic cards (The range segment {pro/mid/low-cost} on which a GPU is used = the number of functional cores they managed to salvage)

      Just because they're disabled doesn't mean they're broken. Say you have a 95% yield on a PS3 core. 8 SPU good = 0.95^8 = 66%, 7+ SPU good = 0.95^8+8*0.95^7*0.05 = 94%. Yet they can't use the full power of the 66% perfectly fine processors without creating two console versions. In other things like CPUs and GPUs they do go in different bins of functional cores/lines/clockspeed but it also depends on what the market wants so they can be downbinned and sold as cheaper parts. In the past people have been buying and unlocking cheaper parts with varying success, as I'm sure you know they are holding back to keep margins high. They know that sooner or later either the technology or the market won't let them push out these kinds of improvements at those prices. Given the recent developments in the world economy, I think many will figure their Core-based machines are "good enough".

      --
      Live today, because you never know what tomorrow brings
    3. Re:That's already the case. by Anonymous Coward · · Score: 0

      blind faith and "best theory matching centuries of data by millions of scientists of every nation and field" differ

      Let's analyze this. You say that they "differ", but really you're trying to say a whole lot more than just that. Beating around the bush can indicate hesitancy to be blunt and direct, which can indicate wanting to be sure of something but not really being so. You feel that a direct assertion would welcome direct challenges, which you're not prepared to defend against so you opt for innuendo. And that implication obviously is that "blind faith" is wrong and "centuries...millions...every..." is right. The latter of which is well-known to be fallacious reasoning. So in summary, while you may be right, your argument is as weak as your confidence in it.

    4. Re:That's already the case. by Joe+Snipe · · Score: 1

      Well, I can't find the article or the comment now, but I am positive that I found you. You made an anonymous comment with regards to posting on craigslist for reasons I don't need to get into here (I'm working on my detective skills, not my embarrassing /. users skills).
      I'm just posting here as a reference note for myself, but if you remember the post and it was indeed you please let me know.

      --
      Sometimes, life itself is sarcasm...
  20. Re: "yes, triple core do exist" by Joce640k · · Score: 1

    Again, this is a defective four core chip which you've been duped into purchasing.

    --
    No sig today...
  21. Not SM cores? by Anonymous Coward · · Score: 0

    6 cores? not 4 or 8 or 16? Wouldn't it be more profitable if they were to introduce cores in half or quarter steps? 2 cores, then 2.5 cores, then 2.75...
        Personally, I could really dig on 3.1415 cores. Maybe install it in a roof-mounted server or something.

  22. I Want by WED+Fan · · Score: 4, Funny

    I'm holding out for a 12 core processor.

    I'm also holding out for a razor blade with 6 blades, screw those wimpy 5 blade razors that Tiger is pitching right now. (F*ck, I have a beard, why do I want a razor blade? Screw it, I'm still waiting for 6 blades.)

    --
    Politics is the art of looking for trouble, finding it everywhere, diagnosing it incorrectly and applying the wrong fix.
    1. Re:I Want by uigrad_2000 · · Score: 1

      I'm holding out for a 12 core processor.

      So is AMD

      I've been following the news of this 6-core processor for a while, and the news articles about it in the past say that it is the last of the Penryn line for Intel. So, what ever happened to the Penryn V8 (8 cores)?

      --
      Free unix account: freeshell.org
    2. Re:I Want by MightyYar · · Score: 1

      Obligatory Onion reference:
      Fuck Everything, We're Doing Five Blades.

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    3. Re:I Want by ginbot462 · · Score: 1

      Fuck that. Try Mad Mag's from `79.: 67 blades.

      http://www.wired.com/wired/archive/12.03/play.html?pg=4

      --
      Atlas Shrugged : Thematic Story :: Battlefield Earth : Organized Religion
    4. Re:I Want by flappinbooger · · Score: 1

      I haven't been following the 6 core processors at all, but I'm waiting for Intel to do something really unexpected and clever.

      Wouldn't it be good to take like 20 or 30 of those tiny little Atom processors and put them in one package in some way or another and get this multi-core stuff rolling?

      6 cores? Meh. Lets go double digits and stop messing around.

