Slashdot Mirror


Linux Kernel Patch Hints At At 32-Core Support For AMD Zen Chips

New submitter Iamthecheese points to an article which says that a patch published on the Linux Kernel Mailing List indicates that AMD's forthcoming Zen processors will have as many as 32 cores per socket, but notes that while the article's headline says "Confirms," "the article text doesn't bear that out." Still, he writes, There are hints of such from last year. A leaked patch for the 14 nanometer AMD Zeppelin (Family 17h, Model 00h) reveals support for up to 32 cores. Another blog says pretty much the same thing. We recently discussed an announced 4+8 core AMD chip, but nothing like this.

136 comments

  1. So what? by Anonymous Coward · · Score: 0

    Linux has supported SMP for a long time. I am expecting these AMD chips to run 32 cores under Linux by granted.

    1. Re:So what? by Anonymous Coward · · Score: 1

      This. The number of cores the system can use is even configurable.

    2. Re:So what? by Anonymous Coward · · Score: 5, Informative

      Linux already supports 32 cores very well, (Or 1024...) Still, driver support is needed for the details of adressing (up to) 32 cores on that particular architecture. Hence the patch. AMD may or may not turn out a 32-core chip in the near future - but at least their architecture supports that number of cores. Which is a bit interesting. If it turns out too hard to make, expect chips with 12-20 cores and gradually more as production quality ramps up.

    3. Re:So what? by cb88 · · Score: 1

      That and there is a good chance with that many cores there is a NUMA architecture... at some level.

    4. Re:So what? by Khyber · · Score: 1

      "Still, driver support is needed for the details of adressing (up to) 32 cores on that particular architecture."

      The details of x86-64 have been well known for more than a decade. The architecture hasn't changed.

      --
      Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
    5. Re:So what? by __aaclcg7560 · · Score: 1

      The architecture hasn't changed.

      Unless AMD pulls a fast one by presenting a 32-core processor with eight general processors and 20 graphic processors.

    6. Re:So what? by __aaclcg7560 · · Score: 1

      That's 12 general processors and 20 graphic processors. My skinny vanilla latte haven't kicked in today for me to do math this early in the morning.

    7. Re:So what? by Anonymous Coward · · Score: 0

      That and there is a good chance with that many cores there is a NUMA architecture... at some level.

      Let's hope not.

    8. Re:So what? by afidel · · Score: 3, Informative

      Intel's upcoming chips top out at 44 threads:
      SKU Name Cores/Threads Base Clock Boost Clock L3 Cache (LLC) TDP
      Intel Xeon E5-2699 V4 22/44 2.2 GHz ~3.6 GHz 55 MB 145 W

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    9. Re: So what? by Dresdenboy · · Score: 1

      That particular patch only tells us, that AMD might support up to 32C/64T per socket for the Zen family. 2P systems could theoretically support 64C/128T then. Of course this depends on the core size and power consumption.

    10. Re:So what? by Pseudonym · · Score: 2

      At the cache level, usually. I haven't checked, but I would hope that the Linux scheduler is smart enough to know that it's cheaper to migrate a thread between cores on the same die than between dies because the cache is likely to be warmer.

      --
      sub f{($f)=@_;print"$f(q{$f});";}f(q{sub f{($f)=@_;print"$f(q{$f});";}f});
    11. Re:So what? by Shirley+Marquez · · Score: 1

      We might see an actual 32 core chip. It will be an Opteron that is optimized for running large numbers of servers in a single box. The clock rate of the cores will be relatively low for thermal reasons and the chip will have no graphics processors.

    12. Re:So what? by stoatwblr · · Score: 1

      They haven't done this kind of chicanery with the APUs. It'd get them so much bad press that it's simply not worth it.

  2. Intel by Anonymous Coward · · Score: 0

    Intel will probably come out with a slightly faster 64 core chip just before AMD releases the Zen architecture...

    1. Re:Intel by qbast · · Score: 3, Insightful

      Zen is (according to AMD, so I guess it is optimistic) is supposed to bring 40% improvement in instructions per clock. That would put it around Sandy Bridge level. They would have to pull off 100% improvement to be competitive at high levels once again.

    2. Re:Intel by AmiMoJo · · Score: 4, Interesting

      AMD long ago gave up competing on raw CPU performance with Intel. They compete on price and integration. They have better on-board GPUs than Intel, and they cost less. The XBOne and PS4 both use AMD CPUs and GPUs.

      The question is if these markets are enough.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    3. Re:Intel by Anonymous Coward · · Score: 1

      The question is if these markets are enough.
       
      Yes.

      For people who simply don't care about specs the AMD will come in at the right price point. For people who do care about specs but are honest about what they're using their systems for it'll also likely be a no brainer.

      Aside from a few real power users the only people who care about maximum power are lunkheads who want to make teh 1337 b0xen for no other reason than bragging rights. No one else really pays for the high end processors.

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

      Yes and no... AMD had, a few years back, advertised that semicustom would be up to 20% of their revenue. Now it is a much, much larger percentage... Enough to keep going? Maybe, but this is not the AMD of yester-year. That much is clear.

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

      How about people who don't want their PC to be a space heater?
      Will they buy AMD?

    6. Re:Intel by Anonymous Coward · · Score: 1

      While that's true, AMD hasn't had a strong product launch since 2012. You can't just let the market go for 4 years and expect to be in business. They sold high end chips to complete with mid range intel and soon their chips only competed with core i3 CPUs. Without a major catch up effort, they're out of the x86 business.

      R&D matters.

    7. Re:Intel by Anonymous Coward · · Score: 1

      Yes. Especially those. You can get a decent CPU for everyday use, _and_ graphics that leaves Intels integrated offerings and quite a few discrete chips in the dust on a pretty damned decent power budget.

