Follow Slashdot blog updates by subscribing to our blog RSS feed

 


Forgot your password?
Close
typodupeerror
×
Databases Encryption Oracle Hardware

Oracle To Debut Low-Cost SPARC Chip Next Month 92

Posted by timothy from the slow-walk-to-the-bottom dept.
jfruh writes: Of the many things Oracle acquired when it absorbed Sun, the SPARC processors have not exactly been making headlines. But that may change next month when the company debuts a new, lower-cost chip that will compete with Intel's Xeon. "Debut," in this case, means only an introduction, though -- not a marketplace debut. From the article: [T]he Sparc M7 will have technologies for encryption acceleration and memory protection built into the chip. It will also include coprocessors to accelerate database performance. "The idea of Sonoma is to take exactly those same technologies and bring them down to very low cost points, so that people can use them in cloud computing and for smaller applications, and even for smaller companies who need a lower entry point," [Oracle head of systems John] Fowler said. ... [Fowler] didn’t talk about prices or say how much cheaper the new Sparc systems will be, and it could potentially be years before Sonoma comes to market—Oracle isn’t yet saying. Its engineers are due to discuss Sonoma at the Hot Chips conference in Silicon Valley at the end of the month, so we might learn more then.
This discussion has been archived. No new comments can be posted.

Oracle To Debut Low-Cost SPARC Chip Next Month More

Oracle To Debut Low-Cost SPARC Chip Next Month

Comments Filter:

  • Licensing (Score:5, Funny)

    by pr0nbot ( 313417 ) on Thursday July 30, 2015 @11:30AM (#50215155)

    In related news, Oracle have also announced a new per-transistor licensing model.

    • Re:Licensing (Score:5, Insightful)

      by garyisabusyguy ( 732330 ) on Thursday July 30, 2015 @12:33PM (#50215865)

      With 32 cores, this chip must have the Oracle licensing people very excited

      • You don't think Oracle would allow something to be designed which didn't maximize license revenue, do you?

        Why, yes, we'll sell you this CPU for $800 ... but the licensing costs for your organization running this in production in a web-facing environment will be 16 trillion dollars.

        Oracle is all about maximizing license revenues.

        One Rich Asshole Called Larry Ellison. It costs a lot of money to maintain private islands and yachts.

      • GP was talking about the #transistors, not cores :=))

        • Yes, but Oracle currently charges licensing based on the number of cores you are running their software one, databases in particular.

          The massive number of cores in this chip (and transistor count increases with core count) would lead to large licensing fees, unless Oracle creates a means to limit the cores that their product runs on based on licensing

          In the 90's it was pretty popular to tie application licensing to a CPU ID, I wonder if something similar would come into play here

    • What do you wanna bet Oracles new sparc chip includes functions that automatically call home and report on violations of obscure licensing provisions that someone may not have realized they violated.

  • How timely... (Score:3)

    by msauve ( 701917 ) on Thursday July 30, 2015 @11:32AM (#50215185)
    Just in time for Debian to drop support [slashdot.org].

    • Re: (Score:2)

      by JBMcB ( 73720 )

      And yet they still support POWER. Odd.

      https://www.debian.org/ports/p... [debian.org]

    • Re: (Score:2)

      by Z00L00K ( 682162 )

      Anyone left outside Oracle that uses Sparc now?

      Today it's x86 or ARM that are worth to be concerned about.

      • Re: (Score:2)

        by jstuxx ( 4202009 )
        x86 is probably going the same way as Sparc. x86 is powerful but too powerful to be used on mobile devices and doesn't scale very well on desktops when it comes to parallel processing.

        • Re:How timely... (Score:5, Interesting)

          by Lord Apathy ( 584315 ) on Thursday July 30, 2015 @05:01PM (#50218587)

          Horse hocky. My Nexis 7 rolled over and died a few weeks ago so I had to scare up a replacement tablet. I choose Asus Z580C to replace it. This tablet has a intel atom Z3530 processor in it, which I found out later is a x86 based processor.

          I've had it for 2 weeks now and I've very pleased with it. To say the x86 can't be used well in a mobile processor is grade a bullshit.

        • x86 is probably going the same way as Sparc. x86 is powerful but too powerful to be used on mobile devices and doesn't scale very well on desktops when it comes to parallel processing.

