Slashdot Mirror


Intel Launches 16 and 18-Core Core i9 Desktop Chips To Take On AMD Threadripper (hothardware.com)

MojoKid writes: Intel has officially launched its Skylake-X processor offering in response to AMD's Ryzen Threadripper series of desktop CPUs. The new Core i9-7980XE and Core i9-7960X are 18 and 16-core configurations respectively, with 2.6GHz and 2.8GHz base clocks and 4.4GHz max boost clocks. Both chips support Intel HyperThreading, with 36 threads of processing for the 7980XE and 32 for the 7960X, while both also have 44 lanes of PCI Express connectivity and support for DDR4-2666MHz memory. Both chips also utilize Intel's X299 chipset platform and are LGA 2066 socket compatible. The Core i9-7980XE has 24.75MB of shared L3 cache, 1MB of L2 cache per core, and a TDP of 165W. The Core i9-7960X's details are essentially same, though two processor cores and the cache associated with them have been lopped off. The Core i9-7960X has a couple of advantages, however, in that its base clock is 200MHz higher than the flagship Core i9-7980XE and it has higher all-core frequency boost to 3.6GHz, while the 7908XE tops out at 3.4GHz on all cores. The new chips are multi-threaded beasts in the benchmarks, posting the highest scores seen to date in heavily threaded workloads. They also offer strong single-threaded performance that outpaces AMD's Ryzen processors. Power consumption is surprisingly good as well and only marginally higher than the 10-core Core i9-7900X. However, at $1999 for the Core i9-7980XE and $1699 for the Core i9-7960X, as usual with Intel high-end chips, they're certainly not cheap.

119 comments

  1. Wow. $$$ by Anonymous Coward · · Score: 0

    I guess if you did a lot of encoding or compiling maybe. But I'd have to give someone a blowjob to be able to afford one of these things. Yowza.

    1. Re: Wow. $$$ by Anonymous Coward · · Score: 1, Funny

      Just one bj?

      You're either reaaaally good or know some very cash loose johns.

    2. Re: Wow. $$$ by Zero__Kelvin · · Score: 2

      More like 32 or 36 blowjobs simultaneously... on film.

      --
      Guns don't kill people; Physics kills people! - John Lithgow as Dick Solomon on Third Rock From The Sun
  2. More cores to idle 99% of the time! by Anonymous Coward · · Score: 0

    Hooray!

    1. Re:More cores to idle 99% of the time! by Anonymous Coward · · Score: 0

      Hooray!

      We'll chalk it up to other things that are useless on account of being idle most of the time like cars, microwave ovens, coffee makers, light bulbs, swimming pools, Jacuzzis, cameras, hair trimmers, bathroom scales, razors, faucets, and toilets.

  3. Hyperthreading by Anonymous Coward · · Score: 0

    How trustworthy is Hyperthreading after the Kaby Lake mess? I still don't have it enabled.

    1. Re:Hyperthreading by jopsen · · Score: 1

      What makes you think the next bug will be in HT?

      You can say this with respect to any feature of the CPUs...

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

      Well, there is always micro code revision if it's needed, right?

  4. Too little too late by xxxJonBoyxxx · · Score: 5, Interesting

    Sorry Intel, the new AMD procs offer great performance for the money. No reason to go Intel for at least a generation.

    1. Re:Too little too late by Anonymous Coward · · Score: 0

      Intel will just go back to doing underhanded things.

      Watch H.J. Lu to get suspended from glibc commits again.

    2. Re:Too little too late by Anonymous Coward · · Score: 0

      but SKYLAKE doesn't shove windows 10 up your ass, either. windows 7 and 8.1 will continue to function with this processor, and receive all the necessary support and updates through their respective lifecycles.

      unlike kaby lake (or the upcoming coffee lake) or your precious ryzen, which all artificially-restrict windows users to the shithole of windows 10 thanks to a little collusion between microsoft and the chip makers.

    3. Re: Too little too late by Anonymous Coward · · Score: 0

      I missed the joke, and Google isn't clearing it up... what?

    4. Re:Too little too late by Anonymous Coward · · Score: 1

      What the fuck are you talking about?

      Ryzen supports Windows 7. Sauce. New generation Intel CPUs do not. With the better performance per dollar offered by the AMD chips, I certainly haven't chosen Intel. My recently purchased 1600 on a mini ITX board is doing a great job as my home server.

    5. Re:Too little too late by Anonymous Coward · · Score: 0

      "necessary support"? From Microsoft??

      If you need necessary support from microsoft then you have put yourself in a wrong position. AND you are in a wrong internet forum. GTFO.

    6. Re:Too little too late by AmiMoJo · · Score: 3, Interesting

      There are other advantages to AMD parts too. More PCIe lanes, better chipsets especially if you want to do virtualization with IOMMU pass-through, longer expected lifespan of the socket and motherboard, and a less terrible secret backdoor system.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    7. Re:Too little too late by Anonymous Coward · · Score: 0

      Well, too little anyway. Most software is not written to use more than one or 2 cores, adding more cores really gets you nothing for all of that $$$$$. Biggest performance boost will be going from spinning disk to SSD. Most people will be fine with 3-6 years old machines, even for most gaming.

    8. Re:Too little too late by Anonymous Coward · · Score: 0

      Did we just revert back to 2012? DX12 and Vulkan, the predominant APIs going forward for gaming, can spread the workload across as many cores as are available.

      Excel can use as many thread as are available

      Blender can too

      Seriously.......how are you still holding onto this "2 cores is all you need" garbage?