      Not saying you can't get better performance with a discrete cpu / gpu combo, but not in the same monetary/power budget space.

    8. Re:Intel by petermgreen · · Score: 0

      AMDs integrated graphics USED TO leave Intel's in the dust but these last few generations Intel has been working very hard to fix that and it seems with their latest generation they are suceeding.

      http://www.tomshardware.co.uk/...

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    9. Re:Intel by Khyber · · Score: 1

      "While that's true, AMD hasn't had a strong product launch since 2012."

      AMD hasn't NEEDED a strong product launch, considering the lack-luster performance of the mobile i5 versus an old as dirt Athlon II.

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

      Not really. Once you factor in heat and electricity, AMD doesn't look so good anymore. Plus the latest iGPU on intel CPUs readily beat AMD's "APU"s

    11. Re:Intel by KlomDark · · Score: 1

      Which is why I almost always buy AMD - Even if current Intel technology can beat it, I see it as an investment in the future. Keeps Intel on their toes having competition. If AMD dies, then Intel innovation slows WAY down.

      That would be awesome if Intel comes out with a 64 core chip just before AMD releases Zen, competition in action. If I truly needed 64 cores, then I would buy Intel, if not, then I will buy a cheaper 32 core AMD. Works perfectly for me.

      You've always got to think long term, life as it is now is guaranteed to change - do what you can to make sure it changes for the better.

    12. Re:Intel by Anonymous Coward · · Score: 0

      AMD long ago gave up competing on raw CPU performance with Intel. They compete on price and integration.

      The price/performance ratio of a chip is the real-world reference of performance.

      It doesn't make anyone any good if the chips that lead the raw performance category are always placed in a price range that falls outside of everyone's budget. When anyone has a budget, performance is measured in terms of the best performance that can be afforded.

      And in this category, AMD has been beating Intel for some years now, particularly in the AMD FX-83?? line.

    13. Re:Intel by Cid+Highwind · · Score: 2

      A mobile i5 from 2012, with half as many cores, running at half the clock speed, probably at half the voltage of the Athlon.

      You're benching Intel's 17 watt netbook CPU from 2012 versus AMD's 95 watt underdesk spaceheater from 2010, and think that's a good thing for AMD when they nearly tie?

      --
      0 1 - just my two bits
    14. Re:Intel by Anonymous Coward · · Score: 0

      The consoles went with AMD for supply chain reasons.

      No matter what the volume, Intel won't make custom SoCs for Microsoft and Sony on their terms. Intel also won't fork over a lot of IP and secret sauce so the chips can be second sourced.

      Microsoft learned a LOT about chip supplies when they made the Xbox (Intel cpu, Nvidia gpu). Same for Sony with the PS3 (Nvidia gpu) - Both ran in supply and IP issues with those respective companies.

      AMD, being generally in the shitter, has less to lose and so they were willing to supply IP and sign agreements to satisfy the console makers. Both Microsoft and Sony have the rights to fabricate their own processors if they desire.

    15. Re: Intel by Immerman · · Score: 2

      True. It seems that AMD learned their lesson when they held the performance crown - while they might be able to outcompete Intel on raw performance and affordability, they'll never be able to afford to compete against Intel's dirty tricks and anticompetive behavior. So instead they target the mainstream and console market, and let those who are actually interested in the price:performance ratio to come to them.

      --
      --- Most topics have many sides worth arguing, allow me to take one opposite you.
    16. Re:Intel by CrashNBrn · · Score: 1

      I hope it's enough. As is, it's almost impossible to find a decent AMD laptop. Your choices are HP, HP, HP, HP, sometimes Lenovo or Asus. Yet on Lenovo's own damned website they don't even offer|list the mid-to-higher-end machines you can buy with AMD. Lenovo lists 5 (3 models) and they are all low-end junk.

    17. Re:Intel by greenfruitsalad · · Score: 1

      well, amd is almost dead and intel's innovation has slowed down to a crawl. apart from new instructions, there is almost no reason to upgrade a processor bought in the last 4-5 years. you simply don't gain much.

      for me, the magic trigger words are "hardware accelerated hevc/vp9 encoding". if a cpu that allows for real time 4k hevc/vp9 encoding comes out, i'll switch immediately. otherwise, i'll stay with my current cpu for a good few more years.

    18. Re:Intel by unixisc · · Score: 1

      Is Intel planning any ARM chips? I doubt they've done that since they sold off XScale to Marvel

    19. Re:Intel by citizenr · · Score: 1

      x4 640 is a mobile ultra low power 17W cpu?

      --
      Who logs in to gdm? Not I, said the duck.
    20. Re:Intel by Anonymous Coward · · Score: 0

      Linking to "benchmarks", and Tomshardware. LOL.
      Wanna bet all those "benchmarks" are 1. compiled with ICC, which is known to cheat with AMD hardware and 2.very thoroughly optimized to work well with Intel hardware and "not so much" with AMD? Besides, knowing "Tomshardware" - no I'm not going to waste any time on them - they probably misconfigured the AMD systems too, just to make sure.

      And then there was this little issue of cost too. I guess you kind of forgot that in your haste. LOL.

    21. Re:Intel by Anonymous Coward · · Score: 0

      Bullshit. But it's good to know you think selective, rigged "benchmarks" can substitute using your own senses. I guess that would make you a good candidate for the first prosthetic brain implant. Not much to lose.

    22. Re:Intel by greenfruitsalad · · Score: 1

      is power in your country free? fx-83xx needs roughly twice as much of it as comparably priced (and 15-20% less powerful) i5-46xx.

    23. Re: Intel by Anonymous Coward · · Score: 0

      Your post makes no sense. First you state they use ICC as a way to make AMD seem faster. Then in the next sentence you say they use tricks to make Intel seem faster. While also misconfiguring the AMD system to make it seem slower.

