Catch up on stories from the past week (and beyond) at the Slashdot story archive


Forgot your password?
AMD Upgrades Hardware Linux

Linux Kernel Patch Hints At At 32-Core Support For AMD Zen Chips 136

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.
This discussion has been archived. No new comments can be posted.

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

Comments Filter:
  • by Anonymous Coward on Monday February 08, 2016 @06:24AM (#51461177)

  • Cores Schmores (Score:2, Insightful)

    by AbRASiON ( 589899 ) *

    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 und

    • by Anonymous Coward

      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 adv

      • Intel won't let AMD die.

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

      • 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 assumption

    • Re: (Score:2, Insightful)

      by qbast ( 1265706 )
      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).
      • 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.

        • Re:Cores Schmores (Score:4, Insightful)

          by qbast ( 1265706 ) on Monday February 08, 2016 @09:24AM (#51461691)
          You are more optimistic than AMD's marketing department? That's some impressive optimism.
          • 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.

            • 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.
              • 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.

      • by AmiMoJo ( 196126 )

        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.

    • Re:Cores Schmores (Score:4, Interesting)

      by GeekWithAKnife ( 2717871 ) on Monday February 08, 2016 @07:16AM (#51461261)

      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.
      • 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 /.

    • Re:Cores Schmores (Score:4, Interesting)

      by TeknoHog ( 164938 ) on Monday February 08, 2016 @08:06AM (#51461409) Homepage Journal

      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.

      • by mwvdlee ( 775178 )

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

        • by AmiMoJo ( 196126 )

          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.

      • 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.

      • 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.

    • Re:Cores Schmores (Score:4, Informative)

      by TheRaven64 ( 641858 ) on Monday February 08, 2016 @08:41AM (#51461535) Journal
      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).
    • 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.

    • by KGIII ( 973947 )

      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.


  • by ssam ( 2723487 ) on Monday February 08, 2016 @07:44AM (#51461347)
    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.
  • 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' op

    • by Anonymous Coward

      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.

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

  • 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 las

    • by afidel ( 530433 )

      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.

  • Complete bullshit (Score:2, Interesting)

    by Anonymous Coward

    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.

  • 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