Forgot your password?
typodupeerror
Hardware

Samsung May Start Making ARM Server Chips 116

Posted by samzenpus
from the new-ground dept.
angry tapir writes "Samsung's recent licensing of 64-bit processor designs from ARM suggests that the chip maker may expand from smartphones and tablets into the server market, analysts believe. Samsung last week licensed ARM's first 64-bit Cortex-A57 and Cortex-A53 processors, a sign the chip maker is preparing the groundwork to develop 64-bit chips for low-power servers, analysts said. The faster 64-bit processors will appear in servers, high-end smartphones and tablets, and offer better performance-per-watt than ARM's current 32-bit processors, which haven't been able to expand beyond embedded and mobile devices. The first servers with 64-bit ARM processors are expected to become available in 2014."
This discussion has been archived. No new comments can be posted.

Samsung May Start Making ARM Server Chips

Comments Filter:
  • Apple is busy switching to these chips for their laptops/desktops. Coincidence?

    • by gigaherz (2653757)
      Apple decided to stop buying their LCDs, why would they begin buying their ARM chips now?
    • Apple is busy switching to these chips for their laptops/desktops. Coincidence?

      Yes. Because when I'm looking for a server, I need to be able to RUN THINGS ON IT! You know, like exchange and our autocad plugin licensing program and our fax controller and our voicemail control program and active directory. I can't even think of anything an arm chip would help with other than being slow and not running anything. It wouldn't even work as a file server because then it'd have to run some RT-style version of server 2012 and Linux probably won't run on it either. What a pointless device.

      • by morgauxo (974071)
        ... A couple of game servers, a Bittorrent tracker, IRC server...
      • Arm seems to be pretty strongly pushing linux support for 64-bit arm devices and I imagine the opensource server apps will pretty quickly follow. Samba4 will probablly run too if you want to host an AD tree.

        It will be insteresting to see what MS does and whether they gimp the 64-bit arm version of windows in the same way they gimp the 32-bit one but even if they don't I wouldn't expect specialist propietry server apps to be ported any time soon. So for those uses arm is probablly out of the running for now.

  • by toygeek (473120) on Thursday November 08, 2012 @03:56AM (#41916333) Homepage Journal

    I understand the implications of lower power for infrastructure reasons. Lower power means lower cost for power, lower cooling needs, etc. I get that. But what is the "Killer app" for these low power servers? Is it data warehousing? Simple web hosting? I can see these being useful for odds-and-ends servers in data centers with bigger iron for more heavy duty apps, but why is everyone jumping on this bandwagon?

    • by White Flame (1074973) on Thursday November 08, 2012 @04:04AM (#41916361)

      I/O bound servers, where a more powerful CPU would be mostly idle anyway.

      Web hosting, data warehousing, networking infrastructure, and the like do fall that way pretty often, though obviously there are exceptions.

      • by Joce640k (829181) on Thursday November 08, 2012 @04:42AM (#41916493) Homepage

        I/O bound servers, where a more powerful CPU would be mostly idle anyway.

        Didn't we invent SSDs to fix that...?

        • You realize there are these things called networks, and they aren't exactly as fast as the CPU...
          • The mechanics of serving today, they got like 10000 hosts stuffed into one machine, the hoster knows well that 90% of those sites are idling most of the time, so it is not an issue, but has the multicore muscle to save the day in a busy thread spike. The I/O bottleneck is actually not a problem, there are very few high traffic websites. A common web hoster just needs a low-power hexa, octa or better multicore on the cheap.
        • by Morlenden (108782) on Thursday November 08, 2012 @06:23AM (#41916883)

          The I/O limit could be on memory. Servers can have >1000 times more RAM than there is cache on a CPU chip. With enough threads and/or processor cores the cache hit rate drops, so that the memory bus is 100% busy. At that point a faster CPU gives no benefit, may as well us a low-power one.

        • by Chris Mattern (191822) on Thursday November 08, 2012 @09:26AM (#41917591)

          No, we invented SSDs to alleviate that. Even an SSD is much, much slower than the CPU. Hell, your *RAM* is much slower than the CPU; that's why CPUs have memory caches. Even with SSDs, there's a lot of load profiles where the CPU is not the bottleneck. A slower CPU that's cheaper, uses less power and generates less heat looks good to anybody with that kind of load profile.