      Which one is it? Your rant is worthless as it stands. If you don't like toms results, then fork that bitch.

    24. Re: Intel by Anonymous Coward · · Score: 0

      You call bullshit but never back it up and say why it is bullshit. The OP wins this round. Are you a shill or worthless? Which one is it? You tell us. You could be both, they aren't mutually exclusive.

    25. Re:Intel by Anonymous Coward · · Score: 0

      Netbooks are more like 2-8 watts by my count. 17 watts is a cpu for a full-size laptop.

      Though I guess our definition of 'netbook' may differ.

    26. Re: Intel by Anonymous Coward · · Score: 0

      No, what makes no sense is you, and your ignorance. The entire premise that ICC would cheat to make AMD look better, shows that you don't have any clue whatsoever what "ICC" is and that you have forgotten that sabotaging your competitors is "cheating" too. Which makes this discussion pointless, since if you don't know that, well... It kind of makes your opinions on "benchmarking" worthless.

      FTR, here is a good starting point just in case you actually care to find out. He makes a pretty good job at explaining it, and you can read more about it in other places in case you don't trust "some blog".

    27. Re:Intel by Cid+Highwind · · Score: 1

      You're right. Notebook, not netbook.

      Still it's a long way from benchmarking AMD's enthusiast desktop chip versus Intel's enthusiast desktop chip.

      --
      0 1 - just my two bits
    28. Re:Intel by sexconker · · Score: 1

      The problem is that the hardware encoders all produce shitty fucking results compared to the software encoders. Yes, they're much faster, but so what? The only purpose for fast encoding is for real time streams. 99% of the people interested in that are gamers, and both AMD and nVidia offer live encoding shit with EZ-PZ integration for the popular streaming services.

      As a gamer (who doesn't stream), I'd use my real GPU. If I was worried about losing a small fraction of gaming performance, I'd split my outputs to a separate box entirely.
      As someone who rips and encodes his blurays, I simply throw it at x264 with the ultra slow preset and my desired bitrate and let it run. It finishes when it finishes.

    29. Re: Intel by Anonymous Coward · · Score: 0

      Pretty sure he meant "Intel faster" not "amd".

    30. Re: Intel by Anonymous Coward · · Score: 0

      No, as I said above, "cheating" was meant to be read as "making AMD slower than they really are", i.e stabbing your competitor in the back off stage where you have to have a "backstage pass" to see it.

      It's a slick move: Intel can feign innocence effectively enough to fool some particularly susceptible individuals, "we are just making sure the generated code is 'compatible'". The guy who does the deed, i.e the programmer using the compiler presumably never looks at or is in many cases not even competent enough to interpret the assembly output from the compiler - and then, as the proverbial cherry on top of it, comes the long tail of "benchmarkers". We all know who these are, they rarely have any clue whatsoever apart from how to start sisoft sandra, much less about what they are actually measuring but "Intel wins, herpa derp, I can benchmark!".

      In reality practically *none* of them could tell with any degree of certainty whether they were measuring how effectively the Intel C/C++ Compiler was sabotaging the AMD system they were running the code on, or if they were measuring how well the programmer had used every trick in the book to make the code run optimally on an Intel CPU and hides its failings, or if he - yes, Intel does have economic interests in those who produces these various kinds of "benchmark software" - did the same but to make sure the test bombs on an AMD etc, etc. And that's discounting deliberate dishonesty on the account of the one running the benchmark, which isn't exactly uncommon.

        It also IMO says something about how much faith Intel have in their own products when they have to resort to tactics like this.

    31. Re: Intel by Anonymous Coward · · Score: 0

      lol why should I spoon feed you? The truth is out there, all you need is a brain and google. Just start googling for intel, compiler benchmark and cheating.

    32. Re:Intel by armanox · · Score: 1

      I try to buy AMD for that reason too - I dread to see a market without them. My guest desktop at home is running an AMD FX 8120 (with a GTX 580, SSD, and 16GB RAM) and it's good enough for when people use it. Other times it just runs BOINC.

      --
      I'm starting to think GNU is the problem with "GNU/Linux" these days.
  3. Obligatory XKCD by Anonymous Coward · · Score: 5, Funny

    https://xkcd.com/619/

    1. Re:Obligatory XKCD by Anonymous Coward · · Score: 4, Funny

      I am afraid that this is more appropriate: http://i.imgur.com/GDyOS.png

    2. Re:Obligatory XKCD by cfalcon · · Score: 1

      Man the axis labels really make that lol

  4. Cores Schmores by AbRASiON · · Score: 1, Insightful

    AMD best hope this CPU has some actual guts to it for performance / power efficiency. They haven't had a great CPU since the Duron / Thunderbird days when they were (arguably) the leader on the desktop.

    Their CPU's have gotten progressively worse compared to intel, to a point where it's pretty much complete folly to go AMD at this point, which is a big shame.

    Let's hope they close the gap significantly, very significantly. They've almost always been behind, even if it's only slightly (yet had to hugely undercut prices)
    At their current rate, I do not see them lasting a hell of a lot longer. So this one better be the one for a couple of years.

