Slashdot Mirror


Intel Unveils 10-Core Xeon Processors

MojoKid writes "Intel announced its new E-series of Xeon processors today, claiming that they will deliver nearly unparalleled advances in CPU performance and power efficiency. It has been just over a year since Santa Clara released its Nehalem-based octal-core Beckton processors. Whereas Beckton was focused entirely on performance and architectural efficiency, these new Xeons are more balanced. The new chips boost the core count to ten (up to 20 threads with HT enabled) and will be offered at a wide range of power envelopes. The new E7 series incorporates the benefits of the Sandy Bridge architecture, its support for new security processing instructions, and its improved power management technology. Intel has also baked in support for low-voltage DIMMs, which allows vendors to opt for 1.35v products."

128 comments

  1. unparalleled by BisexualPuppy · · Score: 5, Funny

    claiming that they will deliver nearly unparalleled advances in CPU performance

    What's the point of having 10 cores then ?

    1. Re:unparalleled by RalphSouth · · Score: 1

      I was wondering if anyone saw the irony. Thanks :-)

    2. Re:unparalleled by ArcherB · · Score: 2, Insightful

      claiming that they will deliver nearly unparalleled advances in CPU performance

      What's the point of having 10 cores then ?

      I laughed at NEARLY. Nearly unparalleled is not unparalleled. Not unparalleled is... well, paralleled.

      --
      There is no "I disagree" mod for a reason. Flamebait, Troll, and Overrated are not substitutes.
    3. Re:unparalleled by Anonymous Coward · · Score: 0

      | What's the point of having 10 cores then ?

      Well, according to other announcements in the news today Sunbeam has said they will be using 8 of these new Intel processors in their new digital series of toasters. A spokes person said "With the new Sunbeam iDigital series toasters, users will be able to control the degree of doneness of their toast by turning a dial and selecting 1 through 10. Sensors will collect this number and present it to an Intel 8052 micro controller that will adjust software running on the E-series processors located near the corners of the bread. Timing loops and type of calculation performed will determine the heat generated by the E-series ensuring a perfectly toasted piece of bread every time."

      Samsung announces it's iBagel toaster using a rotating, (speeds of 5400, 7200, 10,000, and 15,00 RPMs), e_Series processor whose heat generation is digitally controlled in ten separate settings.

  2. Specs by ustolemyname · · Score: 4, Informative

    130W TDB at 2.4 GHz, on the high end. Sadly, that information wasn't in the posted article. http://news.softpedia.com/news/More-Details-About-Intel-s-Upcoming-Xeon-E7-8800-CPU-Line-Emerge-183270.shtml

    1. Re:Specs by Spikeles · · Score: 4, Informative
      --
      I don't need to test my programs.. I have an error correcting modem.
    2. Re:Specs by 517714 · · Score: 1

      SGI is going to use up to 256 of these in a supercomputer, bring some weenies and marshmallows.

      Oracle’s 11g database can run 10 times faster at encryption tasks using the E7 series chips. Lots more performance comparisons and the 19 companies names Bull, Cisco, Cray, Dawning, Dell, Fujitsu, HP, Hitachi, Huawei, IBM, Inspur, Lenovo, NEC, Oracle, PowerLeader, Quanta Computer, SGI, SuperMicro, and Unisys

      --
      The US government have made it clear that we have no inalienable rights; any we do not defend vigorously will be taken.
    3. Re:Specs by Anonymous Coward · · Score: 0

      Why is this better than a 12-core Opteron with quad-channel DDR3?

    4. Re:Specs by robthebloke · · Score: 1

      Because each of the 10 cores can handle 2 threads via hyper-threading (i.e. 20 vs 12). In addition you have AVX instructions which allow you to process 8 floats or 4 doubles in a single instruction (vs SSE's 4 floats/2 doubles). Assuming there are no bugs in their chipsets, it should be a bit of a beast...

    5. Re:Specs by Thundersnatch · · Score: 3

      Why is this better than a 12-core Opteron with quad-channel DDR3?

      Because each Intel core is a lot faster than each of the 12 cores on the latest Opterons. For many workloads, single-thread performance still matters. Search for "SPECint2006 Rate" results on the latest processors - a latest-gen Intel core is about twice as fast as an AMD Bulldozer core. 2*10 > 12

    6. Re:Specs by timeOday · · Score: 1

      SGI is going to use up to 256 of these in a supercomputer, bring some weenies and marshmallows.

      130W seems impressively low for 10 fast cores (20 hyperthreads) if you ask me. Just a few years ago that would have been an entire cabinet full of P4's complete with a dozen power supplies, etc.

    7. Re:Specs by wisty · · Score: 1

      Because Intel chips are currently better than AMD chips, clock for clock.

      The only place where AMD has an edge is Zacate (AMD integrated graphics + a duel core Bobcat - it's Atom killer), and *maybe* Llano (too early to tell).

      Those are budget systems, which leverage AMD's ATI acquisition. Intel HD is miles ahead of the old Intel graphics, but I think Zacate is better.

      However, those are low-power consumer chips. Not server chips. Intel still owns the server.

    8. Re:Specs by default+luser · · Score: 1

      I would not put too much faith on the theoretical 2x performance increase offered by AVX this generation. Although the processing hardware is there, the processor itself is not designed with enough fetch width to keep the units fed.