  5. This sounds perfect for Rust! by Anonymous Coward · · Score: 0

    This highly parallel environment sounds perfect for a programming language like Rust that has been designed from the bottom up to support writing highly parallelized software applications. As we see more and more CPUs like this end up in regular computers I think we will really see Rust shine. The fastest software will end up being Rust software because it will naturally make such good use of the CPU and all of its cores.

    1. Re: This sounds perfect for Rust! by nsuccorso · · Score: 2

      Imagine how fast this Rust fanbot will run, as long as itâ(TM)s written in Rust! With this new processor family, the Rust bot will post up to 4 million odes to Rust per Slashdot story, per second! Youâ(TM)ll see no Rust gathering on this processor! Rust!!

    2. Re: This sounds perfect for Rust! by Anonymous Coward · · Score: 0

      Rusty scored some painkillers and cooking wine again...

    3. Re:This sounds perfect for Rust! by Anonymous Coward · · Score: 2, Funny

      I think we will really see Rust shine

      Isn't this an oxymoron?

      I'm not trolling. Just punning.

  6. Any faster? by Anonymous Coward · · Score: 0

    Have Intel's processors gotten significantly faster in the last 5 years?

    1. Re: Any faster? by Anonymous Coward · · Score: 0

      More cores, yes. Run my software faster than my i7-3370k dektop? Not significantly.

      I love articles like this. It says I did the right thing years ago buying the highest end I could afford and not touching it again. Maybe in another 5 or 10 years I'll upgrade because the all the fans will burn out from the dust and dog fur getting caked in there.

    2. Re:Any faster? by ArchieBunker · · Score: 1

      Not really. Software has also slowed as a result. Things still load as fast as they did two decades ago. An SSD makes a nice improvement but software never feels any faster.

      --
      Only the State obtains its revenue by coercion. - Murray Rothbard
    3. Re:Any faster? by UnknownSoldier · · Score: 5, Insightful

      Depends on what you are doing. Is single-threaded? Multi-threaded? Needs ECC, Memory bound? Computer bound? etc.

      For gaming? Nope. An i7-7700K is still faster then the iCore 9. LOL.

      For rendering? Yep 2:07 vs 7:19

      However, it is important to point out:

      * Intel CPU's are the fastest CPU's around but you literally PAY through the nose 2x- 5x for a measly ~10% increase in performance.
      * AMD's Ryzen and Threadripper CPUs have WAY better bang/buck. i.e. In Blender 2.78c AMD's Theadripper 1950X ($999) is faster then the Xeon E5 2699 v4 ($4,115). LOL.

      Conclusion:

      Is the i9-7960X worth a whopping $700 more then Threadripper 1950X?

      For many people, the answer is no. That is money that could be spent into a better GPU or more RAM/SSD.

      What CPU is "best" depends on your workload.

    4. Re:Any faster? by drinkypoo · · Score: 1

      Things still load as fast as they did two decades ago. An SSD makes a nice improvement but software never feels any faster.

      No way. Game load times are way better, because PC developers always sucked at seek optimization and seek times used to beat you down hard. No more. Both initial load and level load are way better these days. Gaming is the most demanding type of application users typically run on their PCs.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    5. Re:Any faster? by Anonymous Coward · · Score: 0

      "Gaming is the most demanding type of application users typically run on their PCs."

      You mean on YOUR PC. You are not "users". You are a case of one.

    6. Re:Any faster? by drinkypoo · · Score: 1

      "Gaming is the most demanding type of application users typically run on their PCs."

      You mean on YOUR PC. You are not "users". You are a case of one.

      No, I mean you're a typically idiotic AC. The vast majority of users will never do anything as taxing as gaming, period. Please don't comment again until you learn to read, if not think.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    7. Re:Any faster? by Anonymous Coward · · Score: 0

      Figuratively pay through the nose.

      There is no actual cutting of noses.

      http://www.neatorama.com/2008/08/07/origins-of-familiar-phrases/

  7. Hooray! by fuzzyfuzzyfungus · · Score: 5, Insightful

    So, it's a Xeon that can't do ECC. Seems totally worth it.

    1. Re:Hooray! by alvinrod · · Score: 1

      That's what I was wondering about as well. The lack of ECC support seems like a deal breaker for some workloads. The weird thing is that their previous HEDT chips had ECC support, so I'm not sure why they removed it, especially when they have more competition than anytime in recent memory.

    2. Re:Hooray! by Anonymous Coward · · Score: 0

      That's what I was wondering about as well. The lack of ECC support seems like a deal breaker for some workloads. The weird thing is that their previous HEDT chips had ECC support, so I'm not sure why they removed it, especially when they have more competition than anytime in recent memory.

      The last time I specified anything remotely close to 16 actual cores it was for a dedicated data processing rig for a lab, and I needed 2 processors to get enough pci-e slots. I tend to think I'd want ECC there if I did it again. (I think I used it last time, but I'm not sure.)

      What is the current expected mean time between memory glitches with say one of these and say 64GB of ram running without any sort of overclock? Is it more than say once or twice a year?

      The biggest advantage I see in a single chip solution might be reduced jitter in a system, particular when threads move between physical CPUs. I suppose a single chip might be cheaper as well, so there is that. Perhaps I'll get a chance to try to implement something interesting in Linux to see what is really possible. Windows, even with my best effort your going to get appreciable jitter, and probably multiple milliseconds, not matter what resolution you set the system timer to. (0.5ms is min, afaik.)

    3. Re:Hooray! by fuzzyfuzzyfungus · · Score: 4, Interesting

      I'm not privy to Intel's cryptic market segmentation schemes; but I'd imagine that it is because they now have competition. As long as AMD was basically irrelevant; "High end" could pretty much mean what Intel wanted it to: either the point on the i7 price performance curve where 'price' really starts to overshadow 'performance' or the end of the Xeon range with low core counts somewhat limited cache and total system RAM support; at their preference.