    1. Re:Cores Schmores by Anonymous Coward · · Score: 1

      Intel won't let AMD die. They don't want the scrutiny of being the sole CPU supplier for the whole desktop, laptop, server (most at least) markets.
      Intel already paid AMD quite some bucks a few years ago after admitting wrongdoing. Before killing AMD, they'll beg them to be sued for another infringement (there are plenty of ways in which Intel has not being fair) to have legal cover to fund AMD.
      For high end server market, IBM gear is still doing quite well, and some Power8 iron is reasonably priced. The advantage for some people is that it also runs in little-endian, something I shall never understand (I think, live, and breathe in big endian; for me, bit 0 is and can only be the most significant bit of any entity, period).
      However I'm more interested in Power9 with hardware support for 128 bit floating point in IEEE format for some scientific computations, there are case where double precision dos not cut it (subtle effects of general relativity, among others). It won't be very fast, but the mainframes already support it so I suspect that they will have similar latencies which, while not low, are decent for the complexity of the instruction (see http://arith22.gforge.inria.fr/slides/s1-schwarz.pdf, page 25).
      Power9 adds fuse multiply-add to improve performance and precision. However Power9 is for next year (which quarter I don't know), but as a scientist I can make a strong case for buying a server or 2 based on hardware quad precision floating point support helping a lot for some projects

    2. Re:Cores Schmores by qbast · · Score: 1, Insightful

      They are not going to - even AMD's optimistic estimates talk about 40% improvement. This is way too little to close the performance gap. At best they can match top speed Intel CPUs from ~2011 (late Sandy Bridge).

    3. Re:Cores Schmores by GeekWithAKnife · · Score: 3, Interesting


      Quite wrong about AMD CPUs getting progressively worse.

      Intel has outpaced AMD their process technology is more sdvanced allowing them to do magical things like significantly increase performance AND reduce power at the same time...

      This also has something to do with Intel's past blocking of AMD products when the K7 Thunderbird was kicking ass. Year later cash strapped AMD agreed to settle the matter to the tune of $2 billion. I'm sure if they had a bit more time and money they could have gotten more.

      Now, unsurprisingly Intel's advantage is only this much and not more, most likely because Intel needs AMD to exist. It's a great way to compare and handy not to be declared a monopoly.

      So AMD has been improving, albeit at a slower pace than Intel. They can still compete but need to change the approach to fight where they can shine and profit rather than everywhere Intel goes.

      --
      A 'singular oddity' is an event that cannot be explained and only happens when you are alone.
    4. Re:Cores Schmores by TeknoHog · · Score: 1

      Intel won't let AMD die.

      Nope, but they can *puts on sunglasses* chip it away little by little.

      --
      Escher was the first MC and Giger invented the HR department.
    5. Re:Cores Schmores by TeknoHog · · Score: 3, Interesting

      AMD best hope this CPU has some actual guts to it for performance / power efficiency.

      Perhaps cores-schmores is one way to approach this? Lots of small cores with relatively slow clocks, as higher clocks tend to worsen power efficiency. I'm not discounting Intel's success with single-core performance per se, but I sometimes feel it's aimed at speeding up legacy applications, while those with modern OSes and code are happy with the cheaper multicore offerings from AMD.

      --
      Escher was the first MC and Giger invented the HR department.
    6. Re:Cores Schmores by beheaderaswp · · Score: 1

      I'm a little more optimistic.. AMD is due, And they have new process.

      This summer is going to be an exciting time in processors.

      --
      Another consultant who stuck it out.

      "We are the Priests, of the Temples of Syrinx..."
    7. Re:Cores Schmores by mwvdlee · · Score: 2

      Sadly, the vast majority of applications people use in their daily ARE "legacy" applications.

      --
      Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
    8. Re:Cores Schmores by Anonymous Coward · · Score: 0

      32x more heat, 32x more power consumption, sucky performance. 32x more fail for amd.

    9. Re:Cores Schmores by TheRaven64 · · Score: 3, Informative

      The Thunderbird was nice, but it was more of a price/performance winner than overall performance. A 1GHz Thunderbird ran stable at 1.3GHz and was similar performance to a 2GHz Pentium 4 at a fraction of the cost (particularly as the P4 required RAMBUS DRAM, so you could stick twice as much DDR in Athlon for the same money). It wasn't until the Opteron that AMD really started winning on performance. The integrated DRAM controller was a big win and being first to 64 bits (which, on x86, means more GPRs, sane floating point ISA, and PC-relative addressing) gave them a huge advantage. Unfortunately, they haven't really been competitive since the Core 2, except in market segments where Intel intentionally cripples their offerings (e.g. no more than 2 SATA ports on the Atom Mini-ITX boards to avoid competition with the i3 boards, making AMD the only viable option).

      --
      I am TheRaven on Soylent News
    10. Re:Cores Schmores by Anonymous Coward · · Score: 0, Troll

      One way to achieve better power efficiency is to consider to not have all cores 64-bit but actually run some 32-bit. Most applications today are still 32-bit and running such an application on 64 bit is a bit waste.

    11. Re:Cores Schmores by Anonymous Coward · · Score: 0

      There are even DOS applications still in use these days. No joke.

    12. Re:Cores Schmores by qbast · · Score: 3, Insightful

      You are more optimistic than AMD's marketing department? That's some impressive optimism.

    13. Re:Cores Schmores by Anonymous Coward · · Score: 0

      AMD isn't the one to watch out for. I'd be concerned with Atmel/Microchip.
      They can deliver ARM chips that are on-par with Intel on performance/watt.

      ARM laptops - Linus-approved.

    14. Re: Cores Schmores by Anonymous Coward · · Score: 1

      If it's only a bit of waste with 64bit cores, the most optimal solution would be to go with 63bit cores.

    15. Re:Cores Schmores by Anonymous Coward · · Score: 0

      They haven't had a great CPU since the Duron / Thunderbird days when they were (arguably) the leader on the desktop.

      They haven't?

      Athlon 64 chips 2004-2005 smoked intels pentium 4 offerings
      Athlon 64 X2 (first native dual cores for desktop btw) 2004-2007 were the best available on the desktop
      Phenom 2 2008-2011 were neck and neck with core 2 quad offerings

    16. Re:Cores Schmores by Anonymous Coward · · Score: 0

      So that is why they outperformed every single p4 then even when you compared them both overclocked...
      So how exactly did they not have the best performance at the time?