      People keep talking about how the Atom chips are nice but slow. Well, what about 4? 8? Heck, they're small and cheap and don't use much juice or make much heat, I'll take 20.

      --
      Flappinbooger isn't my real name
    5. Re:I Want by Anonymous Coward · · Score: 2, Funny

      F*ck, I have a beard, why do I want a razor blade?

      So you can quit the carnival and get a regular waitress job

    6. Re:I Want by Anonymous Coward · · Score: 0

      I'm laughing at myself because I nearly asked, "why would you put a * where the 's' goes? what is wrong with fsck?"

      Then, I realized that wasn't the only four letter word starting with an f.

    7. Re:I Want by eclectro · · Score: 1

      I'm also holding out for a razor blade with 6 blades

      What kind of hacker are you?? Just use a *two blade* razor and make three passes! Best shave EVAR!

      --
      Take the cheese to sickbay, the doctor should see it as soon as possible - B'Elanna Torres, "Learning Curve"
  23. Yay, more cycles we can't utilize by cbreaker · · Score: 4, Interesting

    Until Intel unveils their version of HyperTransport, this will be more of the same.

    You put a quad-core Xeon against a quad-core Opteron and under most conditions (besides CPU-only work) the Opteron will kill the Xeon.

    Now, we'll have even more cycles we can't utilize, because of the old design of the system.

    If you're going to do anything that uses both RAM and CPU (aka VMware hosts, which is what most big servers are used for these days) you'd better off with an Opteron.

    I'd rather use a dual or quad socket Dual-Core Opteron than a dual or quad socket Quad-core Xeon.

    --
    - It's not the Macs I hate. It's Digg users. -
    1. Re:Yay, more cycles we can't utilize by mr_mischief · · Score: 3, Informative

      In the article it's pretty clear this is a legacy-at-launch part to be a last upgrade for people using the current FSB technology. Other products will use QuickPath, but this is for those who want to keep their current motherboards for one more generation of processors.

    2. Re:Yay, more cycles we can't utilize by Thundersnatch · · Score: 1

      If you're going to do anything that uses both RAM and CPU (aka VMware hosts, which is what most big servers are used for these days) you'd better off with an Opteron.

      You could not be more wrong. Xeons dominate the VMmark benchmarks. Go home, fanboi.

      HyperTransport may indeed be better design than a shared high-speed bus, but that design advantage is negated by Intel's process and manufacturing excellence. Almost all benchmarks bear this out, SPEC, TPC, VMmark, whatever. Except perhaps at the extreme high end (>=8 sockets, which is less than 5% of the server market by revenue). I don't think Intel even offers an 8-socket Xeon platform.

    3. Re:Yay, more cycles we can't utilize by cbreaker · · Score: 1

      "but that design advantage is negated by Intel's process and manufacturing excellence"

      Who's the Fanboy?

      Look - almost everyone I work with for VMware installations insist on Opteron. Benchmarks are one thing, but real-world performance is entirely different.

      There's no doubt that the Intel CPU's are better performers on single-thread operations or operations where there's not a lot of memory IO. But the Opterons crush Intel when there's a lot of memory IO. Why do you think Intel is moving to a HyperTransport of their own? Because they WANT to admit that FSB is inefficient?

      PS. All three servers in the VMMark page that top the 32 core, 24 core, and 16 core are ALL Opteron. And if you think 16 core is not normal, think again. That's a 4 socket quad core Opteron, which is pretty common these days for VMware hosts.

      --
      - It's not the Macs I hate. It's Digg users. -
    4. Re:Yay, more cycles we can't utilize by RightSaidFred99 · · Score: 1

      I think most people will acknowledge that the Opteron has better multi-socket performance (probably starting at 4 or 8 sockets, not sure). How many people are running these behemoths? Not many. The people who insist on Opterons are simply misinformed and don't know what they're talking about, or they are stuck in 2005 when Opteron really did dominate.

      In single and dual socket machines, Intel chips perform better on a majority of real world tasks.

    5. Re:Yay, more cycles we can't utilize by MrNemesis · · Score: 1

      Just some anecdata; we have an IBM 3850 with eight cores (four dual-core Netburst-based 7120N Xeons) running ESX 3, and we can state that for our workloads (bunch of debian VM's running mostly python) it's spanked by a) the four core Core2 Xeon box and b) the four core opteron box (olde style, not barcelona). Profiling shows that the opteron appears to be kept at the highest utilisation because the VM's wait less on memory access.