      See Here

      Summary: a few tests topped %20 improvement.

      And Here

      Summary: a couple of tests topped %20 improvement. Many tests produced slower results with AVX enabled.

      The overall performance boost looks to be around %20-30, at least for now.

      --

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

    9. Re:Specs by Anonymous Coward · · Score: 0

      In addition you have AVX instructions

      This is Westmere-EX and not Sandybridge-EX, so no AVX.

    10. Re:Specs by rbarreira · · Score: 1

      It's called Moore's law.

      --

      The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
    11. Re:Specs by Anonymous Coward · · Score: 0

      Lets see when the Bulldozer comes out. Other possibility is of course that you wrote your post in the future.

  3. Unparalleled? by Anonymous Coward · · Score: 0

    Surely they will be *more* paralleled than any processor before them :-D

    1. Re:Unparalleled? by dropadrop · · Score: 1

      I'm sure some Sun engineers would disagree.

    2. Re:Unparalleled? by drinkypoo · · Score: 4, Funny

      I'm sure some Sun engineers would disagree.

      ...if they weren't busy looking for a new job.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  4. "nearly unparalleled" by L4t3r4lu5 · · Score: 1

    That's almost impressive.

    --
    Finally had enough. Come see us over at https://soylentnews.org/
    1. Re:"nearly unparalleled" by lawnboy5-O · · Score: 1

      and almost sufficiently adequately for the possibilities of dominating a majority of some markets.

  5. E-series of Xeon processors today by antonyan2010 · · Score: 0

    Absolutely no doubout E-series of Xeon processors today will be hot one http://maxwd.com/

    --
    Antony http://maxwd.com/s
  6. SB is no joke performance wise too by Sycraft-fu · · Score: 4, Insightful

    I've got a SB desktop computer and it just screams. they made some sizable per-clock performance improvements. Also AES-NI is no joke. I am pretty amazed by the speed. Tryecrypt supports it and the benchmark difference is huge. With a 100MB buffer a pure software AES implementation benches at 649MB/sec on my system (553MB/sec for Twofish, 254MB/sec for Serpent). Same test with AES-NI on, 2.7GB/sec. That is 4.2x the speed.

    Could be really useful for web servers, particularly if you are looking at going all SSL all the time.

    1. Re:SB is no joke performance wise too by Carewolf · · Score: 2

      I've got a SB desktop computer and it just screams.

      You should clean or replace the fans then.

    2. Re:SB is no joke performance wise too by Anonymous Coward · · Score: 0

      Good for you, but the E7 Xeon is using Westmere cores unlike the FS claims.

    3. Re:SB is no joke performance wise too by djdanlib · · Score: 1

      Yeah, get rid of the fans you have and install some golf fans instead. They don't tend to scream. Or maybe some Lions fans, since they don't really have much to scream about?

    4. Re:SB is no joke performance wise too by Mysticalfruit · · Score: 1

      Same here... we've benched out i7's vs. non i7 (prior generation, i.e Q6600) and for the same clock rate, we're seeing a constant 20% performance increase.

      --
      Yes Francis, the world has gone crazy.
    5. Re:SB is no joke performance wise too by Anonymous Coward · · Score: 0

      He probably got the fans from South Africa. They're loud but they sure do push a lot of air.

  7. Cooling performance... required by Anonymous Coward · · Score: 0

    This is what the craze of liquid cooling systems was all about. Time to buy a large radiator.

  8. Could already buy 12 core AMD chips last year by dbIII · · Score: 1

    Even I've got a machine with four of those in it and I waited about a year for the price to go down.
    processor : 47 vendor_id : AuthenticAMD cpu family : 16 model : 9 model name : AMD Opteron(tm) Processor 6174 stepping : 1 cpu MHz : 2200.000 cache size : 512 KB physical id : 4 siblings : 12 core id : 5 cpu cores : 12 apicid : 75 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw bogomips : 4399.82 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: ts ttp tm stc 100mhzsteps hwpstate [8]

    1. Re:Could already buy 12 core AMD chips last year by Byrel · · Score: 1

      I've been drooling over these; still a bit out of a college student's budget for a single processor motherboard.

      What do you do that can use that much parallelization? (Not that I have anything I could use it for; I just want it anyhow. :)

    2. Re:Could already buy 12 core AMD chips last year by Esteanil · · Score: 1

      What do you do that can use that much parallelization?

      Having just spent $130 in processing time on Amazon EC2 to render a 50 second movie in 13 hours, I'd really like to have a few of these...

      --
      I'm a dreamer, the world is my playpen. But hey, I'm a serious person, I can't dream all the time.
    3. Re:Could already buy 12 core AMD chips last year by geekoid · · Score: 1

      IF this was only about cores, you might have a point. I mean, the cores have to word well, hand threads well and so on. The AMD multicores don't do that as well as Intel.
      Also, we ware talking about servers needed for high utilization. For a basic PC, or even a 'gaming Rig' the difference will be measurable, but not likely noticeable.

      --
      The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
    4. Re:Could already buy 12 core AMD chips last year by PitaBred · · Score: 1

      Neat chips, but for $400 you can get an i5-2500K+motherboard. You won't get 10 cores, but it's still stupidly fast ;)

    5. Re:Could already buy 12 core AMD chips last year by dbIII · · Score: 1

      What do you do that can use that much parallelization?

