Slashdot Mirror

← Back to Stories (view on slashdot.org)

Intel Launches Xeon E7-8800 and E7-4800 V3 Processor Families

Posted by Soulskill on from the xeonward-and-upward dept.

MojoKid writes: Intel is taking the wraps off of its latest processors for enterprise server and pro workstation applications today, dubbed the Xeon E7-8800 / 4800 v3. Like its high-end desktop processors, the Xeon E7-8800 / 4800 v3 product families are based on the Haswell-EX CPU core. These new Xeons, however, offer a plethora of other enhancements and are packing significantly more cores than any current desktop processor. The highest-end Xeon E7-8800 series processors, for example, are 18 core chips. Previous generation Xeon E7 v2 processors were based on the Ivy Bridge-EX core, while the new E7 v3 parts are based on Haswell-EX, though both are manufactured on Intel's 22nm process node. Next generation Broadwell-EX based Xeons will make the move to 14nm. Xeon E7-8800 / 4800 v3 series processors have 32-lanes of PCIe 3.0 connectivity per socket, TSX is enabled in all SKUs, they offer support for both DDR3 and DDR4 memory (though, not simultaneously), and can address up to 6TB of memory in a 4-socket configuration or 12TB in an 8-socket setup. Intel has also goosed the chip's QPI interface speeds to 9.6GT/s.

46 comments

  1. Good for EM simulation by rfengr · · Score: 1

    Looks good for my EM simulation needs. Too bad the licensing to take advantage of all those cores is very expensive.

    1. Re:Good for EM simulation by sribe · · Score: 4, Informative

      Looks good for my EM simulation needs. Too bad the licensing to take advantage of all those cores is very expensive.

      Intel has 2 parts just for you: E7-8891v3 and E7-8893v3, maximum clock frequency, fewer cores. Seriously, they are designed and marketed specifically for "Lower per-core software license fee costs Higher per-core performance".

    2. Re:Good for EM simulation by Anonymous Coward · · Score: 2, Insightful

      Don't worry. I'm sure Oracle already has a plan to screw you with these processors too.

      I hear their next licensing program is called the 'Vinny special'. In this scheme you turn over your ledger, and in return Larry's goons will tell you how much of your gross you need to fork over to stay "in compliance" and how much more you need to pay "keep your kneecaps".

    3. Re:Good for EM simulation by mysidia · · Score: 2

      Microsoft and Oracle already know how to deal with this: it's called "nominal cores". The vendor comes up with a list of CPU models that are assigned "Weighting scores"; cores of certain CPU models are worth 150% of a core each, for licensing purposes, certain cores are worth 75% of a core each for licensing purposes, etc.

    4. Re:Good for EM simulation by mysidia · · Score: 1

      Intel has 2 parts just for you: E7-8891v3 and E7-8893v3, maximum clock frequency, fewer cores.

      This is a good idea for single-threaded tasks which can't be sped up anymore by distributing that task over multiple cores....... maximum single-core speed is ideal for certain workloads, and the extra cores would just be wasted.

    5. Re:Good for EM simulation by Kaenneth · · Score: 1

      Might be able to maintain 5 FPS in Dwarf Fortress.

    6. Re:Good for EM simulation by sribe · · Score: 1

      This is a good idea for single-threaded tasks which can't be sped up anymore by distributing that task over multiple cores....... maximum single-core speed is ideal for certain workloads, and the extra cores would just be wasted.

      To be clear, those two are 4-core and 10-core parts...

    7. Re:Good for EM simulation by davester666 · · Score: 1

      pay-per-cpu-cycle

      --
      Sleep your way to a whiter smile...date a dentist!
    8. Re:Good for EM simulation by Anonymous Coward · · Score: 0

      Get a Xeon Phi. I'm not kidding. You can find a Xeon Phi 31S1P for less than 200$, and it has 57 (fifty-seven) cores, 8GB of RAM. The instruction set is finnicky and you're stuck with Intel's compiler for now, so it's somewhat difficult to milk all its power (nearly a TeraFLOP!). But things will improve with proper Xeon Phi support in ispc: https://ispc.github.io/

  2. Ah, 18 cores by Anonymous Coward · · Score: -1

    Just what I need to watch even more of the YouTube while facebooking.