      Granted, it's not a direct comprison of modern CPU's but the opterons hold their own against the supposedly much faster Core2 Xeons. VMMark is a good general indicator for generic VM performance, but as with any benchmark it's only useful if it's close to your workload. If we get a new cluster it's almost certainly going to be a pair of eight-way boxes and we're quite optimistic that opterons could well play quite nicely, given our VM's thirst for low memory latency.

      I know they don't offer an eight *socket* server, but even with the Core2 quad Xeons there's still alot of cache snooping going on over the FSB, and this can kill performance in highly concurrent SMP apps.

      £0.02

      --
      Moderation Total: -1 Troll, +3 Goat
    6. Re:Yay, more cycles we can't utilize by cbreaker · · Score: 1

      I guess you're not doing much VMware. For us (a consulting firm) we have been doing at least two VMware installations a month (ESX, VC, SAN, etc - we're a small shop, too) and the bare minimum host is a dual socket quad-core CPU from Intel or AMD. We usually choose AMD, because they simply perform better. We usually try to steer customers towards quad-socket boards, because generally speaking it's easier to manage fewer, more powerful servers than it is to manager more less powerful ones.

      It's not something you can exactly quantify right away. When you start loading up a new VM system, you'd never notice a difference between Intel or AMD. But, when you start loading 20, 30 or 40 VM's on a single host, that's when you can really start to see why AMD. You can do less stuff per core per cycle, but you can actually access more cycles because you're not trying to shove 32GB RAM down a single bus.

      Almost all servers now comes with at least two sockets, and almost all CPU's you purchase for them now are quad-core. So that's 8 cores in your average priced server. I don't know why people keep trying to tell me that it's not common when it absolutely is common for an average server to have 8 cores.

      When you go with VMware, you're likely to have more. And almost everyone is moving in that direction. I dare you to find even a medium to small sized IT environment where VM isn't already starting to utilize VMware or isn't planning on it in the near term.

      --
      - It's not the Macs I hate. It's Digg users. -
    7. Re:Yay, more cycles we can't utilize by RightSaidFred99 · · Score: 1

      Oh, the old "it feels faster" excuse. I think you need to go look at the VMWare performance data for the 74xx Xeon CPUs in 4 and 8 processor configurations before you go around claiming the AMDs "feel faster".

      AMD has done a good job marketing HT, I'll give them that. People will swear up and down despite the facts that their "memory hungry" apps just "run better" on the Opteron. I wonder what magic fairy dust people will claim AMD has when CSI hits the market.

    8. Re:Yay, more cycles we can't utilize by cbreaker · · Score: 1

      Which was my point exactly. I mean, I do install Intel VM clusters, and they work.

      My last gig, we had 12 VM hosts. One cluster was a four machine, quad-socket, dual-core "Core 2" based Xeon cluster. Another was four quad-socket, dual-core Opterons. 32GB RAM all around.

      I could run 100 virtual machines on a single Opteron box. (Mind you, many of these VM's were VDI XP guests) but I could not run 75 on one of the Xeons without it crawling to a halt. And there would be no reason for it - the CPU utilization was relatively low. No real indication as to why the performance was so bad - except for the fact that the Intel boxes would have to wait on RAM access so much. Same SAN, same everything else. The Core2's were clocked slightly higher.

      For many shops, the Intel CPU's are just fine but right now, if you want the best bang for your buck with a VMware host or anything else that is multi threaded and uses RAM, you're better off with AMD.

      Even when Intel releases their new bus archetecture I'll probably stick with AMD for awhile until it's proven. I'm sure it will be good - Intel always makes quality stuff, even though they over-predicted how far NetBurst could take them. Besides, AMD has never done me wrong and I think a little bit of loyalty is in order. AMD has done a lot for the x86 market.

      It's nice to see that Intel is following AMD's lead again here with QuickBus or whatever they're calling it. First with x86-64, then with going back to a more efficient CPU design at lower clock speeds, and now with adopting an integrated memory controller and a high speed interconnect bus (which Intel said was a horrible idea when AMD launched Opteron.) Intel might sell more parts, but it's been AMD that's actually innovated in the market.