      Processing seismic data to see what is under the ground. The data is in the form of digitised audio tracks that are picked up by geophones that act just like an old moving coil microphone. Now imagine applying the same filter or other transformation to twelve million audio tracks. It's a task you could split to twelve million CPUs at the stupid extreme - that's how easily the tasks can be split to run in parallel. Of course in reality you want to dump output to disk etc so it doesn't quite make sense to divide it up that finely but it should give you the idea. The software for that sort of thing is already written to run on clusters with as many cpus as you can get - some had to add workarounds to get beyond 1024 hosts on a single job (I don't have that many machines here but there are much bigger places).
      The biggest thing I've had running so far was on 96 CPUs running at 100% for a week and a half - quite a small project compared to other places.

    6. Re:Could already buy 12 core AMD chips last year by dbIII · · Score: 1

      IF this was only about cores, you might have a point.

      It IS only about cores or you are talking about something you don't need but others do. If you don't want to run a huge amount of things at once for sustained periods of time these machines are not for you. File servers, a typical web server or a desktop PC do not often see anything like those sort of loads so that's not what these things are for.
      It's a completely different niche typically called High Performance Computing (misleading name because it's more about getting a lot done at once instead of getting any sort of performance out of a single task).

  9. E7 is not Sandy Bridge based by Raven737 · · Score: 2
    The Quote

    The new E7 series incorporates the benefits of Sandy Bridge

    is a bit misleading, i think.

    As far as i understood it uses the older Westmere EX architecture. So while it may have added instructions also available in the Sandy Bridge architecture, clock for clock it will likely be slower in most cases and probably won't reach the the clock speeds of Sandy Bridge based chips.

    1. Re: E7 is not Sandy Bridge based by yuhong · · Score: 1

      Yea, why not call it the Xeon 7600?

    2. Re: E7 is not Sandy Bridge based by Anonymous Coward · · Score: 0

      +1 on the Westmere EX call.
      I'm assuming the Sandybridge-EX chips will be the Xeon E5 range, with the AVX, quad-channel ram and PCIe 3.0 and possibly QPI slots for Lights peak GP-GPU cards.
      And I'd bet an intel SSD 7xx series(using a new intel ssd controller chip) will be announced too(if we see SATA III in the LGA2011 socket chipset).

      I know what I getting myself for Christmas!!

  10. Re:The NSA was running at 600mhz in 1950 by freeshoes · · Score: 0

    Yeah that line of tin foil hats you have were in use 200 years ago.

  11. Unfortunately AMD's performance is lagging by Sycraft-fu · · Score: 4, Informative

    Hopefully Bulldozer will fix it but right now, they don't do so well. Have a look at this HardOCP article on the new SB processors (http://www.hardocp.com/article/2011/01/03/intel_sandy_bridge_2600k_2500k_processors_review/3). They tossed in a high end 6 core AMD CPU too. It just gets killed. In many tests, it is below the older 4 core i7 CPUs, in pretty much all of them it is below the 4 core SBs and I don't see a one that it beats the 6 core i7 (the 980X).

    AMD offers more cores, but their cores don't do as much. Don't buy in to core hype any more than MHz hype or anything else. More is not automatically better. Have to run benchmarks on it and see how it actually does.

    Like I said, hopefully Bulldozer will change that. Hopefully it'll be competitive with Intel per core, per clock and so on. However right now Intel processors just kill.

    1. Re:Unfortunately AMD's performance is lagging by TheRaven64 · · Score: 3, Interesting

      Bulldozer cores do even less - they're not quite SMT, but they're not quite full cores either (for example, pairs of them share an FPU). So, the number of Bulldozer cores is not quite equivalent to the number of i7 cores, and not quite equivalent to the number of i7 contexts (double the number of cores), but somewhere in the middle. I'm also not sure if they yet have any equivalent of Intel's Turbo Boost, which lets you overclock one core while powering down or underclocking the others, so single-threaded workloads (or a single CPU-bound thread in a multithreaded workload) get a boost.

      --
      I am TheRaven on Soylent News
    2. Re:Unfortunately AMD's performance is lagging by Anubis350 · · Score: 2

      I agree with you about core counts, but about turbo boost... If you're putting this chip, let alone 2 or 4 of them, in a system where turbo boost would be helpful you're using the wrong chips

      --
      "goodbye and hello, as always" ~Prince Corwin, from Zelazny's Amber series
    3. Re:Unfortunately AMD's performance is lagging by markhahn · · Score: 2

      no, we don't have any real info on how fast BD is yet. some technical papers on it indicate it's designed specifically for high clock while maintaining control on power dissipation. the shared FPU is somewhat faster than an unshared FPU would be, so this is a good choice, especially for code that's not always FPU-bound. and AMD has said that BD definitely has thermally-limited clock boosting.

    4. Re:Unfortunately AMD's performance is lagging by ShakaUVM · · Score: 1

      Yeah, Sandy Bridge has slaughtered AMD for the current generation.

      I've been a long time AMD supporter, just because I don't want there to be only one kid on the block (competition is good and all that), but about three hours ago I just bought a 2600K and matching mobo and ram on Newegg. First Intel CPU I've bought since the old $90 Celeron 300A that was 50% overclockable out of the box.