        • I/O bound servers, where a more powerful CPU would be mostly idle anyway.

          Didn't we invent SSDs to fix that...?

          Even if the system is not bottlenecked by a HDD, you wouldn't need much any CPU power if the server is doing a lot of plain I/O, which is just copying bits around.

      • I/O bound servers, where a more powerful CPU would be mostly idle anyway.

        How about distributed databases with high throughput and complex commit protocols?
        Don't we need fast CPU's for that?

        • Hence the GP said, "though obviously there are exceptions."
          He wasn't claiming that these chips would be perfect for everyone, just that there are *some* areas where they would be.

    • by gigaherz (2653757)
      If you expect your datacenter to spend a lot on time processing data, then ARM and other low-power components are probably not for you. If, on the other side, you expect the cpu to be somewhat idle, and the system to spend most of the time on DMA operations between HDDramnetwork, you want a system that uses up the least possible power, specially in idle contiditions. Of course I suppose in most practical examples you don't really have either situation. Chances are you want your datacenter to be able to proc
    • by AHuxley (892839) on Thursday November 08, 2012 @04:18AM (#41916417) Homepage Journal
      Re why is everyone jumping on this bandwagon?
      Think of the colourful charts - a new vision of fast ssd's, new ARM, new streamlined code and huge drops in power costs* when doing some types of math and not using HD's.
      Find some art of a smiling admin and photoshop it all together.
      Invite managers to lunch and sell them the low power, always on, expandable, low cost, union free remote admin upgrade, effortless cloud future - now at a super low price if you sign up today.
      Then up sell the users on your green server, green power supply and find some art of a happy polar bear.
      Its like selling powerpc to the young and dumb all over again.
      • I don't think so (but I'm not in this business either, so this is just my opinion).

        These ARM servers are not for the general public. A lot of servers now go to the Facebook, Google and Amazons. These guys run their own stacks based on open source, so are not much tied to any ISA. Linux based software run fine on ARM. And they have a lot of loads that are I/O bounds (network mostly), so no need for huge CPU. And costs are critical, both in term of cost of hardware and power consumption (direct and cooling)
    • by cstdenis (1118589) on Thursday November 08, 2012 @04:45AM (#41916497)

      * DNS servers (if you aren't virtualizing stuff)
      * email servers (if your spam scanning is external)
      * some database servers (generally io bound not cpu bound, tho it of course depends on the nature of the queries)
      * simple web hosting (stuff like a CDN serving static files needs almost no CPU)
      * monitoring servers
      * Camera/surveillance servers (video processing is mostly done by dedicated chips on capture cards)

      Really, most servers are not CPU bound these days and would probably benefit from many low-clocked cores than few high-clocked ones. They are exceptions of course, that is why we have super-computers at the other extreme.

      • by mjwx (966435)

        * email servers (if your spam scanning is external)
        * some database servers (generally io bound not cpu bound, tho it of course depends on the nature of the queries)

        Where are these servers not CPU intensive. Even in a small business your most CPU intensive servers will be mail and database.

        Things that ARM chips would be ideal for.
        * File server appliances
        * Security appliances
        * Web server appliances
        * Networking appliances (DNS, DHCP, Directory Services)

        You might notice the word "appliances" comes up a lot, well ARM/Linux is already used in a lot of these appliances.

        The one that ARM would be ideal for I havent seen (so it probably exists and I havent seen it)

        • Re: (Score:3, Interesting)

          by Anonymous Coward
          POP3/IMAP/SMTP server:
          95-98% idle
          Anti-Spam server:
          70-45% idle
          These are both ISP servers, with many thousands of active accounts.
          In both cases having more, slower cores would be better than a few faster cores.
        • I dunno, I'm having trouble seeing what gap they fill. In terms of low powered units, well we have those already. They often do use ARM CPUs (or MIPS), with other bits integrated on them, and they work fine for consumer shit. When you start to talk higher end, you need bigger systems.