      I'll keep buying AMD if it means there's actual competition in the market. Remember when Intel used to release CPU's horribly slow, and with minimal increments in speed, for a LOT more money? That stopped as soon as AMD entered the market for real with Athlon.

      I'm not an AMD fanboy, but I regard that company highly for what they've done and that does deserve some respect in my mind.

      --
      - It's not the Macs I hate. It's Digg users. -
    9. Re:Yay, more cycles we can't utilize by Thundersnatch · · Score: 1

      Look - almost everyone I work with for VMware installations insist on Opteron. Benchmarks are one thing, but real-world performance is entirely different.

      All of our internally hosted ESX cluster machines are dual-socket, 8-core Xeons with 64 GB of RAM. Not because we love Intel, but because that configuration gives you the best bang for your server buck. The same is true for our (large) external hosting provider, who is heavily into VMware and hosts thousands of VMs. All on dual-socket Xeons as far as I can tell. Operton-based VMware soltions are not mentioned by their salespeople.

      Two-socket servers dominate the market, for good price/performance reasons. In my experience with our own clusters and those of clients, Vmware cluster workloads tend to be IO bound, not CPU or memory bound. An 8-socket server doesn't help when you're waiting more for network or SAN IO. This makes sense: scaling CPU and memory is cheap, scaling at the SAN layer is extremely expensive. So disk should be your bottleneck. If you have a bunch of CPU-bound VMs, your workload is very different from those I've encountered.

      All three servers in the VMMark page that top the 32 core, 24 core, and 16 core are ALL Opteron. And if you think 16 core is not normal, think again. That's a 4 socket quad core Opteron, which is pretty common these days for VMware hosts.

      No, the 24-core machines are Intel-based. So Intel dominates both the two-socket and four-socket VMmark benchmarks, as I stated originally. You can say "That's not fair, they have six cores per socket!", and I say that makes them an even better value. Those four-socket machines are within 13% of the much more expensive (and larger and more power hungry) 8-socket Operton that leads the 32-core benchmark.

      Look, I would love for AMD to catch up to Intel again... I bought quite a few Opteron servers 4-5 years back. But they just don't make sense for the majority of use cases I see now.

  24. Re: "yes, triple core do exist" by mr_mischief · · Score: 3, Informative

    That's no different from the 486SXes, many of which were 486DX parts with the defective math coprocessor diked out. It's not very different from how the clock rate on every mainstream chip is determined by how many chips turn out to be stable at which speeds.

  25. Anyone doing heavy-duty OCR would by PeeAitchPee · · Score: 4, Interesting

    Gads, who on earth would run a 64-core Windows box?

    The ABBYY OCR engine (Windows only) in any of its latest versions (either direct from ABBYY or OEM'd into someone else's product) will multithread during recognition -- one thread for each core. We currently use a dual quad-core Xeon Windows Server box and I wish I had more cores -- when you get a project to OCR 2.1 million docs in a timeframe of less than a few years, you will too. ;-)

    ABBYY's own server-level product (Recognition Server) will span multiple boxes and use any designated cores available on those boxes -- and it scales linerally with the number of cores available (distributed or local). So yeah, there are still some Windows-only applications where a truly monster box would be great.

    OCR is one of those apps where you can absolutely NEVER have enough resources for big jobs.

  26. Re: "yes, triple core do exist" by confused+one · · Score: 4, Insightful

    What's wrong with that. Intel has sold defective processors for years, either binning them at a lower clock speed or trimming out chunks of cache and selling them as Celerons. If it can serve a purpose, does the job you need to get done, and it's available cheap... I don't see a problem here.

  27. Training! by andrikos · · Score: 1

    Now, how does my "six pack" seem to you?

  28. I wonder if this these... by Schnoogs · · Score: 0

    ...will work in my Mac Pro that already has dual quad cores.

    I'm focusing on multicore programming in graduate school and the more cores the better for what I'm doing. Call me a core whore if you want to! ;)

  29. Re:And how will you power it build your own nuclea by mr_mischief · · Score: 1

    Simple. He'll catch the black holes produced in ZPMs. They'll be released for civilian use by the time anything runs Crysis properly anyway.