    17. Re:Cores Schmores by Anonymous Coward · · Score: 0

      the marketing department is all that's left at AMD...

    18. Re:Cores Schmores by petermgreen · · Score: 1

      The advantage for some people is that it also runs in little-endian,

      Well x86 is little endian too, so that's more of a non-disadvantage than an advantage. Being big endian in a little endian world was a major disadvantage.

      something I shall never understand

      If you have a big codebase that has only ever been run on little endian platforms it very likely will have issues when running on big endian platforms. Rooting out and fixing these issues will often be a non trivial task. Since Intel and little endian arm are the readilly accessible platforms today a lot more code gets written with little endian assumptions than big endian ones.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    19. Re:Cores Schmores by StayFrosty · · Score: 1

      Really? Netburst was a total fail for Intel. Especially in the later years of the architecture. The Athlon 64 and Athlon64 X2 were way more efficient and could more than hold their own. This is what forced Intel to abandon Netburst and release the Core series CPUs. Sadly, AMD hasn't really been able to keep up since.

      --
      "Frequently wrong, never in doubt."
    20. Re:Cores Schmores by serviscope_minor · · Score: 1

      You are more optimistic than AMD's marketing department? That's some impressive optimism.

      Ehhh... I use mostly FOSS stuff. Funnily enough AMD does *Much* better on open benchmarks than it does on closed ones. Their already decent performance along with the new improvements does make me optimistic.

      --
      SJW n. One who posts facts.
    21. Re:Cores Schmores by flatulus · · Score: 1

      You can blame Little Endian on Datapoint

      Bet you have no idea what I'm talking about, right?

    22. Re: Cores Schmores by KlomDark · · Score: 1

      Haha! I LOLd

    23. Re:Cores Schmores by AmiMoJo · · Score: 1

      It really depends on the workload. 32 cores will outperform some high end Intel stuff on workloads that saturate them, I'm sure. AMD is also pushing memory bandwidth up, so it really looks like they are betting on having lots and lots of cheap cores and tonnes of memory bandwidth and everyone decides to write their software to take advantage of it.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    24. Re:Cores Schmores by AmiMoJo · · Score: 1

      Sure, but they run more than fast enough on modern CPUs. That's really been AMD's saving grace - you might as well save a few quid on a slower AMD CPU if all you are going to do with it is run Word.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    25. Re:Cores Schmores by AF_Cheddar_Head · · Score: 1

      DataPoint 2200 and the Intel 4004?

    26. Re: Cores Schmores by Anonymous Coward · · Score: 0

      Written in COBOL. The future is now.

    27. Re:Cores Schmores by KGIII · · Score: 2

      Other than my fairly new laptop, most of what I buy is AMD and I can easily afford the Intel offerings. Though, I usually go with nVidia GPUs when I'm making that choice and not just buying the whole system. I get more than adequate performance for everything I do, at a fine price, and I get to support AMD by doing so. I do buy some Intel products, I'm not some sort of zealot - I don't think. I'm just quite content with AMD and have had good luck with them since I tried my first one back at the K6-II time.

      The difference? Well, my laptop is really a mobile workstation and I could probably have bought 5-6 fairly acceptable laptops for what I paid for this. It's nice and I liked it, so I bought it. It's stupidly expensive, however. (Over $5500 before shipping.) So, I think there's a time and place for Intel - it's just that I really don't normally even notice much of, if any, difference in performance anymore. In case you're curious, it's a Titan X4K and yes, yes it is just what I was looking for.

      --
      "So long and thanks for all the fish."
    28. Re:Cores Schmores by BlueCoder · · Score: 2

      I think the solution for the new PC is going to be a combination of both. 4 fast as possible cores; maybe 8. Then massive additional cores at lower clock speeds and simpler design. Most likely implies a hybrid NUMA design with additional performance specs and turntables for the host OS and user level software(games). Probably a few modes of operating. Automatic management and succeeding levels of the OS taking over management.

      Think of the slower processors as something akin to a floating point coprocessor. Programmers are lazy. Until the hardware exists and they know they will see a benefit they don't want to program for it. Programming for massive unknown hyperthreading is a hard topic. They will always choose the lowest common denominator.

      But having both fast/few and slow/many/efficient changes the game. The fast/few is at the end of it's performance curve life but will live on. It's nice to have a few cores around that run two to three times faster for difficult programs. But having an undetermined number of extra processors sitting around.... programmers won't be able to control themselves when they want more performance.

      I can also imagine this extending to mixed architectures such as x86+Arm like we have heard rumors about. CISC+RISC in the same computer; blasphemy. FPGA compute boards and graphics card becoming coprocessors and integrating on a more equal level with the CPU's.

      P.S. The future of operating systems is a three tiered approach: Hypervisor->OS->Programs. The hypervisor being something akin to a microkernel. What if instead of building compatibility into successive operating systems you could run them all together and forget about compatibility altogether. With additional software and drivers I can even see compositing. This means we can run FreeBSD, Redhat Linux, Ubuntu, Gentoo, Arch, DOS, Windows 3.1, Windows XP, Windows 7, Windows 8, Windows 10, and GNU Hurd, and multiple x86 and Arm versions of Android all on the same machine. Imagine all those with compositing extensions.... And once you get rid of the browser with Flash and Shockwave 99% of viruses disappear so administration actually gets easier and if you do get a virus you can always rollback; or rollout clones to test software. Also one can setup a file system with features like file versioning and encryption so that programs can't just hijack your data.

      The reason I brought up the above is because one can further still extend the hardware with a clustering OS. A business could install such a specialized clustering OS on each of it's desktop machines in the building and then have it's own cloud. Imagine using something like that for rendering and processing video.