          Like if you want a simple little home NAS type of thing, it might ship with a BCM4718 and do just fine. However when you start stepping up to enterprise filers, you need more power. You find NetApps use Intel and AMD CPUs as an

    • by Whiteox (919863)

      It's actually the byte size that matters. Chomping 64 bits per cycle means more data per instruction. You really don't need any of the fancy intel instruction set or construction set for just plain raw processing.

    • by Anonymous Coward

      Who cares about ARM!

      From previous slashdot CPU circle jerk articles the Cell processor should be in everything now! RIP x86!

    • by wvmarle (1070040)

      I'd love to replace my server with a low-power ARM type one (Debian runs on ARM, right?). First of all, remember that there are many many more uses and installations of servers than in server farms and data centres.

      My server is not doing much work, though it has many different jobs. It's running a web site that has a couple dozen hits a day maybe. It's a file server (NFS - for the home directories, and handling backups), Kerberos authenticaion, e-mail/SMTP, LDAP, etc. And it's for just two workstations, and

      • by Ash-Fox (726320)

        It's a file server (NFS - for the home directories, and handling backups), Kerberos authenticaion, e-mail/SMTP, LDAP, etc.

        It might sound absurd, but I find e-mail to be one of the more intensive tasks my servers perform and this is mostly due to anti-virus, anti-spam, archiving etc.

      • by cmdr_tofu (826352)

        What do you do for SPAM? Running a small (less than 10 users) email system over the years, I've had to upgrade from a dual PII to a dual PIII and most recently just got an i7. To be fair I didn't need to get the i7, but the entire system was cheap and the dual PIII had problems that I didn't want to investigate (most likely bad RAM).

        Postfix+mailscanner+spamassassin are not cheap to run! Dspam is maybe a lot lighter than spamassassin. But once you have an active mailserver on the internet you get signifi

        • by wvmarle (1070040)

          The first 90% or so of spam is stopped by greylisting on SMTP level. Yes it delays mails from new senders a bit, but in 99.9% of those cases I'm not expecting it, and am not waiting for it, so that doesn't really matter. And by far most of the mails that I receive are from regular contacts anyway which are accepted instantly.

          The last 10% that does come through amounts to some 30-40 spam per day on my account, and far less on my staff's account (which is not plastered all over the place). The number of e-mai

      • by Tim99 (984437)
        A bit expensive, but a Swedish company does a turn-key for this: http://www.excito.com/ [excito.com]
  • Remember now (Score:5, Insightful)

    by ADRA (37398) on Thursday November 08, 2012 @04:11AM (#41916391)

    The new Google Nexus phones are shipping with 2GB of ram, and its conceivable that tablets will being shipping with > 4GB of ram within a few years. It just looks like Samsung is covering their bases for the future.

    • Re:Remember now (Score:5, Informative)

      by White Flame (1074973) on Thursday November 08, 2012 @04:18AM (#41916421)

      The recent 32-bit ARMs supports LPAE, so you can have over 4GB no problem. That's still running a 32-bit address space per app, which would probably still work fine for a mobile environment.

      • Re:Remember now (Score:4, Insightful)

        by MrDoh! (71235) on Thursday November 08, 2012 @05:11AM (#41916591) Homepage Journal
        Very true, but marketing will probably prefer 64bit chips over 32bit chips with LPAE as it just sounds more powerful to have the 64bit. These go to 11.
        • Very true, but marketing will probably prefer 64bit chips over 32bit chips with LPAE as it just sounds more powerful to have the 64bit.

          It's not that simple. 64bit instructions can handle more data per cycle than 32bit ones, so there is an increase in performance whenever you handle large amounts of data and/or large numbers. I don't know how much of an overhead LPAE adds to execution, but no matter how small the overhead is no overhead at all is still better. Also, I am not sure if I have misunderstood something or not, but I've gotten the impression that even with LPAE the OS can access up to 1TB of memory, but the 32bit applications are

          • Re: (Score:3, Informative)

            by Anonymous Coward

            Umm, you're still processing a single item of data per cycle, but it's now 64-bit long instead of 32. Performance increases if you can process 64 bit as a vector of 2x32/4x16/8x8 bit values, which you could do before with NEON for ARM or MMX/SSE for x86.

            Extra addressable space doesn't matter for most tasks, some, like DBMS, do benefit from it though.