  30. Re: "yes, triple core do exist" by Anonymous Coward · · Score: 0

    and so what is the big deal? This is the way the industry works. I suppose you shouldn't buy anything but the highest speed processor because slower speeds are just higher speed chips that were 'defective'. As long as they do proper QA on the working cores to determine they work, then who cares? Facts are there are defects in crystals and this just happens. No different then LCD panels with 5 bad dots, except here, you are only paying for what is working.

  31. But by Anonymous Coward · · Score: 0

    does it run L l l l inux?

  32. Wow! [obligatory] by cashman73 · · Score: 1
    Imagine a beowulf cluster of these! =)

    But, can it run Windows Vista? Or how about running Duke Nukem Forever on top of Windows Vista? Or is that just wishful thinking?

  33. Moderators... by Anonymous Coward · · Score: 0

    Mod this -1, "Wet blanket"

  34. ZPMs give off too much power for home use NAQUADAH by Joe+The+Dragon · · Score: 1

    ZPMs give off too much power for home use NAQUADAH REACTORs for that.

  35. Re: "yes, triple core do exist" by MightyYar · · Score: 1

    Again, this is a defective four core chip which you've been duped into purchasing.

    In the industry, we call it a "reworked" part. It's not being "duped" if it costs less and does what it advertises.

    By the way, your memory is almost certainly "defective" by your definition. Memory is reworked like crazy - loads of extra traces. And if it's REALLY bad, the top-tier guys sell it to discounters to sell as lower-capacity part.

    --
    W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
  36. Re:No this a S4 cpu the mac pro is S2 and we need by Gilmoure · · Score: 1, Redundant

    A mini-tower with a single Core 2 duo would be nice, in the $1000-$1400 range, Room for two drives, single DVD drive, and 4 GB RAM Mac would work. Maybe just three PCI slots, with one spaced apart from the others for larger video cards.

    --
    I drank what? -- Socrates
  37. AMD vs. Intel: CPU cache by ThePhilips · · Score: 1

    Can anybody explain me why AMD still has tops 1MB cache per core? And this is on Opterons. Normal AM/AM+ CPUs have only 512K cache per core. Intel now has 4MB of cache per core on its workstation CPUs.

    I can not understand why AMD doesn't increase cache size, while it's obvious that cache helps tremendously on memory intensive operations. Smaller caches are not even offset by its integrated on CPU memory controller.

    I'm planning upgrade and though I like AMD price/performance ratio, even for modest workstation Intel is better choice - simply because their CPUs have more cache.

    --
    All hope abandon ye who enter here.
    1. Re:AMD vs. Intel: CPU cache by Ant+P. · · Score: 1

      Intel has gone the huge cache/shitty main connection route while AMD has gone for fast main RAM access and less cache. Coincidentally IBM did the same thing with the Cell - all the SPUs have access to is their own tiny 256KB areas but the CPU can shove data from them to RAM at about 70GB/s so it doesn't matter as much.

      Of course the cache/FSB thing is moot now since Intel won't have a FSB soon.

  38. Not monolithic b4? by A440Hz · · Score: 1

    Hmm, I'll humbly admit here on Slashdot--where knowledge truly equals power-- that I hadn't known that many multi-core chips were simply packaged together, not fabbed on the same die.

    Seems like wire bonding and interconnect for a multi-die package would have to be very carefully done because of the clock speeds. When clocks go into the GHz region, that's the black magic RF domain where wires become effective antennae and all that. Doing traces on silicon allows a designer to route ground traces/pads around signal traces to mitigate traces "talking" to one another.

  39. Re: Mac Pro by An+anonymous+Frank · · Score: 1

    Yeah, ..., A friend of a friend of a friend's neighbour's teenage son has a pre-release Mac Pro unit with the new chip, and he says that he can finally run Vista with all the features activated!!

  40. Re:And how will you power it build your own nuclea by Spatial · · Score: 1

    It's a bit troublesome to build a whole nuclear powerplant just to have it piffle out 350 watts. The bragging rights would be unbeatable though.

  41. Why is 8 a special number? by OrangeTide · · Score: 1

    Why wait for 8 cores when you can get two 6 core chips in a package and have 12?