      Now that AMD has some actually interesting parts again; Intel has less freedom to just call things "High end". Because AMD still lags on single threaded performance, they do have an "is a really fast i7 for extra money" option(the i7-7740x, only 4 cores and limited RAM support; but very, very, aggressive clock speed) and the slightly baffling i57640x(pay a nontrivial premium for an LGA2066 motherboard why exactly?); but because AMD is dishing out the core counts, PCIe lanes, and RAM capacities; they also have the i9s; which are painfully expensive by desktop standards; but look like awfully tempting budget Xeons unless something can be done about that.

      ECC makes a pretty good 'something'. Lasering off virtulization support would go quite badly(making them effectively useless to anyone who spins up even the occasional VM, which is a fair number of people who buy $1000+ CPUs; but probably also being a massive bargain for people who don't plan to virtualize their workstation or server workloads, which is still a lot of units). Disabling AMT wouldn't be effective enough: gamer/enthusiast types wouldn't care; but neither would a lot of workstation or server customers(either all your computers are in one place, so fancy remote access tools aren't interesting; or you can just add an AST2400 or something if Intel tries to charge too much). Gimping core counts or PCIe lanes isn't an option because AMD; which pretty much leaves ECC.

    4. Re:Hooray! by yorgasor · · Score: 2

      Except AMD Threadripper offers ECC support as well. In the olden days, Intel was chimping on the consumer and low server end, trying to keep the Xeons from beating the Itaniums, and that was what led AMD to jump in with native 64bit support and dual core chips and start eating Intel's lunch.

      --
      Looking for a computer support specialist for your small business? Check out
    5. Re:Hooray! by fuzzyfuzzyfungus · · Score: 1

      That it does(and that's one of the reasons why it would be my choice if I were in the market); but I suspect that Intel is more willing to sacrifice that feature vs. AMD than they are to render a pretty massive slice of single-socket Xeons either irrelevant or in need of a nontrivial price cut.

      If AMD makes enough headway that the pain of losing marketshare to the other guy is greater than the pain of your cheap products cannibalizing your high-margin products; I would expect Intel to adjust their strategy; but they have little reason to start by doing that: cutting your margins sucks and if this strategy doesn't work, Intel doesn't really have an engineering problem on their hands; they just need to change some price tags in whatever areas are most seriously threatened. If this happens, the i9 series might well end up orphaned pretty quickly(it has pretty much zero reason to exist if Xeons are getting price cuts); but unlike the Netburst days, Intel isn't in the position of having to sell actually inferior products; but in the position of trying to command somewhat optimistic prices for otherwise competitive or superior products.

    6. Re:Hooray! by Anonymous Coward · · Score: 0

      ECC is rarely a deal breaker for workstation workloads.

    7. Re:Hooray! by Anonymous Coward · · Score: 0

      and??? the percentage of people that need/use ECC on workstations and would look at these could be counted on the fingers of a single hand. It is the same situation for price, anyone that really needs this performance doesn't give a shit about the price. Threadripper is better value for money and supports ECC, but if your only goal is performance that is hardly relevant.

    8. Re:Hooray! by Anonymous Coward · · Score: 5, Insightful

      The advantage of ECC RAM is NOT about "oh, the system has been up for 2 years without a glitch, see, ECC RAM was a waste of time".

      The whole point is that you you can see that there were no errors.

      Just finished a 2 month compute task? No memory errors? Great, the code worked and any abnormal results are due to coding mistakes. Otherwise, you might be tempted to run the whole thing again on the off-chance it might have been a memory error.

      I've had rigs up for > 5 years without a single ECC error, but I do not for one second believe ECC to be a waste of money.

    9. Re:Hooray! by Anonymous Coward · · Score: 1

      A lot of the AMD Ryzen chips support ECC. I just bought a mid-range 1600 with a mini-ITX board and it supports ECC. I bought a 16GB stick of ECC for it for only USD$120.

    10. Re:Hooray! by Lord+Crc · · Score: 2

      The advantage of ECC RAM is NOT about "oh, the system has been up for 2 years without a glitch, see, ECC RAM was a waste of time".

      The whole point is that you you can see that there were no errors.

      Indeed. I just had to reformat an Intel NUC as the filesystem had been completely trashed. Firefox had been a bit unstable on it, but well, that didn't trigger any warnings on my end. I also got one or two weird errors when running apt, but I was running unstable so again I didn't think to much of it...

      Then after a couple of months it stopped booting. Turned out the filesystem was bonkers, due to silent corruption.

      Ran memtest86, and one small but sequential range of addresses failed for every test.

    11. Re:Hooray! by Anonymous Coward · · Score: 0

      you can still use the memory in linux using badmem

    12. Re:Hooray! by Anonymous Coward · · Score: 0

      Perhaps most workstations do multimedia, publishing work. I will agree that doesn't matter then, except if you don't do a yearly memtest and the RAM goes really bad enough to corrupt files and file systems.

      Engineering, or a statistician who needs a 128+ gigs machine right now? (with perhaps issues that spending 6 months in fighting and waiting on bureaucracy will leave you bored and even with a dead career, so spending over 2000 or 3000 on a desktop makes sense)
      Well why spare the ECC? You'll have to buy the same i9 but branded as a Xeon (single CPU only). Same tactic Intel has done for several years.
      Perhaps of note is the Xeon will support (I suppose!) registered memory, and thus up to 4x bigger memory capacity.
      Eventually : would you rather have an 18-core i9 with 128GB, or a 12-core Xeon with 256GB ECC? Perhaps the latter is better anyway if you only wanted to do stupid things like running Chrome, as well as a Windows 10 VM with Edge etc.
      This example has you waste like 10 gigs RAM accomplishing not much. Add your regular OS and browser and other meaningless shit (there are "standalone" javascript + html5 IM clients that were in the news for extreme bloat). You could eat a sizable slab on even a 128 gigs machine already, even though you could have done most of this crap with Netscape and IE and mIRC and MSN and windows media player 6 etc. on a single core machine and less than 100MB RAM back in the days. duh.