    5. Re:Unfortunately AMD's performance is lagging by Rockoon · · Score: 2

      Slashdot featured a comparison of Intel's vs AMD's "Turbo" features just about a year ago now.

      But the other poster is right.. you dont generally want turbo features on servers. This 10 core Intel server chip is in the same boat as AMD's 12 core server chips, as it will under-perform for single threaded tasks. These chips simply arent made for single-threaded performance.

      AMD has been king of the multi-CPU solutions for awhile now so we will have to wait and see how Intels new line will stack up in 4xCPU (40 cores / 80 threads) configurations vs AMD's current king 4xCPU (48 cores) solution.

      --
      "His name was James Damore."
    6. Re:Unfortunately AMD's performance is lagging by geekoid · · Score: 1

      supporting some company because you want competition is a pretty bad was to have competition. Buy the bast bang for your buck, if only one player can deliver, so be it,.

      As long as we continue to have good regulation so another competitor can rise up, all is good for the consumer.

      --
      The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
    7. Re:Unfortunately AMD's performance is lagging by Anonymous Coward · · Score: 0

      One of the big advantages of a monopoly (or a dictatorship) is that you have the power to prevent competitors from rising up.

      Also, when there's only one supplier, you have a single point of failure, both in production and imagination. Without real competition, there's no incentive to innovate or reduce prices.

    8. Re:Unfortunately AMD's performance is lagging by ShakaUVM · · Score: 1

      >>supporting some company because you want competition is a pretty bad was to have competition.

      If you have two equally good products (say the AMD64 vs. whatever Intel had at the time), it doesn't matter particularly which one you buy, so I always chose to support AMD. As I said, if we were down only to Intel, it would be a bad thing in general.

      >>Buy the bast bang for your buck

      Didn't I say I just bought Sandy Bridge? It's head-and-shoulders above anything AMD has right now.

    9. Re:Unfortunately AMD's performance is lagging by Anonymous Coward · · Score: 0

      But the other poster is right.. you dont generally want turbo features on servers.

      No, the other poster is not right. Turbo is just as desirable on servers as it is anywhere else: if the software you're running doesn't hit the CPU's power limits, it makes itself faster until it does hit the power limit. Why would that be undesirable, ever?

      AMD has been king of the multi-CPU solutions for awhile now so we will have to wait and see how Intels new line will stack up in 4xCPU (40 cores / 80 threads) configurations vs AMD's current king 4xCPU (48 cores) solution.

      Your benchmark link is laughable. Aside from the terrible choice of benchmark (nobody who buys expensive highly threaded servers would even think of using PassMark to evaluate them), the only highly threaded quad socket Intel systems tested are literally about 4 or 5 years old. The funny thing is, even those ancient systems, so old they had front side buses, hold their own against some of the much more modern AMD systems. For example, quad X7460 (6 cores 2.66 GHz) beats quad Opteron 6128 (8 cores 2.0 GHz). (I'd expect that in a real server load X7460 might not fare so well... the FSB hurt that generation of Xeons quite a bit. Then again, back when X7460 was new AMD didn't have anything nearly as good as a 6128 to go up against it.)

      Anyways. The new E7 10-core Xeons replace the previous line of X75xx 8-core Xeons (codename Nehalem-EX), and cpubenchmark.net hasn't tested a single Nehalem-EX system. So you have no basis to claim that AMD is king today if that's all the data you have to go on.

      But even that poor data does suggest that AMD is far behind. Just look at the top 3 systems: two 4-socket 12-core (48 cores total) Opterons take the top 2 spots, with a 2-socket 6-core Xeon (12 cores total) nipping at their heels. It doesn't take a genius to extrapolate from these results and predict that a 4-socket Nehalem-EX ought to leave these 4-socket Opterons in the dust.

      (In PassMark. Which, I reiterate, is a terrible benchmark for this purpose.)

    10. Re:Unfortunately AMD's performance is lagging by Lord+Ender · · Score: 1

      As long as we continue to have good regulation so another competitor can rise up,

      Continue to have? CONTINUE TO HAVE? We haven't had decent anti-monopoly regulation since Teddy Roosevelt was president.

      --
      A slashdotter who didn't build his own computer is like a Jedi who didn't build his own lightsaber.
    11. Re:Unfortunately AMD's performance is lagging by Anonymous Coward · · Score: 0

      and AMD has said that BD definitely has thermally-limited clock boosting.

      Didn't they state it as current limited and not talk about the thermal environment directly?

    12. Re:Unfortunately AMD's performance is lagging by Anonymous Coward · · Score: 0

      Hopefully Bulldozer will fix it but right now, they don't do so well.

      Intel dominates the $10k+ price range, but if you're spending less than $10k per system, intel runs twice to four times as much for the cpu/motherboard at the same level of performance.

      Don't buy in to core hype any more than MHz hype or anything else.

      In a bring-your-own-citrix-desktop world, multithreaded performance is everything.

    13. Re:Unfortunately AMD's performance is lagging by dbIII · · Score: 1

      AMD offers more cores, but their cores don't do as much.