    --
    “Common sense is not so common.” — Voltaire
  42. Re: "yes, triple core do exist" by OrangeTide · · Score: 1

    You're really being sold 3 tested and working cores. You're supposed to ignore failed core on the die. It has nothing to do with the 3 that do work.

    --
    “Common sense is not so common.” — Voltaire
  43. Sun is first in everything by OrangeTide · · Score: 1

    Sun has been 64-bit for well over a decade too. Sun had hyperthreading(SMT) before Intel too, and they could do 4-way SMT rather than Intel's weak 2-way. Sun has always been ahead of the curve and gets no credit for it. I guess it's because they are good with technology and bad at capitalizing on it (at least not as good at it as Intel)

    --
    “Common sense is not so common.” — Voltaire
  44. v6 by c0d3r · · Score: 1

    Give me one of these running at 3.4ghz /w 6 cores, and it'll match my 3.4 v6. Now to integrate the two....

  45. Wafer Scale... by Anonymous Coward · · Score: 0

    ...integration by incremental advancement?

  46. Joke: Spacial Symmetry? by Anonymous Coward · · Score: 0

    I thought it was a joke: you are unlikely to have *symmetric* (in a spacial sense) multiprocessing if you have an odd number of cores.

  47. Don't be a dick by cbreaker · · Score: 1

    No, I didn't say it "feels faster." I said it's not easy to quantify, because if you benchmark a few apps or do a few little multithreaded tests, the Intels may be on top.

    You have to actually put substantial load on these systems to see the benefit, and in a virtualized environment you see just that.

    Hey, don't take my word for it. Look at the benchmarks for heavy load servers and shove it up your "single CPU's are more common because I have never done any work in the enterprise" ass.

    --
    - It's not the Macs I hate. It's Digg users. -
    1. Re:Don't be a dick by Anonymous Coward · · Score: 0

      shove it up your...ass

      Thanks for revealing which of you is the one who's been talking out theirs.

    2. Re:Don't be a dick by cbreaker · · Score: 1

      At least I didn't post as Anonymous Coward, you anonymous coward.

      --
      - It's not the Macs I hate. It's Digg users. -
  48. 7400 by 32771 · · Score: 1

    Those where the times when a puny 500MHz PowerPC could be as fast as a 2GHz x86 processor. When Motorola hadn't vanished into the mists of decaying memory (http://www.google.com/trends?q=motorola) and Freescale could have been a GNU project involving our scaly friends in some obscure way.

    Oh well, Freescale should sue Intel for stolen glory or something like that. Also somebody should remind Intel/AMD that decent multiprocessors always come with 2^k cores and not any odd prime composites of cores.

    After all, everybody knows that CELL is the new 7400. Oops, that one got 9 cores, maybe thats how it is nowadays. Well I could adjust to 3^k cores.
    Anybody up for k=4?

    My leet numerology skills allow me to predict that IBM will triumph over INTEL with a 81 core processor.
       

    --
    Je me souviens.
  49. Re:No this a S4 cpu the mac pro is S2 and we need by toddestan · · Score: 1

    Only 4GB of ram max and PCI slots instead of PCI-Express? Why those limitations? Or are you thinking like Apple by intentionally crippling this thing so that they can sell more Mac Pros?

  50. Q3 raytraced? by ypctx · · Score: 1

    So, will it run raytraced (software-rendered) Quake 3?

  51. Oblig Onion by Terminal+Saint · · Score: 1

    Fuck everything, we're doing 6 cores!

    --
    It's sad when choosing an installation directory on your own qualifies you as an "advanced user."
  52. Re:No this a S4 cpu the mac pro is S2 and we need by Gilmoure · · Score: 1

    For a lower priced/mid-range machine, Apple does tend to limit things. 4GB is the limit on MacBooks and iMacs. As for PCI, I meant PCI Express. I don't think anyone makes PCI cards any more.

    Now that I think about it, an iMac, without built in graphics and 1-2 PCI-E slots (with horizontal adapter), and 4GB max RAM would be pretty nice. Put it in some kind of brushed aluminum pizza box and you have an instant classic.

    --
    I drank what? -- Socrates
  53. WTF? by DrYak · · Score: 1

    Just, wtf was that ?

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]