    29. Re:Cores Schmores by afidel · · Score: 1

      x64 actually runs x86 code more efficiently than classic x86 due to the large number of registers available for renaming on x64 which is why you can see significant improvements switching from the x86 to the x64 build of any of the MS OS's on exactly the same hardware with exactly the same applications (no recompile needed). The only thing you give up is a bit of storage (on the OS side) and a bit of ram so it won't work for $200 tablets but for anything with reasonable specs it makes sense.

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

      ... But do they run Dwarf Fortress?

    31. Re:Cores Schmores by AbRASiON · · Score: 1

      So basically your reply is "semantics"?

      Of course AMD aren't getting progressively fucking worse for goodness sakes, who releases a CPU that's slower than the previous.
      They are getting worse /compared to the competition/ hence my post. They are less and less competitive.

      I shouldn't need to spell this out on /.

    32. Re:Cores Schmores by Anonymous Coward · · Score: 0

      Reading comprehension fail.

    33. Re:Cores Schmores by flatulus · · Score: 1

      We have a winner! Good job.

    34. Re:Cores Schmores by TheRaven64 · · Score: 1

      They didn't, the fastest P4 Xeon outperformed the fastest Athlons, but for any given Athlon the equivalent speed P4 was a lot more expensive. Once the Opterons came out, that changed: if you wanted the fastest x86 chip you could buy, you bought from AMD, especially in multi-socket configurations (quad-processor Opterons wiped the floor with memory-starved quad Xeons until Intel integrated the memory controller on die). Worse (for Intel), if you were willing to recompile your code you could get another 20+% out of the Opterons using the x86-64 ISA (more GPRs and cheaper PIC made a big difference, and a floating point ABI that used SSE exclusively and not x87 could give you a 100% speedup in float-heavy code, where even if the x86-32 compiler was using SSE registers for compute it was still losing performance moving them to and from the x87 register stack for function calls / returns).

      --
      I am TheRaven on Soylent News
    35. Re:Cores Schmores by Shirley+Marquez · · Score: 1

      I'd give the credit or blame for little endian to the PDP-11, not to Datapoint. The 11 shipped a year before the Datapoint 2200, and it was very popular (notably being the first platform on which Unix was widely used) so it's probably far more influential.

    36. Re:Cores Schmores by Shirley+Marquez · · Score: 1

      I think a big part of that is the compilers. Open benchmarks are mostly compiled with GCC which has optimization that is well tuned for AMD processors, especially if you are compiling 64 bit code. Closed benchmarks are likely to be compiled with either Visual Studio (not great for AMD) or ICC (downright terrible for AMD), except for Mac benchmarks which are usually compiled with LLVM/Clang.

    37. Re:Cores Schmores by serviscope_minor · · Score: 1

      ICC isn't just terrible, it's blatantly fixed. They used to detect not the instruction set, but the processor ID and so disable the fast code paths on AMD processors even though the fast code paths run fine and well.

      There was an article a while back about how changing the cpuid made the code much faster. It's another of Intel's dirty tricks.

      --
      SJW n. One who posts facts.
  5. holy licensing fees, batman.. by Anonymous Coward · · Score: 0

    those per-core software licensing fees better finally die off.

  6. Re:Wake me up when there's a patch by sumdumass · · Score: 2

    I hear that rm -rf has some success with that. I'm not sure though as I don't care much for the argument.

  7. Kilocore by Anonymous Coward · · Score: 0

    Long time ago, when I saw my first dual-core machine, I predicted that I will see a kilo-core machine in my lifetime. That prediction still stands, and the step from 16 to 64 is just one little step on the way.

    1. Re:Kilocore by AC-x · · Score: 2

      I predicted that I will see a kilo-core machine in my lifetime.

      Do GPU shader cores count?

    2. Re:Kilocore by thinkwaitfast · · Score: 3, Interesting
      There used to be a company called rapaport I believe who were developing a chip called the Kilocore. The point was that if you were decoding images, 1024 slower cores would be as fast, yet significantly less energy hungry than one core 1024x faster.

      CMOS technology, is static meaning that there is no current flow through a gate when it is on or off. Current only flows while the transistor is transitioning states. P = I x V and as I (current) increases, so does power. All 'digital' circuits are actually analog and you can show that I is proportional to frequency squared. Instead of having a power (^) increase in energy use, you have a linear relation.

    3. Re:Kilocore by thinkwaitfast · · Score: 1
      Edit: Actually Rapport. https://en.wikipedia.org/wiki/...

      It appears to be dead, but a very interesting technology.

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

      Kilocore single system image NUMA machines have existed for well over a decade.

    5. Re:Kilocore by erice · · Score: 1

      CMOS technology, is static meaning that there is no current flow through a gate when it is on or off. Current only flows while the transistor is transitioning states.

      That's the idea but it has never quite worked that way. There is always a small current flow from vdd to ground even when the gate is "off". At smaller geometries, this leakage becomes not just significant but can be the majority of the power drain. Thus, having lots of cores ready but not active does not help. They still suck power. Finfets help a great deal but only for a while and at 14nm and below the problem is coming back. The work around is to actually turn off the power to inactive regions. This works but shutting down and restarting units is complicated and time consuming, making it more difficult to respond to transient demands.

  8. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    What the hell are you blathering. :D

  9. Re: Wake me up when there's a patch by Anonymous Coward · · Score: 0

    Who said anything about going back? I'm just waiting for the next big thing that will replace the curse that SystemD is.

    It could be worse, but it could also be better, and considering the current situation it only matters that it won't be SystemD.

    Also, you want to use Unix but hate shell scripts? Maybe you should look for another distro.

  10. at at at? by Anonymous Coward · · Score: 0

    at at at

  11. Re:Wake me up when there's a patch by Anonymous Coward · · Score: 0

    I recommend looking into cryogenics.