    Or you know, something important like um...how are you going to use this?

    1. Re:Ah, 18 cores by DiSKiLLeR · · Score: 1

      Oh, I don't know, servers? Virtualisation hosts?

      Why would anyone use a Xeon with that many cores in a desktop? o_O

      --
      You can tell how powerful someone is by the magnitude of the crime they can commit and be able to get away with.
    2. Re:Ah, 18 cores by Areyoukiddingme · · Score: 3, Interesting

      Why would anyone use a Xeon with that many cores in a desktop? o_O

      For my compiler, you insensitive clod. Now that we have SSDs that can feed the beast fast enough to keep it busy, I would be delighted to have one of these on my desk.

    3. Re:Ah, 18 cores by Anonymous+Brave+Guy · · Score: 2

      Why would anyone use a Xeon with that many cores in a desktop?

      I can think of quite a few specialised but realistic applications: CAD/CAM/CAE, rendering/pre-viz, high-end audio or video mixing work, simulation, and running modern web apps as fast as their traditional desktop equivalents used to run on a Pentium II.

      --
      If you disagree, post your argument. (-1, Overrated) isn't your personal censorship tool for views you don't like.
    4. Re:Ah, 18 cores by ILongForDarkness · · Score: 1

      Exactly. Not that it would likely be worth it for my employer, even with salary accounted for, but my work project has 25 subprojects that need to be built but a max depth of 5 I think in the dependency graph. So could reduce my full builds from ~1min 5-10 times a day to say 10s 5-10 times a day. But usually I can multitask: do another once over the pending changes, etc. So the time isn't usually wasted anyways.

    5. Re:Ah, 18 cores by Anonymous Coward · · Score: 1

      Oh it must be so traumatic... back in my day we use parallelism to get our build time down to 30 minutes. Except on the Cray T3D where, ironically, it took 24 hours.

    6. Re:Ah, 18 cores by Anonymous Coward · · Score: 0

      > 25 subprojects [...] max depth of 5 [...] dependency graph

      Java?

    7. Re:Ah, 18 cores by ILongForDarkness · · Score: 2

      No it isn't tramatic just a waste of time. Especially when a couple people come over to your desk and want you to check something on another branch. Checkout, deploy database. Then build. Then when switching back need to build again. So 3 people sitting around waiting for a progress bar.

      I've lived the HPC game too. In those days for me at least it was 5% dev and 95% reading/writing journal articles, books, either triggering or automating compute job configurations etc. Very little code but running for 200k+ cpu hours.

    8. Re:Ah, 18 cores by bored · · Score: 1

      But, that is what shared build machines are for. Not everyone is going to be building at once, and with a 5-20 member team its a lot less expensive to buy a machine with 40 cores and a bunch of midrange desktops/laptops, than buy all the developers high end workstations.

    9. Re:Ah, 18 cores by ILongForDarkness · · Score: 1

      We have "build" machines too. They get hijacked to run CI workloads. Typically 8-16 jobs running concurrently 24-7. They build -> then trigger smoke, other, security, migration etc testing.

      Often we compile several times locally in the process of getting things working. Sadly highly coupled code between C# and tsql/db code. You need to migrate and build/run tests locally to have any hope of pushing something to a CI/build server that has a hope in hell of not breaking everything.

      Anyways, I like having a high end local desktop, but then again I'm running webserver, db, and client workloads simulatanously on my local machine. 32GB ram, typically > 16GB in use at any given time. Without it we'd need to have dedicated dbs on servers we could migrate ourselves without any conflicts with any other users as we muck with stored procs and such.

      These huge number of core server CPUs other than for big stuff like non-scale out db workloads and such are kind of silly. For the last 15 years at least they've been trying to sell us on the idea that everyone wants to go back to having thin clients with VMs hosted on fat dense servers. The only one that wants that are the accountants. Then if you take into account productivity it might be a wash. Especially since clock for clock server hardware is probably ~4X more expensive.