      Perhaps 18 cores ought to be enough for everybody. The problem is we're going to reach 400GB RAM used or the like before maxing out such CPU, just so we can read black text (or light gray text) on white background (or lighter gray background), and do internet telegraph but with round pictures to represent other peoples's user accounts, or whatever the next frontier in computing will be.

    13. Re:Hooray! by Anonymous Coward · · Score: 0

      It's a xeon that can't do ECC but can be overclocked. So there's that.

    14. Re:Hooray! by Agripa · · Score: 1

      A lot of the AMD Ryzen chips support ECC. I just bought a mid-range 1600 with a mini-ITX board and it supports ECC. I bought a 16GB stick of ECC for it for only USD$120.

      As far as I know, all of the Ryzen chips support ECC. AMD said it was supported but not validated on the initial ones.

      This follows the pattern set by AMD where all of their socket AM chips have supported ECC.

    15. Re:Hooray! by Agripa · · Score: 1

      If you want ECC, then the choices come down to most AMD processors and Intel Xeon processors. If the comparison then is between Xeon and the current Zen based processors, Intel looks significantly worse as far as performance for a given price. Intel's current desktop releases become irrelevant.

      I went from an ECC supporting Intel Pentium 4 to the AMD Phenom II because of Intel's market segmentation and have no complaints. For me, AMDs Zen based processors compete against Intel processors like the Xeon E3-1275 v6 and Xeon E3-1285 v6 which are not competitive at all.

  8. 165W by ChunderDownunder · · Score: 5, Interesting
    That's way hotter than the worst Pentium IV.

    "Power consumption is surprisingly good". I wouldn't like to see the power bill at the end of the month and what sort of passive cooling is used to achieve a quiet workspace?

    I can see why the review website is called Hot Hardware.

    1. Re:165W by Anonymous Coward · · Score: 0

      I use an AMD 9370 you insensitive clod!

    2. Re:165W by Anonymous Coward · · Score: 1

      uh, those things take 500 watts when you overclock them and run them full out (e.g. prime95)

      165 watts. LOL

    3. Re:165W by Anonymous Coward · · Score: 0

      Could I perhaps interest you in concrete flooring and a lead cladded pc case?

    4. Re:165W by Mad+Merlin · · Score: 5, Insightful

      The Pentium 4 was also only a single core (or dual core if you count the short lived Pentium D line, which was based on Pentium 4 cores glued together) with vastly worse IPC. These have up to 18 cores and will chew through multithreaded workloads something like 50x faster than the fastest Pentium 4, while using comfortably less than double the power at full tilt (the i9-7980XE uses more than it's TDP at full load, around 195W, but recall that the Pentium 4 had a 115W TDP). Also, the idle and lightly loaded power usage on the i9-7980XE is dramatically lower than any Pentium 4. Unless you're running the CPU in part of a render farm that works 24/7 or something, it's going to be drastically quieter and use less power overall than any Pentium 4, not to mention absolutely obliterate it on performance.

      Having said that, I'd still opt for a Threadripper over one of these if I was building a computer today. The extra raw performance from the i9-7980XE over the 1950X (between low single digit %s to around 40%, depending on the test) is nice, but when you consider the weaker X299 platform (fewer PCIe lanes, no ECC) and the toothpaste under the IHS in the Intel (meaning it's impossible to properly cool it without delidding and potentially destroying the CPU, not to mention the runaway power usage even with a mild overclock) for double the cost, Threadripper seems like the obvious pick.

    5. Re:165W by drinkypoo · · Score: 2

      Don't forget the spectacular expense of the X299 platform. As usual, you'll wind up spending an extra hundred bucks on a decent motherboard for Intel as opposed to AMD.

      I'm still running an FX-8350 on a G1 Gaming, and it's spectacular for what it is. Rock-solid, awesome price:performance for when I built it. A new AMD system would be literally twice as fast, though.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    6. Re:165W by ravenshrike · · Score: 1

      Which never got nearly as hot or power hungry as this thing does once you OC it to an equivalent stage on it's performance curve. Course, the heat issue is primarily because Intel chooses to use toothpaste to save marginal amounts of money at best.

    7. Re:165W by Agripa · · Score: 1

      Don't forget the spectacular expense of the X299 platform. As usual, you'll wind up spending an extra hundred bucks on a decent motherboard for Intel as opposed to AMD.

      And then Intel magnanimously allows you to spend more for a dongle to enable RAID.

  9. Threadripper has more pci-e and $700 less by Joe_Dragon · · Score: 4, Informative

    Threadripper has more pci-e and $700 less

    1. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      also performs less. if your job, which brings in actual money, requires the most performance threadripper is not the one for you.

    2. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      If you drive to work in anything less than a $100,000 car, it's not the right one for you.

    3. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      Does it perform $700 better?

    4. Re:Threadripper has more pci-e and $700 less by Joe_Dragon · · Score: 1

      and for work like that AMD takes ECC Intel does not and with AMD you get more PCI-E for stuff like video cards and pci-e storage.
      Intel is pushing that MB fake raid with a key all tied to the slow DMI bus.