      Apart from running twelve things at once?
      I think you are comparing apples to aardvarks here. Something that is designed to run on a single core may run a bit better on a two or four core machine when everything else gets out of it's way but after that you won't notice any improvement.
      I think you are looking at this in entirely the wrong way and are missing the entire point of these chips with a lot of cores and thus what you are using to measure their performance makes no sense. It does not matter because if you do not grasp this idea these chips are not for you and are for others with different loads. Functionally it can be almost identical to having a cluster in one handy box with a few savings on overhead.
      It's about running a lot of independent things at once. More IS better in that situation. It's a niche and not the general situation in computing but it's a big enough niche to make it worth making the stuff.

    14. Re:Unfortunately AMD's performance is lagging by Anonymous Coward · · Score: 0

      You don't want to spend too much time on that global lock, or wait on the reduce too long.

    15. Re:Unfortunately AMD's performance is lagging by jon3k · · Score: 1

      Depends on the workload. In virtualized environments with very mixed workloads (eg - a few hundred virtual desktops) turbo boost is incredible.

    16. Re:Unfortunately AMD's performance is lagging by Anubis350 · · Score: 1

      Point taken, I guess using the apps I do all the time I forget about other types of workloads :)

      --
      "goodbye and hello, as always" ~Prince Corwin, from Zelazny's Amber series
  12. Uncomplification. by Snufu · · Score: 1

    "...they will deliver nearly unparalleled advances in CPU performance..."

    Good to hear. Hopefully the next iteration will be fully unparalled. Much easier to program for a single core.

  13. Santa Claus? by Gumbercules!! · · Score: 0

    Am I the only person who initially read that as "It has been just over a year since Santa Claus released its Nehalem-based..."?

    1. Re:Santa Claus? by somersault · · Score: 1

      Yep.

      --
      which is totally what she said
    2. Re:Santa Claus? by Anonymous Coward · · Score: 0

      Nope.

    3. Re:Santa Claus? by lysdexia · · Score: 1

      I always see "Nehalem" as "Nifelheim". Some wish to put Christ back in Christmas, I want to put Santa Claus back in the Apocrypha.

  14. day of placing them in the cage scheduled by Anonymous Coward · · Score: 0

    just metaphorically as yet. they are still being built. the greatest story ever to be untold? tag team interviews from real people, guaranteed to generate facial expression images that are hard to focus on, yet impossible to forget?

    so far, all of the highly eligible contestants have the same reply; 'we're not going in the cage, plus we still want to kill you, & almost everybody else'. so we'll see?

  15. I have a cpu of * cores. by Anonymous Coward · · Score: 0

    1 core, 2 core, 4 core, 8 core, 16 core, 64 core, 128 core, 256 core, 512 core, 1024 core, 2048 core, 4096 core, 8192 core......

  16. Re:The NSA was running at 600mhz in 1950 by AHuxley · · Score: 3, Informative

    Have a read of what the NSA had in the 1950's and 60's at: Read up on ATLAS, ABEL http://www.governmentattic.org/3docs/NSA-HGPEDC_1964.pdf

    --
    Domestic spying is now "Benign Information Gathering"
  17. My xmas list. by miffo.swe · · Score: 1

    Hardware accelerated SSH
    Hardware accelerated LZMA

    Thats about it.

    --
    HTTP/1.1 400
    1. Re:My xmas list. by Trongy · · Score: 1

      The AES instruction set referred to as security processing instructions in the summary will accelereate ssh.

    2. Re:My xmas list. by miffo.swe · · Score: 1

      Thanks, missed that little gem. Will be interesting to see how a bulldozer handles this.

      --
      HTTP/1.1 400
    3. Re:My xmas list. by yorugua · · Score: 1

      So this CPU accelerates ssh? So it's a Linux/BSD/*ix accelerator? Microsoft won't be happy.

    4. Re:My xmas list. by robthebloke · · Score: 1

      It accelerates ssh in exactly the same way that fmul accelerates a calculator. I don't think microsoft will be concerned....

    5. Re:My xmas list. by VolciMaster · · Score: 1

      The AES instruction set referred to as security processing instructions in the summary will accelereate ssh.

      Is this anything like the accelerators Sun put in the Niagara line a few years back?

  18. Nice Try! by Anonymous Coward · · Score: 0

    Still... looks to far away from SPARC's 128 threads.

    1. Re:Nice Try! by the+linux+geek · · Score: 1

      Too bad the T3 has been killed on pretty much every industry-standard benchmark, against the full range of 12-core Opterons, 8-core Power7's, and 8-core Nehalem-EX...

  19. Re:The NSA was running at 600mhz in 1950 by Anonymous Coward · · Score: 0

    Just to be clear, that means 50MHz when compared to a modern i7.

  20. Shaving analogy by ozbird · · Score: 1

    Courtesy of the D-Generation.

    1. Re:Shaving analogy by fostware · · Score: 1

      +1 - Oh yes.... What we neeEEEEEEd is points :)

      --
      "We know what happens to people who stay in the middle of the road. They get run over." - Aneurin Bevan
  21. Re:The NSA was running at 600mhz in 1950 by freeshoes · · Score: 0

    Nasa put men on the moon in the 60's so does that mean we should all be going on holiday (vacation) to the moon? Some technologies don't scale or are too expensive to mass produce.