  3. just what I need by ihtoit · · Score: -1, Troll

    ...wake me up when they cram 18 cores into a laptop.

    --
    Political debates have me rolling my eyes so much I think I got optical whiplash. I should sue. - Foamy The Squirrel
    1. Re:just what I need by Anonymous Coward · · Score: 0

      Why is this sarcastically just what you need? Why is this uninteresting if this isn't for laptops? Also what laptop workload uses 18 cores?

    2. Re:just what I need by Anonymous Coward · · Score: 0

      Because he's a cool hipster who thinks that people with desktops are old farts..

  4. Most CAD Modeling still uses one core. by Anonymous Coward · · Score: -1

    Too bad Solidworks still uses 1 core for its main functionality. Where's a 4.7 GHz Pentium 4 when you need it?

    1. Re:Most CAD Modeling still uses one core. by DiSKiLLeR · · Score: 5, Informative

      Get the i7-4790k which runs up to 4.4ghz and is unlocked so you can overclock it to 4.8ghz or so.

      It's probably hundreds of times faster than the shitty pentium 4 you mentioned to boot......

      --
      You can tell how powerful someone is by the magnitude of the crime they can commit and be able to get away with.
    2. Re:Most CAD Modeling still uses one core. by Anonymous Coward · · Score: 0

      Too bad netburst was a highly inefficient architecture. I mean a Intel Atom E3815 @ 1.46GHz is 5% faster. and a Intel Atom D2701 @ 2.13GHz is twice as fast.

      Of course I figure you're being sarcastic about the awesome power efficiency of the Pentium 4 architecture.

    3. Re:Most CAD Modeling still uses one core. by msobkow · · Score: 1

      Pre-Haswell Core i7 dual core laptop chips run roughly 4 times as fast as a 3.8GHz P4 single core -- per thread. And that is without overclocking. Haswell cores are even faster, and the desktop chips run at much higher clock rates than the laptop chips, so I've no doubt you could see 5-6 times the performance on a current generation CPU.

      --
      I do not fail; I succeed at finding out what does not work.
    4. Re:Most CAD Modeling still uses one core. by Anonymous Coward · · Score: 0

      You mean turn off 3 cores, overclock one to orbit?

    5. Re:Most CAD Modeling still uses one core. by Agripa · · Score: 1

      Too bad netburst was a highly inefficient architecture. I mean a Intel Atom E3815 @ 1.46GHz is 5% faster. and a Intel Atom D2701 @ 2.13GHz is twice as fast.

      How fast are they with 1/4 to 1/8th of the memory bandwidth?

  5. No GPU by Anonymous Coward · · Score: 0

    Where do I trade my shitty Intel HD gfx for the extra 14 cores in my i7?

  6. Mainframe era? by Anonymous Coward · · Score: 0

    Their E7-8890 has 18 cores and support 8 sockets. That's 144 cores on a server at 2.5 GHz. That sounds like a low or even mid end mainframe from years ago.

    1. Re:Mainframe era? by afidel · · Score: 3, Interesting

      Uh, it's nearly as much CPU power (141 cores at 5.2GHz, but even more CISC that x86) as the current mainframe, zSeries hasn't been about brute CPU in decades, it's about balanced CPU and I/O combined with high QoS and absolute stability. As an example the Z13 has nearly 1GB of L4 cache in the I/O coprocessors.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    2. Re:Mainframe era? by Anonymous Coward · · Score: 0

      Z runs the fasted microprocessor available on the earth.

    3. Re:Mainframe era? by Anonymous Coward · · Score: 0

      Ah, what is micro about it?

    4. Re:Mainframe era? by kriston · · Score: 1

      It's breathtaking to use systems that are explicitly designed for multiple workloads. I wonder how much energy and space datacenters could save if everyone and their brother hadn't gone whole-hog on an architecture that is only marginally suitable for multiprocessing. It keeps getting better, but x86-64 is just not designed for this.