    5. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      no idea for you, but for me at a billable rate of $360 an hour for the resources we have doing work we would get that $700 back in a couple of days of savings. others mention ECC etc but those are not issues for our compute intensive work as everything is triple verified anyway so ECC gives us nothing and neither does storage or Video bandwidth. I am sure that is not the case for others but these CPU's would be our choice for next cycle of upgrades unless AMD/Intel release something else before that happens in 3 months time (we cycle our hardware at least once a year, often more frequently).

    6. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      also performs less. if your job, which brings in actual money, requires the most performance threadripper is not the one for you.

      Oh yeah? Adolf Hitler WOULD say that....

      Sorry, couldn't help it. Moore's Law has officially met Godwin's Law. LOLOL...

    7. Re: Threadripper has more pci-e and $700 less by dilvish_the_damned · · Score: 1

      Maybe the job is to Indy cups. Or whatever Danica Patric does, for instance. She could use an i9 to do that.

      --
      I think you underestimate just how much I just dont care.
    8. Re:Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      If you need i9 performance then i9 is not for you. Multiprocessor systems are.

      i9 has no use cases. Threadripper covers anything below it and multiprocessor systems cover anything above it.

      i9 is DOA.

    9. Re: Threadripper has more pci-e and $700 less by HumanWiki · · Score: 2

      What idiotic nonsense. I know plenty of people that own cats up in to the 7 figure range and drive themselves because they enjoy the experience of driving an exotic, super or hypercar.

    10. Re: Threadripper has more pci-e and $700 less by HumanWiki · · Score: 1

      And an idiotic auto correct. Cars. 7 figure cars.

    11. Re: Threadripper has more pci-e and $700 less by Anonymous Coward · · Score: 0

      I only clicked to view your whole message because of "cats" and was disappointed.

    12. Re:Threadripper has more pci-e and $700 less by ravenshrike · · Score: 0

      Highly unlikely unless you're running AVX512 specific loads.

  10. Oh wow. An ugly quick hack by Anonymous Coward · · Score: 0

    Same old Intel BS. Not new technology, just a an ugly hack of cores glued together with Intel's version of Gorilla Glue. This pig won't fly.

  11. Re: Wow. $$$ by Anonymous Coward · · Score: 0

    Just one bj?

    You're either reaaaally good or know some very cash loose johns.

    Dude, it's all in the sell. I've seen strippers bilk regulars for a few hundred at a time over an extended period of time for nothing more than waving her titties in his face and letting him sit there with a shit eating grin and a woody he'll have to take care of himself later.

    But, more on topic ... not everyone will want this. But, it will pave the way for the rest of us as the people who want the bleeding edge splash out and eventually the prices come down.

    If you're not a gamer, but want a machine that can do a whole lot of tasks at once without bogging down, more cores is always better. My AMD 8-core (they call it 8 core, it's 4 cores hyperthreaded) chews through most stuff you can do on a desktop quite nicely, because I tend to run 1-2 VMs at any given time, plus a bunch of other stuff.

    A 16 core machine with enough RAM is a poor man's ESX host and can run a lot of things at once. It isn't going to do any of them the fastest of all, but it will let you run a lot of stuff concurrently without bogging down .. the first time I had 3 different browsers, 2 VMs, iTunes playing music while ripping a CD, I was a happy camper. Because the machine just does what it needs to.

    These days, cores and threads make for a very responsive machine you can do a bunch of things on at the same time without stuttering, and that is a good thing.

    My last machine was 4 cores, this is 8 cores, I'm looking forward to 16 or 32 cores and a lot of RAM. You don't need to peg them all doing busy CPU work, but you can have a machine which multitasks like a son of a bitch. And as a workstation, that's going to count for a lot.

    When you can run Chrome, Opera, Firefox, iTunes, two VMs, run a backup of your machine while downloading a large file, and one or two other things, a machine like that is a dream to work on.

    Bring on more cores, there's a reason why even a basic desktop is now a 4 core machine.

  12. Re-badge Kaby Lake... by Anonymous Coward · · Score: 0

    I've heard that the Core i9-7980XE were re-badge Kaby Lake processors because Intel had no product to compete with AMD.

  13. meh by JustNiz · · Score: 1

    >> 2.6GHz and 2.8GHz base clocks and 4.4GHz max boost clocks.

    They obviously did that for heat/power consumption but single thread performance is gonna suck. My guess is you're only gonna actually see 4.4 Ghz once in a blue moon, and even then it won't be sustainable for more than a few seconds.

    This is a desktop processor not a server chip. Single threaded performance is critical.

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

      I bet it's gonna be a beast for mining though

    2. Re:meh by Mad+Merlin · · Score: 1

      You are wrong. Not only will it run at max turbo on single threaded code all day every day, it'll barely use any power doing it. Idle cores use very little power.

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

      Single thread performance is not always critical for a server. If it is, this is either domain specific or the software has a vertical scalability issue.
      Things like the Cadmium ThunderX wouldn't even exist if single thread performance was so critical.

    4. Re:meh by ravenshrike · · Score: 1

      If you're running single threaded applications primarily why the fuck would you buy the 7960X or 7980XE?

    5. Re:meh by JustNiz · · Score: 1

      Beceuse its being marketed as a desktop processor not as a server core.

    6. Re:meh by JustNiz · · Score: 1

      Under windows especially, the other cores wont ever be idle though.

  14. Re: Wow. $$$ by Anonymous Coward · · Score: 0

    Uhm, yeah, dude, we were talking bjs. Why're you talking cpus?

  15. My prediction about this thread by Anonymous Coward · · Score: 0

    Every sub-thread will include:

    One fanboy will say something positive about his favorite vendor.
    Then another fanboy will reply saying that the first vendor sucks and that the other vendor is much, much better.