  12. Re:Yes, Sys V. by Anonymous Coward · · Score: 1

    Look, MikeeUSA:

    I don't like systemd. I even go to some lengths to have a Debian running without. But every time I see your dirty drivel, I feel the urge of embracing systemd [1] [2] [3], just to avoid being associated with you.

    One could get the impression that you are a pro-systemd false-flag operation except... I think you're just an idiot. One way or the other, I won't give up my stance just because of you.

    [1] https://twitter.com/zacchiro/s...
    [2] http://etbe.coker.com.au/2015/...
    [3] https://identi.ca/cwebber/note...

  13. power of 2 by ssam · · Score: 2

    If the previous max cores per socket was 16, and the value in the kernel needs to be a power of 2, then at most this tells us that they have a 17 (more likely 18 or 20) core CPU on the way.

    1. Re:power of 2 by Anonymous Coward · · Score: 0

      Athlon II X3 is triple-core and Linux works fine on that, there is no power-of-two limitation.

    2. Re:power of 2 by ssam · · Score: 1

      Sorry I was not clear enough. The kernel value for max number of cores must be a power of 2. So to use that triple-core CPU the kernel would actually need to support up to 4 cores. So if AMD plans to release a 20-core, they can't just bump the number in the kernel to 20, they have to increase it to 32.

  14. Re: Wake me up when there's a patch by Anonymous Coward · · Score: 0

    True but with SystemD you can have 32 AMD Zen cores, and with *BSD less than half of that.

    This feature alone is worth making the compromise.

  15. Re:It is botnetted. (Remote control) by Anonymous Coward · · Score: 0

    I can't even...

  16. Re:It is botnetted. (Remote control) by Anonymous Coward · · Score: 0

    Oh, no. Forgot to take your meds?

  17. Cores or 'cores'? by Junta · · Score: 1

    AMD's dual-core, partially shared, but partially independent has been a confusing thing. Better than hypethreading, but worse than real cores, claiming performance of real cores.

    Note for all those desktop enthusiasts out there, don't get too excited. To look at Intel as an example, they go up to 4 cores per desktop socket, but go to 18 cores per socket in servers (at 150W per socket) as of this moment (can't talk about unreleased product). AMD does 8 'core' desktop processors (4 modules) and 16 'core' opteron (really 8 modules), so it's not just an Intel thing.

    --
    XML is like violence. If it doesn't solve the problem, use more.
    1. Re:Cores or 'cores'? by Anonymous Coward · · Score: 1

      AMD fake core technology (as I like to call it), isn't that confusing.

      You do get integer cores, but not floating point. 1 float per module, 2 integer units. It's really that simple. Depending on what you're doing with your PC, it can be a big problem or a very small one. Many people like to offload onto GPUs now anyway for the other case.

    2. Re:Cores or 'cores'? by tangent3 · · Score: 1

      There are 2 floating cores per module. However, the 2 cores will be combined into one if operating on 256bit AVX instructions

    3. Re:Cores or 'cores'? by Anonymous Coward · · Score: 0

      I recently found out that a pipeline stall in one AMD "core" causes the other core to also stall. They're much more coupled than I thought.

  18. Re: Wake me up when there's a patch by Anonymous Coward · · Score: 0

    I recommend that you do the same, but instead of making sweaters you should learn something useful like the fundamentals of the shell, because Unix and scripting go hand in hand.

    On the other hand, Microsoft will be always there for your kind.

  19. Re: Wake me up when there's a patch by Anonymous Coward · · Score: 0

    Citation? Even Windows 7 32 bit supports 32 cores, and there are 16+ core CPUs to test that.

  20. wonder if it's a big LITTLE architecture? by elwinc · · Score: 1

    From what I've read about AMD's Zen architecture, they've dispensed with the "two single threaded cores per module" architecture and now have SMT allowing two threads in each core according to this, much like "hyper threading" on Intel chips.

    If that's the case, and we can expect a 32 core chip to execute 64 threads, then that's an awful lot of threads to keep supplied with data and instructions. In comparison, the biggest Intel Xeon I know about, the E5-2699 v3 has 18 cores, 36 threads, 45MB of last level cache, and 4 memory channels (68GB/sec to RAM). Intel sticks pretty close to that 1.25MB cache per core in their big Xeons. So if you adhered to Intel's apparent rules, a 32 core 64 thread chip would need 80MB of LLC and maybe 6 memory channels. Anandtech estimates 5.7 billion transistors for the big Xeon. Scaling the Intel design from 18 to 32 cores would require over 10 billion transistors! That number leads me to believe that an SMT 32 core 64 thread chip built with 2016 technology would not be practical.

    What might be practical is a chip with some "heavy" cores optimized for balls-to-the-wall floating point execution, and other "lighter" cores for lower power integer tasks. This has been done in "octocore" mobile phone chips and called a big LITTLE architecture. The idea is that the OS and various decoding and checksumming tasks can stay resident on the low power light cores, while the heavy cores do things like game physics and photo noise reduction. Because the multiprocessing is not symmetric, the OS kernel needs special rules to assign tasks to cores. Which leads me to wonder if AMD has something like big LITTLE up its sleeve for 32 core Zens.

    --
    --- Often in error; never in doubt!
    1. Re:wonder if it's a big LITTLE architecture? by afidel · · Score: 1

      SKU Name Cores/Threads Base Clock Boost Clock L3 Cache (LLC) TDP
      Intel Xeon E5-2699 V4 22/44 2.2 GHz ~3.6 GHz 55 MB 145W

      So Intel is keeping 1.25MB of L3 per thread for the next generation. Memory is the same at 4x DDR4 though AFAIK speeds will be upped.

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

    Pro-systemders are usually SJWs who oppose men marrying female children.