  22. You do seem to be correct by Sycraft-fu · · Score: 2

    Though these do not seem to have all the Sandy Bridge technologies. In particular, AVX isn't listed. Thus is does not seem to have new SB instructions. Maybe they are talking about the improvements to the existing AES-NI instructions (SB is faster with those than older i7s) however it does not appear to have new extensions.

    I don't know that AVX is of much use to servers, but it does mean this isn't SB architecture. Which means it is not as efficient per clock (SB made some good gains in that area, not that the original i7s aren't pretty efficient already). Also mean it probably doesn't have their new turbo boost tech. That isn't a huge deal, but is nice. It gives a wider range of boot options depending on how heavily cores are loaded.

    On the older processors you find 1/1/1/2 is a common turbo boost spec. That means it can increase 100Mhz at most with 4, 3, or 2 cores loaded and 200MHz at most with 1 core loaded. For the SB processors it is 1/2/3/4. It's a bigger deal for mobile, since they are clocked slower and have bigger turbo boost levels, but still nice for desktops and servers. Means if something hits a single core hard, you can get a non-trivial clock boost.

    Does make it less of an interesting announcement. More cores is cool and all, but SB is neat because of the new architecture. Apparently that is still to come for servers.

    1. Re:You do seem to be correct by Junta · · Score: 1

      And *particularly* this series lags even "entry" level Xeons (the ones that go up to two sockets). Generally, about 6 months after an architecture makes it to desktop land the associated entry Xeons release, and then about six months after that the high-end Xeon implementation of that architecture comes out. Hence this announcement in the ballpark of six months after the low-end Xeon Westmeres (I think a bit longer, but too lazy to look up).

      --
      XML is like violence. If it doesn't solve the problem, use more.
    2. Re:You do seem to be correct by DoofusOfDeath · · Score: 1

      I don't know that AVX is of much use to servers

      For my scientific computing work, getting as many AVX units as possible onto a single motherboard is actually a big deal. So it would have actually been great if these 10-core chips had AVX.

    3. Re:You do seem to be correct by yuhong · · Score: 1

      FYI, Nehalem-EX and Westmere-EP was released around the same time, March 2010 or so. For comparison, Nehalem-EP was released May 2009. Lynnfield was released September 2009 or so. The 45nm Clarkdale was released January 2010. The desktop Sandy Bridge was released January 2011. And now we finally have Westmere-EX.

  23. Web application development by Anonymous Coward · · Score: 0

    very nice post.good information.
    More info:- http://www.elantechnologies.com/services/web-apps

  24. Oblig. comment: Imagine... by Anonymous Coward · · Score: 0

    ...a Beowulf cluster of these!

  25. Re:The NSA was running at 600mhz in 1950 by TheRaven64 · · Score: 1

    First, MHz is a meaningless metric when independent of instruction set. Second, how much do you think the NSA was willing to pay for their 600MHz? I was talking to some IBM guys a bit about some of their high-end machine a while ago, and wondering who was actually buying them. Their reply was that they weren't allowed to disclose their customers, but 'most of them had three letter initials'. These machines had 1TB of RAM and up, and a price tag where optional features were measured in increments of millions of dollars. Some of their customers, apparently, bought the top-of-the-line model.

    So, if you want to be able to use the same sort of hardware as the NSA, I'm pretty sure IBM or SGI would be happy to sell it to you. You'll find the dollar price will be at least 8 digits, but I'm sure you're happy to pay that, rather than let the technologies be 'suppressed'.

    --
    I am TheRaven on Soylent News
  26. It's not a power of 2 by snsh · · Score: 4, Funny

    Any CPU with where the number of cores is not a power of 2 makes me uncomfortable. Six cores, ten cores - it just feels wrong.

    1. Re:It's not a power of 2 by Henriok · · Score: 1

      What about an uneven number, like the three core Xenon processor in Xbox 360?

      --

      - Henrik

      - when the Shadows descend -
    2. Re:It's not a power of 2 by Anonymous Coward · · Score: 0

      Or my Phenom II X3 720. Multithreaded software that had some type of engineering insight built into it should have no problem with the number of cores a processor has.

    3. Re:It's not a power of 2 by AHuxley · · Score: 1

      Dont worry, video encoding will just use any number of cores found. Your average game will use one core to keep the port to current generation of consoles simple.

      --
      Domestic spying is now "Benign Information Gathering"
    4. Re:It's not a power of 2 by Anonymous Coward · · Score: 1

      I'll take them off your hands.

    5. Re:It's not a power of 2 by Anonymous Coward · · Score: 0

      Just don't take any corners at full speed and you should be fine.

    6. Re:It's not a power of 2 by Rudeboy777 · · Score: 1

      What about multithreaded software that DOESN'T have engineering insight built into it? (ie. almost all multithreaded software)

      --

      From hell's heart I fstab at /dev/hdc

    7. Re:It's not a power of 2 by adisakp · · Score: 1

      Your average game will use one core to keep the port to current generation of consoles simple.

      Ummm... that might have been a current or valid point 5-6 years ago with PS2 and XBOX but not today.

      Speaking as a game programmer, most of the industry has been working for years on optimizing games for multiple cores. The current generation of consoles (XBOX 360 and PS3) are multicore and the next generation promises to have even more cores. Heck even handheld gaming systems (Sony NGP has 4 cores), portables, tablets (iPad2 is dual-core), and phones are going multicore.