  16. Re: Wow. $$$ by Anonymous Coward · · Score: 1

    Why the hell are you running iTunes? As a media player?? Really??

  17. Not only $$$, but not competitive. by Anonymous Coward · · Score: 0

    These are priced so out of the range compared to AMD you have to be an idiot to buy one.

  18. Imagine... by Anonymous Coward · · Score: 0

    A beowulf cluster of hot grits down your pants. Or Natalie Portman's pants.

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

      Natalie Portman is ugly

  19. These are really, really fast! by Anonymous Coward · · Score: 0

    Wordstar on Windows 3.1 will really smoke. Oh, wait, probably no multithreading needed. Oh, well.

  20. Re: Wow. $$$ by Anonymous Coward · · Score: 0

    Another dumb ass on /.

    Stupid beyond reason!

  21. Linus, is that you? by Mal-2 · · Score: 1

    How many of you "heard" the summary being read in Linus Tech Tips style? I know I did. It certainly read like some of their "content" lately.

    --
    How is the Riemann zeta function like Trump rallies? Both have an endless number of trivial zeros.
  22. 44 lanes! by darkain · · Score: 3, Insightful

    44 lanes of PCIe? That is only four more lanes than my first generation Xeon E5 workstation that I'm using right now, which is only a quad-core chip. Granted though, this machine is pretty maxed out with that tho, even with just one GPU, thanks to PCIe SSD, dedicated sound card, and 10gbe networking.

    1. Re:44 lanes! by AmiMoJo · · Score: 2

      PCIe lane starvation is a big problem now, and Intel is failing to solve it.

      Now we have NVMe SSDs all wanting 4 lanes, and USB 3.1 needs a couple of lanes per port to give maximum bandwidth, standard desktop CPUs don't have enough for today's needs, let along room for expansion. If you want that system to last 5+ years you want some free lanes to add expansion cards later.

      Threadripper finally delivers plenty of PCIe lanes. And ECC RAM support. And a software TPM. And it's a lot cheaper. And it runs cooler.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
  23. Why foolish names? by Futurepower(R) · · Score: 1

    The language has good features, but why did they call it Rust? Why do programmers choose self-defeating names? Gimp is another example. Malwarebytes is not malware, it is anti-malware software.

    1. Re:Why foolish names? by fisted · · Score: 1

      I for one am tired of the other way -- where the name of the software tries to communicate how amazing it is. That kind of software generally turns out to be crap -- eh, i mean, HyperCrap Pro Ultimate++ Superdooper edition 2018.

    2. Re:Why foolish names? by Anonymous Coward · · Score: 0

      Because it is punk to use such names. Cyberpunk, if you will. Some FOSS projects distance themselves from closed source commercial crap in every possible way.

    3. Re:Why foolish names? by Anonymous Coward · · Score: 0

      Rust is named after a type of fungus; not the metallic oxidation.

    4. Re:Why foolish names? by drinkypoo · · Score: 1

      Rust is named after a type of fungus; not the metallic oxidation.

      What a massive improvement. It won't kill your chevy, but it will kill your roses.

      Seriously, who comes up with this shit? Rust is a cool name for a post-apocalyptic survival game. (Too bad the game itself is such a fuckfest. Linux dedicated server instructions don't work, developers just don't give a shit.) It's not a good name for a language.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    5. Re:Why foolish names? by Anonymous Coward · · Score: 0

      Microsoft, and not macrosoft?

  24. AMD - Job well done by Lady+Galadriel · · Score: 5, Insightful

    Competition is a good thing. Without AMD, and all the people who helped keep them alive, Intel would have sat on things like this.

    In the long run, Intel parts are likely going to be better. They have more money, more chip desigers, and un-fortunantly more customers, (some that will pay outragous prices).

    --
    Lady Galadriel
    1. Re:AMD - Job well done by thejynxed · · Score: 1

      It isn't just some....pretty much every corporate giant and military in the world purchases Intel's chip offerings, in bulk. Intel's consumer-end market is and always has been a fraction of their overall sales (and that includes the bulk-buyers in this segment such as Dell and Apple). This has only slightly changed in the short era since ARM-designs took off in popularity. If AMD and a few other of the smaller chip makers could procure those kinds of contracts, things might actually change, but until then we're stuck with Intel basically at the top of the heap for the foreseeable future along with Samsung, being the other 600-lb gorilla in the chip space but whom rarely gets discussed when they are arguably just as bad as Intel.

      --
      @Mindless Drivel: 100% of Twitter posts ever Tweeted.
  25. Re: Wow. $$$ by Anonymous Coward · · Score: 0

    Welcome to the next bottleneck: disk I/O

  26. ECC by nojayuk · · Score: 2

    It's about time high-end and even commodity PCs moved to supporting ECC and using it as common practice. When total RAM fit in a PC was 1 or 2GB and data rates were a few hundred MB per second at best a bit error rate of 1 per trillion reads or writes was acceptable. Now that common motherboards can accept 64GB and more and RAM access speeds have also escalated the chances of a problematic bit error occurring in code or data have shot up, especially as the RAM's die mask sizes have decreased.

    As an aside I've used commodity mobos in the past that accepted and would run ECC RAM but only as regular memory, the chipset didn't implement any kind of error-correcting capability. My workhorse machines for bit-bashing all have ECC properly implemented on server-grade hardware.

  27. Amazing by Anonymous Coward · · Score: 0

    I knew Intel had more up their sleeves.

  28. Rust is irrelevant by Anonymous Coward · · Score: 0

    Just how many desktop/mobile tasks benefit from multi-threading?

    You make Rust sound like it's for idiots. The daft obsolete sounding name doesn't help? How long until the products oxidise and decay away in to a pile of dust?