    >In the United States, as late as the 1880s most States set the minimum age at 10-12, (in Delaware it was 7 in 1895).[8] Inspired by the "Maiden Tribute" female reformers in the US initiated their own campaign[9] which petitioned legislators to raise the legal minimum age to at least 16, with the ultimate goal to raise the age to 18. The campaign was successful, with almost all states raising the minimum age to 16-18 years by 1920.

    >Also: see: Deuteronomy chapter 22 verses 28-29, hebrew allows men to rape girl children and keep them: thus man + girl is obviously fine. Feminists are commanded to be killed as anyone enticing others to follow another ruler/judge/god is to be killed as-per Deuteronomy. It is wonderful when this happens from time to time: celebrate)

  22. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    Here, have a cookie, some libre vidya:
    www.lgdb.org/game/chaosesque-anthology

  23. AMD Strategy hasn't changed by Anonymous Coward · · Score: 0

    http://oi62.tinypic.com/6g8uc9.jpg

  24. Intel Cores Schmores by DrYak · · Score: 1

    Perhaps cores-schmores is one way to approach this? Lots of small cores with relatively slow clocks, as higher clocks tend to worsen power efficiency.

    Which is also the road that Intel themselves pursue with Xeon Phi (the currently used descendant of their failed GPU).

    I'm not discounting Intel's success with single-core performance per se, but I sometimes feel it's aimed at speeding up legacy applications

    Yup, the drawback is that not a lot of current application are able to run on tons of separate threads.
    Not only "legacy" but even applications recently produced or currently being produced.
    But the architecture can have some success on servers, and some scientific workloads.

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
  25. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    Actually, SJWs are quite pro-pedo now, doing all those "pedos are people oppressed by their own sexuality" articles after a certain big voice of the movement got outed out as one.
    But you're obviously just a shitposter so...

    Also this whole "SJW is everyone that i dislike" is quite harmful and stupid.
    They're a very specific group of nutjobs with a very specific agenda and methods, generally being easy to spot due either being neckbearded men with a massive "white guilt" or women with dyed hair and "problem glasses", generally tying to enforce insane and illogical PC things.

  26. Re:Yes, Sys V. by qbast · · Score: 1

    This discussion *really* took a weird turn. How the fuck do you get from config.sys to pedos?

  27. Re:Wake me up when there's a patch by Stewie241 · · Score: 1

    Those were *my* config.sys and autoexec.bat files, you insensitive clod!

  28. Complete bullshit by Anonymous Coward · · Score: 2, Interesting

    This is like looking at a hardware register in a generic register layout that leaves 8 bits for "core index" and deducing that the manufacturer must be intending on delivering a 256-core CPU.

    Then you find the documentation for the specific family and find out that bits 7-3 are "reserved and will be read as zero".

    But the driver patch they submitted doesn't make that assumption "just in case".

    Because it's easier to plan ahead in the driver than it is to actually deliver a 256-core CPU.

  29. I'm confused by jones_supa · · Score: 1

    Why does the article call it "leaked patch"? That seems like a normal public patch to Linux Kernel Mailing List.

    Also when I read the source code, I do not see anything suggesting 32 cores, and instead the patch adds support for an "instructions retired" register which is introduced in the Zeppelin architecture.

    So is the article rubbish or am I rubbish? Once again I get the feeling that by even just slightly scraping the surface, things turn out to be completely different than what is described. :D

    1. Re:I'm confused by Anonymous Coward · · Score: 0

      heh, it's not you. It's Slashdot. Slashdot has become a tabloid.

  30. Re:Yes, Sys V. by jbengt · · Score: 1

    No, the prevailing view is that the translation of the Hebrew should be closer to "If a man find a lady who is a virgin, who is not pledged to be married, and lay hold on her, and lies with her, and they be found" rather than "and rapes her" (It's two words in Hebrew, and different words, like those for "seized" or "forced" would more likely be used to describe rape).
    Context also suggests that the intent was for a case where the woman was willing or seduced.
    Also, Exodus 22:16-17 says almost the same thing, including the same punishment of requiring the paying of a bride-price and forcing the man to marry the woman, but uses a word translated as "entices" or "seduces" rather than "lays hold of".

  31. Re:Wake me up when there's a patch by jedidiah · · Score: 1

    > So you want to go back to shell scripts? A system in the style of your father's CONFIG.SYS and AUTOEXEC.BAT is what you want?

    That presupposes that a DOS batch file is anything like a Unix shell script. All you've really done is demonstrate how utterly clueless you are about either of the things you're whining about.

    People who have no clue, should be in no position to force anyone else to "abandon the past". They simply aren't qualified to judge. This is the fundemental problem with the SystemD crowd. They are idiots distracted by shiny objects.

    --
    A Pirate and a Puritan look the same on a balance sheet.
  32. Re:Yes, Sys V. by AF_Cheddar_Head · · Score: 1

    Welcome to Slashdot.

  33. All that's old is new again by Anonymous Coward · · Score: 0

    Newisys was working with AMD to create cache-coherent processor images of up to 128 cores (32 sockets at the time) back in 2007 with the Hypertransport connected Opterons.

  34. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    Did you seriously just get triggered by someone referring to config.sys and autoexec.bat, reasonably non-scalable solutions to startup issues that were only ever side-cribs from the Unix side of things and doomed to replacement, as being the $CURRENT_YEAR argument, and then just start unironically demanding lolis be delivered to your door? I can't even tell you /pol is that way, because you'd be btfo even by straight up Nazis. I don't know where to tell you to go.

  35. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    We have a recent rash of trolls that seem to talk about Republicans, or Democrats, or SJWs. I'm actually hoping its three edgelords in an honors dorm somewhere.

  36. Re:Yes, Sys V. by Anonymous Coward · · Score: 0

    This is Slashdot. We don't tolerate facts and evidence around here.