      --

      Kriston

  7. Sandbagging by Anonymous Coward · · Score: -1

    They are just slowly ramping up to give the illusion of "researching a better product". Yeah right, they had 32 core Xeons a few years ago. In fact if you go look them up, some were made as far back as 2011 and cost around $18,000.

    We all know that production cost for the mac daddy chip vs the smaller chip is nearly identical and it's just a price scheme where the early adopters pay R&D costs to have teh new shiny.....

    So perhaps we can skip this 6-8-12 core crap and cut right to the meaningful chips that are possible to make *right now*?

    By not releasing all your technology at once, you can instead incrementally reap profit over and over by trickling updates to something you invented years ago. It's called Sandbagging guys and this is where we're at now. Especially looking at how many chips these days are identical yet microcode "locks" some of the cores... How is this not extortion? If only one big company has a fabrication lab nice enough to make these chips, how exactly do we call their bluff? Normally their competitor would step in, give us the available tech and reap profits but that can't really happen because there is essentially a Monopoly here with a cartel around it..... (and competitors license use of the same high tech lab in this case)

    We should have been running 16-core desktop chips about 2 years ago. Today we should already all have 32-core chips and be hearing about the latest release of something *new* that they are supposedly working on.... 32-core chips were talked about 5 years ago already at this point.

    1. Re:Sandbagging by NotInHere · · Score: 1

      Discoveries are made very irregularly, and are hard to plan. Therefore, its better for a company in the long run to "sandbag".

    2. Re:Sandbagging by ILongForDarkness · · Score: 1

      Sun back in the day, not sure if they still do it, used to offer servers with say half of the cores disabled. You could buy licenses and they'd turn on the extra cores without even needing a reboot. They offer different price points even if it means they waste some good cores disabling them to make an artificial performance different its still better for them than to have to make a different design/fab for each step in the process. The lifetime of a chip architecture/manufacturing process is so short that building n lines to make n products would be crazy expensive.

  8. Snap. by maseo126 · · Score: 1

    These procs sound awesome! Energy misers too. I would love to get some stuff running on them to see what they are like realtime:).

  9. still on Haswell by Tumbleweed · · Score: 1

    So they're not even based on Broadwell yet; when are they expecting to get Xeons based on Skylake out - next year?

    1. Re:still on Haswell by afidel · · Score: 1

      It's been like this since the P4/Foster Xeon:
      Desktop->workstation/1P server->DP server->MP server.

      This is the final spin of the Haswell line, Broadwell-EP Xeon's are set to launch at the end of the summer.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  10. Obligatory by Anonymous Coward · · Score: 0

    But does it run Linux?

  11. I've played with a 144-thread x86 beast. by Chirs · · Score: 1

    It's *beautiful* for simulating a cluster on a single machine.

  12. what by Anonymous Coward · · Score: 0

    toronto stock exchange is enabled for all stock keeping units.
    What does this mean?

  13. Seems to still be architecturaly-gimped by Khyber · · Score: 3, Interesting

    It appears that they didn't do much to the QPI besides boost the speed a bit. That's not going to fare well in HPC stuff. The reason I didn't use the V2 E7-8*** line was because due to how gimped the memory architecture was, you could run 2 socket 4 GPU, 4 socket 2 GPU, but not 4/4.

    It was cheaper, and just as effective, to go with the E5 instead, and make multiple node systems into a single box, instead. 8 socket, 12 GPU. Fuck yea.

    --
    Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
    1. Re:Seems to still be architecturaly-gimped by Khyber · · Score: 3, Interesting

      Quick clarification: Not the memory controller was gimped, but how processors communicated and shared stuff out of their memory to other processors was gimped. And the E7 v3 looks to have the same limitation. Pumping up QPI speed might help alleviate that SOME but nowhere near what's needed for multiple socket multiple GPU configs in a single non-nodal system.

      --
      Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
  14. BFD - compilers? by Anonymous Coward · · Score: 0

    When will compilers and large programming libs start to make efficient use of multiprocessing, and apps stop needing 150MB to display a web page?

    What about a wider faster GPU bus so we can offload smaller transforms to real, massively parallel processors? ATM, ~4k N is the breakeven for many computations.