    8. Re:It's not a power of 2 by Ripley · · Score: 1

      Sad. From the comments, it seems nobody even remembers what a hypercube computer is.

    9. Re:It's not a power of 2 by mpfife · · Score: 2
      Shesh - read it again buddy - there are 10 cores.

      Again proving there are 10 types of people in the world, those that understand binary, and those that don't.

    10. Re:It's not a power of 2 by Henriok · · Score: 1

      The Phenom II X3 is a four core processor with one core disabled due to manufacturing errors.

      --

      - Henrik

      - when the Shadows descend -
  27. Re:The NSA was running at 600mhz in 1950 by AHuxley · · Score: 1

    "high speed electronic static storage in the amount of 1,024 words. The word size was 36 bits instead of ATLAS I's 24, two address logic instead of one, more sophisticated instruction code, and the basis of all computing today, input-output program controlled instructions. Having two-address logic instead of one was very powerful for computers of this age. The new instruction codes included another first, a 'repeat' instruction, some arithmetic instructions, a scaling factor ability, and index jumping capability. " The NSA, then like now wanted to find data, numbers... then voices.

    --
    Domestic spying is now "Benign Information Gathering"
  28. Octal? by Anonymous Coward · · Score: 0

    Octal is a numerical system: adj: "relating to or using a system of numerical notation that has 8 rather than 10 as a base."
    and
    noun:"the octal system; octal notation."

    Perhaps they meant:
    octo- (also oct- before a vowel)
    combining form
    eight; having eight

  29. Octal vs binary gives performance boost by Anonymous Coward · · Score: 0

    I think working in octal will give a huge performance boost as compared to working in BINARY.

    One would think that would have been touted as a major feature as going from on/off to on/2/3/4/5/6/7/off states is a nice break-through.

    Each octal-bit now can now store 256 states vs on/off previously. Instantly increases memory density, bandwidth on the bus etc.

    1. Re:Octal vs binary gives performance boost by Chris+Burke · · Score: 1

      There's a good reason they aren't touting it. Turns out that making logic gates that can sense 8 different voltage levels is much more complicated, area-intensive, and slower than just being able to slam the output to one of the voltage rails as hard as you want/need. They tried and tried, but it was a dog all around.

      Then came the real breakthrough -- the realization that you can encode the 8 states in octal using 3 normal binary signals, and so simulate an octal circuit, only faster and smaller!

      But then calling it an "octal" chip seemed kinda silly, so they have mostly been keeping quiet about it and letting people think it had to do with the number of cores in certain platforms.

      --

      The enemies of Democracy are
  30. Re:The line of tinfoil hats by TaoPhoenix · · Score: 1

    Nah, that was probably 100 years ago courtesy of F. W. Woolworth. Before that everyone liked quality too much. Unhardened steel hats!

    --
    My first Journal Entry ever, in 8 years! http://slashdot.org/journal/365947/aphelion-scifi-fantasy-horror-poetry-webzine
  31. Next Mac Pro? by bjb · · Score: 2
    I bet the first production hardware we see this in is the 2011 Mac Pro. Apple seems to get the lead time on these things nowadays so they can once again claim "we're the shiniest" for several weeks.

    I'm still quite content with my E5462-based 2008 model, thanks :)

    --
    Never hit your grandmother with a shovel, for it leaves a bad impression on her mind...
    1. Re:Next Mac Pro? by MachineShedFred · · Score: 2

      I don't expect we'll see a Mac Pro announcement next week, as Apple's support for the AMD Radeon 69x0 cards is horribly broken in anything you can see outside of a lab in Cupertino. Announcing a system with "next generation performance" that uses previous generation video cards is something they are trying to get away from.

      However, NAB is next week in Las Vegas, so who knows what they might do to get people to stop looking at CUDA-accelerated Adobe Premiere.

      --
      Slashdot still doesnâ(TM)t support Unicode after it was added to the HTML standard in 1997.
    2. Re:Next Mac Pro? by Anonymous Coward · · Score: 0

      It depends... There were 8 core xeons available when Apple released the latest mac pro's, yet Apple went with the 6 cores.

      Although these 10 core sounds great. They might not have the same clock speeds as the current 6 cores.

    3. Re:Next Mac Pro? by the+linux+geek · · Score: 1

      No. These will not be in the Mac Pro, just as Nehalem-EX wasn't - these are aimed heavily at multi-socket data-processing workloads. The Mac Pro will probably get the Xeon E5.

    4. Re:Next Mac Pro? by Anonymous Coward · · Score: 0

      I bet the first production hardware we see this in is the 2011 Mac Pro.

      I bet you're wrong.

      (Not just being contrary. Xeon E7 is a high end 4-socket server chip. Apple has never used any of the predecessors to the E7 in Mac Pros; they use workstation/small-server 1/2-socket Xeon models. You should start expecting a new Mac Pro when Intel releases the Sandy Bridge derived 2-socket Xeon sometime later this year.)

    5. Re:Next Mac Pro? by petermgreen · · Score: 1

      Indeed, while intel did introduce 8-core xeons the clock speeds sucked so much that really the only reason to use them was if you wanted a 4-socket system or had some other weird requirements (e.g. INSANE ammounts of ram). For two socket systems with up to 96GB of ram the 4/6-core 56xx series xeons were the best option, especially if the system is to be used as a workstation.