            Biggest performance increase from new 64-bit architectures, applicable both for x86_64 and ARM64, is bigger register set - you don't need as much memory accesse

          • Your post contains a number of misconceptions.

            It's not that simple. 64bit instructions can handle more data per cycle than 32bit ones, so there is an increase in performance whenever you handle large amounts of data and/or large numbers

            The first is that the size of the address space corresponds to data size. NEON, the ARM vector instruction set, can already perform operations on 64-bit integer or floating point values[1]. This is even true on x86, where you have 64-bit operations that work on a pair of registers. The advantage is that you have 64-bit registers, so you don't need to use two for each 64-bit operation (6 of your 14 GPRs on ARMv7 if you want two source and one destination, comp

            • Were you the guy who explained why the conditional instructions of 32-bit ARM were no longer an advantage, hence the lack of them in 64-bit ARM? I forgot the explanation and can't find it, and would be grateful if you point me to it.
      • While it is a workable hack to support more than 4GB of RAM without expanding the virtual address space, it is a hack. Much better to just g 64-bit and call it good. Hence I imagine that's what you'll see with mobile devices. When they start to need more RAM, they'll shift to 64-bit.

        Same shit with desktops and many Intel servers. Intel supported PAE, and Windows implemented it as AWE, with 32-bit chips. Was never very popular though, due to the limitations and performance issues with paging. Now, with actua

      • by evilviper (135110)

        PAE is a hack. It works, but you should avoid it if you damn-well can. And it sounds like we all can avoid it.

    • by wvmarle (1070040)

      It's that they're missing ethernet ports and are low on storage, but a modern phone is more than powerful enough to serve as a simple server.

      • It's that they're missing ethernet ports and are low on storage, but a modern phone is more than powerful enough to serve as a simple server.

        My old Nokia N900, with its 650Mhz single-core CPU, was doing quite fine as a small Samba+SSH+Transmission+Mumble - server with spare CPU-resources left over, too, so yeah, I agree with this. I just installed DD-WRT on my Buffalo - router the day before yesterday and the proceeded to install uMurmurd (a simplified Mumble-server) on it, and it still handles routing 1Gbit/s Ethernet and 802.11n WIFI on top of it perfectly fine with only a 333Mhz ARM CPU. I love how DD-WRT made the box so much more useful and

    • by Solandri (704621)
      Samsung already has a line of tablet-like tablet PCs (i.e. not notebooks which convert into a tablet) which it's been selling for over a year [engadget.com]. Given Microsoft's announcement of Windows for ARM, it's hardly surprising that Samsung is prepping for an ARM version to go with its Intel version.
  • by SpaghettiPattern (609814) on Thursday November 08, 2012 @05:10AM (#41916589)
    I would gladly welcome commodity server motherboards with ARM 64 bits CPUs. I trust I would easily find a suitable distro for my home server.
    • by drinkypoo (153816)

      Perhaps if Linaro's work bears fruit, that will be a realistic vision. Right now support for ARM-based devices is all over the place and is only now being unified in the kernel, let alone boot loaders etc.

    • If this thing does crypto well, I could use a quad-core ARM chip at home.

      But I doubt those chips are targeted at home or small business. They'll probably have much more than 4 cores, to achieve similar throughput to the current x86 offerings.

  • MIPS and ARM are very similar Instruction Set Architectures. While I've only taking a cursory look at the new ARM64, it doesn't seem as clean as MIPS64. So with the same level of optimization, MIPS should be able to get a better performance per watt and higher IPC. SiByte had working MIPS64 CPUs 12 years ago. MIPS used to dominate the TOP500, but recently Intel has left them in the dust. So I don't see how Samsung is going to do any better with ARM.

    Then again, if x86 can become the IPC leader, any ISA has

  • by jittles (1613415) on Thursday November 08, 2012 @10:07AM (#41917861)
    I just got an email from Samsung at the beginning of this week asking me to apply for a job in Dallas, TX. They are looking for an ARM Server hardware/software development team. They sent me the software job description and it looks like they want people who can tweak some firmware and perhaps even tinker with the Linux kernel. Looked like a great job but they require an MS in CS/CE and prefer PH Ds. I don't know why they even bothered emailing me. They have my resume and I clearly do not have a masters.
    • by ledow (319597) on Thursday November 08, 2012 @10:28AM (#41918031) Homepage

      Because "we require" rarely means "we won't touch you with a bargepole unless you have". It's there to weed out the chaff who think they're not good enough or important enough to apply.