  29. Obligatory:Intel CPU Backdoor Report (May 5 2017) by Anonymous Coward · · Score: 1

    The goal of this report is to make the existence of Intel CPU backdoors a common knowledge and provide information on backdoor removal.

    What we know about Intel CPU backdoors so far:

    TL;DR version

    Your Intel CPU and Chipset is running a backdoor as we speak.

    The backdoor hardware is inside the CPU/Bridge and the backdoor firmware (Intel Management Engine) is in the chipset flash memory.

    30C3 Intel ME live hack:
    @21m43s, keystrokes leaked from Intel ME above the OS, wireshark failed to detect packets.
    [Video Link] 30C3: Persistent, Stealthy, Remote-controlled Dedicated Hardware Malware
    [Quotes] Vortrag:
    "DAGGER exploits Intel's Manageability Engine (ME), that executes firmware code such as Intel's Active Management Technology (iAMT), as well as its OOB network channel."

    "the ME provides a perfect environment for undetectable sensitive data leakage on behalf of the attacker. Our presentation consists of three parts. The first part addresses how to find valuable data in the main memory of the host. The second part exploits the ME's OOB network channel to exfiltrate captured data to an external platform and to inject new attack code to target other interesting data structures available in the host runtime memory. The last part deals with the implementation of a covert network channel based on JitterBug."

    "We have recently improved DAGGER's capabilites to include support for 64-bit operating systems and a stealthy update mechanism to download new attack code."

    "To be more precise, we show how to conduct a DMA attack using Intel's Manageability Engine (ME)."

    "We can permanently monitor the keyboard buffer on both operating system targets."

    Backdoor removal:
    The backdoor firmware can be removed by following this guide [github.io] using the me_cleaner [github.com] script.
    Removal requires a Raspberry Pi (with GPIO pins) and a SOIC clip.

    Decoding Intel backdoors:
    The situation is out of control and the Libreboot/Coreboot community is looking for BIOS/Firmware experts to help with the Intel ME decoding effort.

    If you are skilled in these areas, download Intel ME firmwares from this collection [win-raid.com] and have a go at them, beware Intel is using a lot of counter measures to prevent their backdoors from being decoded (explained below).

    Useful links:
    The Intel ME subsystem can take over your machine, can't be audited
    REcon 2014 - Intel Management Engine Secrets
    Untrusting the CPU (33c3)
    Towards (reasonably) trustworthy x86 laptops
    30C3 To Protect And Infect - The militarization of the Internet
    30c3: To Protect And Infect Part 2 - Mass Surveillance Tools & Software

    1. Introduction, what is Intel ME

    Short version, from Intel staff:

    Re: What Intel CPUs lack Intel ME secondary processor?
    Amy_Intel Feb 8, 2016 9:27 AM

    The Management Engine (ME) is an isolated and protected coprocessor, embedded as a non-optional part in all current Intel chipsets, I even checked with the engineering department and they confirmed it.

    Long version:

    ME: Management Engine

    The Intel Management Engine (ME) is a separate computing environment physically loca

  30. 44 Single Root PCIe Lanes by Anonymous Coward · · Score: 0

    AMD threadripper fans can crow all they like, they only get max 32 lanes per PCIe root complex.

  31. Useless by bradley13 · · Score: 1

    Beyond a certain point, adding more cores doesn't add any performance. On the desktop, your average user is only *actively* using one or two applications. A typical application can't really make use of more than 2-3 threads, and probably doesn't make full use of those. Four cores is plenty, 8 is luxury that will mostly be idle. Anything over 8 is just nonsense on a typical desktop.

    --
    Enjoy life! This is not a dress rehearsal.
    1. Re:Useless by Anonymous Coward · · Score: 0

      Anything over 8 is just nonsense on a typical desktop.

      What makes you think these are marketed to the typical desktop user?

    2. Re:Useless by drinkypoo · · Score: 1

      What makes you think these are marketed to the typical desktop user?

      How far do you think Intel can get making chips which are useful only to people who are compiling a lot of software, or doing massive image or video editing projects? There are people like that out there, but not very many of them. Intel has way too many different SKUs.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    3. Re:Useless by Anonymous Coward · · Score: 0

      Beyond a certain point, adding more cores doesn't add any performance. On the desktop, your average user is only *actively* using one or two applications.

      And now, imagine that people will run this one servers. I maintain applications which have many processes, each with many threads, the more I can throw at them the better they run, and the happier the users are. There's a lot more people do with computers than desktop stuff. For an ESX host, this will be very useful since you can put a lot more CPUs into the machine. Hell, database servers LOVE lots of CPU, and provide better responsiveness and concurrency -- I can write DB queries which will saturate a 24 core machine for 20 minutes, in fact, I have on numerous occasions.

      A typical application can't really make use of more than 2-3 threads

      And even on my desktop I run 2-3 applications each of which can run several threads quire happily. Hell, my laptop and my desktop are both running at least one VM, and those VMs run faster when you can give them multiple cores. My weakling little 4 core laptop from work? I regularly peg the CPU load on that. And even 8 or 9 years ago I maintained application servers with 16 cores which still wasn't enough -- and we had 4 of them.

      Four cores is plenty, 8 is luxury that will mostly be idle. Anything over 8 is just nonsense on a typical desktop.

      Please, a 4 core machine has been around as a common thing for almost a decade, and it's all too easy to bog one of those down -- there's a reason it's considered entry level at this point. I had a quad core desktop back in '08, and my personal desktop is an 8 core machine. I could make use of more cores if I had them. And even if they're idle, modern CPUs just scale down their clock rate and voltage when not at max usage.