      I suspect the next major revision on the mac pro will use some form of sandy bridge based LGA2011 xeon. Probablly with up to 8 cores per socket and two sockets (up to 16 cores total).

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  32. just what we need a $2500-$3000 1 cpu systems w by Joe+The+Dragon · · Score: 1

    just what we need a $2500-$3000 1 cpu system with a low-mid range video card and like 2GB ram at the base price.

  33. Re:The NSA was running at 600mhz in 1950 by putaro · · Score: 2

    I skimmed the document, I didn't see anything particularly exciting about ATLAS or ABEL. ABEL apparently had drum storage and core memory. There's no way any of the stuff in that document was running at 600MHz.

    The Cray-1 ran at 100MHz and the NSA and national labs snatched them up. There would have been no market for the Cray if there were secret machines running at 600MHz.

    I worked in supercomputing in the late 80's and early nineties. At that time it was still possible to assemble processors out of discrete components and outperform microprocessors. Relatively small teams could build really fast machines. By the mid nineties this was no longer possible. Today, the industrial base required to make a high performance processor is huge. The government can't have machines significantly faster than what's commercially available. There's not enough money in the black budget to fund it. That's why you see the Air Force making a supercomputer out of Playstations.

  34. crypto performance by Anonymous Coward · · Score: 1

    Could be really useful for web servers, particularly if you are looking at going all SSL all the time.

    Sure, except you also have to worry about algorithms like RSA, DH, SHA1, SHA256, SHA384, SHA512, and providing a good source of random bits as well (hardware RNG).

    That's one thing I like about Sun/Oracle's T-series chips: they have all the above algorithms. A ~4 year old T2 chip can do RC4 at 81 Gb/s, AES-128 at 44 Gb/s, and AES-256 at 31 Gb/s: that's enough to saturate 10 GigE connections (in both directions at times). SHA-256 at 41 Gb/s and RSA-2048 at 6400 op/s make for very fast web secure servers.

    http://blogs.sun.com/sprack/entry/ultrasparc_t2_crypto_performance
    http://blogs.sun.com/bmseer/entry/ultra_fast_cryptography_on_the

    If companies web companies want to offer HTTPS, they just need to throw up a bunch of these as SSL proxies to feed back into your normal (Linux) app servers. Given that they run Unix (Solaris), you can probably leverage a configuration management system (e.g. Puppet) in a lot easier fashion than you could an appliance-based load balancer as well.

  35. A note about power consumption by Anonymous Coward · · Score: 0

    From one of the articles linked to in this thread: "Watts Consumed (lower is better)"

    To me, that's not an unbiased opinion. I work for a power company, guys, and I don't like to see this slanderous talk on a website as prestigious as this one. Plus, it's still cold outside. I have the data to prove that my computer room is, on average, 10% warmer than the entire rest of my house - and it's on the bottom floor. I just want you all to remember that you can run your computer all day and it won't drive your gas bill up _one cent_

  36. Yeah, but can it play Crysis? by Anonymous Coward · · Score: 0

    Seriously,

  37. Re:DEAR SLASHDOT by Anonymous Coward · · Score: 0

    This shouldn't be modded -1. He's right. I can't click through links either (newest chrome). Shit's busted.

  38. But when can i get one by Anonymous Coward · · Score: 0

    that goes to eleven?

  39. octal-core? by VolciMaster · · Score: 1

    It has been just over a year since Santa Clara released its Nehalem-based octal-core Beckton processors

    Huh? Why are the core operating on octal? Does this new version run in decimal?

  40. imagine.. by Anonymous Coward · · Score: 0

    imagine a Beowulf cluster of those..

  41. Rebooting by dadelbunts · · Score: 1

    Will i have to send a small drilling robot to nuke the middle core if i need to reboot?

  42. Big Deal... by Barnum · · Score: 1

    My cores go to 11. None. More. Parallel.

    --
    I can't wait to eat that monkey...
  43. Meh by the+linux+geek · · Score: 1

    First glance at benchmarks indicates that this is still a bit slower than Power7, and has a similar or more expensive price. Considering we're a few months away from the Power7+ kicker, I don't expect this to have much adoption outside Windows Server users.

  44. Not necessiarly by Sycraft-fu · · Score: 1

    Not all tasks are of an equal load at all times. You can have situations where there is a strong load on less cores, and then later ones with a load on all cores. That's the reason for such a thing to exist.

    Not only that but turbo boost doesn't just work with how many cores are loaded, it has to do with electrical load and thermal load as well, hence why it can be active even if all cores are loaded. So it allows for a chip to meet a given TDP, but then if cooling is good it can go faster, and scale back if not.

    It's a useful technology that'll hopefully keep getting better. The more flexible the scaling, the more energy efficient CPUs can be when lightly loaded and the more powerful they can be when heavily loaded.

  45. 8 + 2 = unparalleled? by Anonymous Coward · · Score: 0

    What happened to the 80 core universe that Intel promised years ago? That would be unparalleled for sure!

  46. Intel Unveils 10-Core Xeon Processors by Anonymous Coward · · Score: 0

    yes, it's very fast.... you can get information about this on http://www.sawanswers.com/search?q=process