      I've applied for numerous jobs that have "required" things like MCSE's and A+, and first-class degrees and I clearly state that I don't have them, but what I do have is X amount of experience doing Y.

      The bright employers (i.e. the only type you *want* to work for anyway) pick it up and say "Oh, right, he's probably spent so long DOING the job, he never got around to paying the certification tax on a bit of paper to say he could do it." or "He was out earning a wage in this sector while our own guys were still in university playing with microcontrollers". The bad ones, of course, shove it off and it gets lost in the HR department because it "doesn't meet criteria".

      I've also advised people to ignore this sort of thing in the past, so long as you *CAN* put forward a reasonable case of being suitable for the job anyway, and it's never perfect (there is no magic way to get a job) but it's helped a lot of them to get positions they didn't think they were good enough for. How many of the industry founding fathers and visionaries had PhD's or Masters? Nowhere near all, and they still got there.

      Don't blatantly ignore high requirements, just substitute what you have instead (and, if you like, in your covering letter explain that: "Although I notice that the job requirements include X, I feel that my extensive expertise in position Y performing task Z should be sufficient to prove that I'm capable of performing to the standards required") if you think you have a shot of doing the JOB.

      Applications processes are mainly about weeding out the vast number of applicants, but secondarily they are about YOU weeding out the vast number of jobs available. Because if your employer can't see that you can do the job, just because you have an absence of certain desired letters after your name, you probably don't want to work there anyway (and they probably will ignore your application, but the chances that they veto you for future posts because of your politely-worded ambition are vanishingly small... and again, those sort of people you just don't want to work for anyway).

      That may be *why* they bothered emailing everyone. Because they aren't just interested in PhD's, but they just want a high standard of applicant. One who has those qualifications, or one who has the skills and knows how to get through a job application process by playing on them.

      The worst that happens is they say No, and keep your information on file for future reference. The chances it will prejudice any future applications - a concern I've heard from the people I've given personal advice - are basically zero (do you really think HR departments keep years and years and years worth of applications that they are already TRYING to narrow down to just a few candidates from thousands and somehow and check them for every post? No.).

      And, you never know, they might just say "Well, actually, you're not right for this particular position, but we are just about to advertise for X as well, and that's look more suited to you."

      In job-hunting, there's nothing wrong with being ambitious, so long as you're honest. And even if they offer it you and you don't like the idea of working in a crowd full of bitter PhD's, or it's not better than your current job, again - you can so "no" just as easily as they can.

      • by jittles (1613415)

        Oh I agree with what you're saying but 1) the job is in Dallas, TX. 2) In my experience, these large companies are very hard to get into w/o meeting the basic requirements. If you know someone, you can get into them, but I bet the application would never make it past HR. I'm a pretty spot on match for 90% of their requirements, maybe more. But I am not going to bother applying for a job that is somewhere I don't want to live, and is also likely just a waste of my time. I have a job already and am only c

  • by EmperorOfCanada (1332175) on Thursday November 08, 2012 @12:00PM (#41919075)
    I look at the raspberry pi at $25 and think that would make an OK server. So a slightly upgraded pi with a good arm processor and say 4-8G of memory would be an awesome server as part of a cluster. For many servers in clusters a bit of storage is needed for boot up; the data mostly stays in ram. Then all that would be needed would be the occasional more traditional machine for HD storage. It would be killer to be able to keep adding new little servers for $99.
    10 machines with say 4 cores each and 4G each would give a cluster with 40 cores and 35 gigs of in ram storage; all for around $1000. Plus anything by ARM would probably be pretty good efficiency-wise.

    Due to redundancy and the extreme capacity adding flexibility I would much prefer $99 machines to just a boring regular server with just an big old ARM chip. Or even a boring regular server with a pile of ARM chips.

What the large print giveth, the small print taketh away.

Working...