      You may run one thing at a time, and you may not load up 4 or even 8 cores, but for both professional work and personal stuff, hammering the hell out of a lot of CPU is something many of us do all of the time. Daily in fact.

      Being able to run a VM or two, compile something, have a couple of browsers open, ripping a CD while playing music, and running a couple of other things -- plus overhead for the OS, antivirus, and servicing network stuff. And that's just my personal machine.

      Few individual tasks will require this many threads, but multiple concurrent tasks can easily make use of this.

      CPU and RAM is something which is shockingly easy to use vast quantities of. I regularly find 16GB of RAM of 4 or even 8 cores isn't as much as I'd like to have.

      You may lack the imagination or the workload to hammer on this kind of stuff, but many of us could make use of it without even trying that hard. And there's always a market for more power in the same footprint.

      These aren't being marketed to people who don't do much. But for the people who need it, there's definitely a market. I fully expect my next machine to be a 16 core machine with 32GB of RAM, because the last few iterations have doubled both CPU and RAM as I go.

      My mom won't need one, but when the prices come down, even that AMD Threadripper is something I'm looking forward to.

  32. intel ripoff con artists by strstr · · Score: 1

    if you track Moore's Law, it hasn't been followed in ages. performance of chips used to double about every year. the "GHz" doubled, or equivalent suchs as instructions per second, transistor count, fill rate, bandwidth, core count, etc.

    This stopped along time ago. Around the year 2005, the first quad core process landed- transistor counts hit 1 billion. Then they sat at quad core and 1 billion transistors for ages, barely adjusting clock rates, making small under the hood tweaks that amounted to marginal performance boosts each year. After 10 years of quad core, and 1 billion transistor counts, the first 6-core hit the market, just a couple of years ago. But in reality, by 2006-2007, we should have had 8 core chips. And by 2008 we should have had 16 core chips. And by 2010 32 core chips, and so on. By 2011 64 chips. By 2013 we should have had 256 core chips. By 2016 we should have hit 1024 core chips. This is because technology at least doubles in capacity every 18 months or less. There's a hint here: someone, something, hindered the market, and stopped competing.

    Intel's first extreme edition processor was $1000 10 years ago or so. Now they have coffered up their first real performance chip upgrade in ages, they expect double that price. And trust me: $1000 was seen as unobtainable in price once. It's a monster of a price. $2000 certainly is double that. My argue is, since Moore's Law was abandoned years ago, and each new generation of chip barely improves upon the old, this new $2000 chip should really be $1000 at best. It's bringing the performance we should have been at 10 years ago to the table today basically, and thus is a rip off and outdated even before it hit the market.

    My understanding is capitalism is at work here. They're not competing or bringing new technology to the market, except for military applications.

    https://www.trumpsweapon.com/

    1. Re:intel ripoff con artists by Anonymous Coward · · Score: 0

      >if you track Moore's Law, it hasn't been followed in ages. performance of chips used to double about every year.

      This is not the Moore's law. The law is about transistor numbers (or density as here).

    2. Re:intel ripoff con artists by Anonymous Coward · · Score: 0

      Unfortunately you can't shrink things forever, at the bleeding edge they are literally counting transistor dimensions in atoms. Gate 50 atoms wide, uh-oh. And you can't increase clock rates forever, you do sort of need your data buses to be on the same clock cycle at both ends.
      Intel is known to purposefully allow AMD to catch up, i.e. sit on things a while or play with price until demand decreases, but they are not light years ahead and AMD is certainly not holding back with what it can do.

  33. Bang for Buck? by Anonymous Coward · · Score: 0

    != Intel

  34. Please compare this to the same price CPU from AMD by Anonymous Coward · · Score: 0

    EPYC-7551P is much closer to the price of this Intel offer at 2100$
    EPYC-7451 is 1700$

    Intel is not looking that good anymore...

  35. Intel needs a better name for their cpu by reboot246 · · Score: 1

    Am I the only one who is amused by the name Intel chose to name their CPUs? Core? Really? It has been a source of amusement since the first one they made.

    It just sounds silly to say 4 core Core i5 or 18 core Core i9. It's nearly as amusing as "https colon slash slash slash dot dot org".

    1. Re:Intel needs a better name for their cpu by Anonymous Coward · · Score: 0

      I'm still amused by "Core 2 Duo"

      "Core Solo" and "Core Duo" were quite fine as names, but when they upgraded to Conroe, it became Core 2...

  36. Re: Wow. $$$ by Anonymous Coward · · Score: 0

    Why the hell are you running iTunes? As a media player?? Really??

    Because I've owned iPods since around 2000 or so, and because say what you will about iTunes, there are simply things you can do with iTunes you can't do with any other player.

    That extra metadata iTunes keeps? It allows you to do things like making a playlist of "played less than 5 times or not played in the last 6 months". It lets you build playlists which are built on a series of AND and OR combinations. It actually gives you a lot of control over playlists that you can build with those complex rules, like a simplified SQL. It also lets each of my individual players (I own about 4 iPods of various generations plus I have an iPhone for work) track the playcounts and update those globally.

    So, who gives a fuck if you don't like it? The world isn't a one size fits all place. And like it or not, iTunes is simply capable of things I've yet to see another music player be capable of doing.

    The metadata that iTunes maintains is unlike any other player, because none of them have that. Me, I prefer to play the music in my collection I've not heard in some time, because I have about 60GB of music, all of which I like and want to hear.

    Windows Media Player is shit, and most of the OSS stuff are fairly basic and kludgy. And they utterly lack the benefits of the metadata database iTunes maintaines. For me, the stuff you can do with that metadata adds a tremendous amount of value to how I play music.

    Don't like it? Deal with it, not my problem.