          Intel continues to work on reducing power consumption of x86 while retaining performance.
          ARM continues to work on increasing performance while retaining low power consumption.
          I'm hoping for everybody to win.

      • Re:How timely... (Score:4, Interesting)

        by mlts ( 1038732 ) on Thursday July 30, 2015 @12:06PM (#50215567)

        SPARC and POWER still have a place. There are some computing tasks that can't really be split up among multiple nodes, so they still require gigantic CPU requirements. Usually this is related to legacy databases which cost less to keep on the legacy architecture than spend the time to try to move it to PC clusters.

        Another use for SPARC and POWER (and to a lesser extent, ARM) are security applications. In theory (and this is theory, mind you), if another F0 0F bug is found on the x86 platform, perhaps giving attackers remote access to ring 0, having multiple architectures will help mitigate the effects of it.

        Of course, with SPARC and POWER, virtualization is an integral component of both platforms, and for some tasks, it just might be the case that slicing off a lot of LPARS and zones may be cheaper than buying a lot of PCs and using a VMWare cluster, due to the license fees involved.

        • Re:How timely... (Score:4, Interesting)

          by Tough Love ( 215404 ) on Thursday July 30, 2015 @12:43PM (#50215971)

          MIPS is another arch with staying power, mainly because of being largely patent-free. Opencores has VHDL. [opencores.com] IIRC, China has come up with some functioning clusters based on this and there are design wins to be found in embedded (e.g. Broadcom). I don't think there is really anything special about MIPS that makes it attractive. A servicable but unexciting architecture with some programmer-visible quirks that cater to ancient design assumptions that lost validity long ago. MIPS isn't going to die because some embedded designer is always going to find it the cheapest way to chip their product.

        • And don't forget, competition is good. Single sourcing leads to technical stagnation.

        • StackGhost (Score:1)

          by Anonymous Coward

          The SPARC ISA also supports a novel stack-smashing prevention technique that ARM, MIPS, POWER, and x86 do not: StackGhost.

          https://en.wikipedia.org/wiki/Buffer_overflow_protection#StackGhost_.28hardware-based.29

          It's used by default on OpenBSD. Here's a slide from a presentation Theo deRaddt did about 10 years ago:

          http://www.openbsd.org/papers/auug04/mgp00026.html

          If you're a C or C++ developer and you're serious about code quality, you could do worse than focus on portability; portability across operating sys

        • "There are some computing tasks that can't really be split up among multiple nodes, so they still require gigantic CPU requirements. Usually this is related to legacy databases which cost less to keep on the legacy architecture than spend the time to try to move it to PC clusters."

          True but what does that have to do with the usage of Power/Sparc? There do exists 32 and 64 processor xeon systems, and sgi will even sell you a system with 256 cpus and 64 TB ram if you can pay the price.

          https://www.sgi.com/produ [sgi.com]

      • Re:How timely... (Score:4, Insightful)

        by alvieboy ( 61292 ) on Thursday July 30, 2015 @01:11PM (#50216311) Homepage

        Yes, ESA (European Space Agency) uses SPARC, but another implementation (LEON2 and 3, fault tolerant versions [1] ). And NGMP[2] I think is also SPARC based.

        LEON is developed by Gaisler, and was funded by ESA.

        Alvie

        [1] https://en.wikipedia.org/wiki/... [wikipedia.org]
        [2] http://microelectronics.esa.in... [esa.int]

    • Yeah. Oracle could put Oracle Linux on it, instead of Solaris, otherwise it could cannibalize the high end Sparc servers. Or if Linux is no longer an option, maybe OpenBSD or FreeBSD.

  • [T]he Sparc M7 will have technologies for encryption acceleration and memory protection built into the chip.

    Well, encryption acceleration has been available on x86 for a while and memory protection has been available on... well, I seem to remember that was the big feature the 286 had over the 8086, and it was only new to PCs at that point. That's a rather peculair thing to brag about, especially as the SPARC chip has always had it since it's inception.

    Whatever though. I am kind of in two minds about this.

    • [T]he Sparc M7 will have technologies for encryption acceleration and memory protection built into the chip.

      Well, encryption acceleration has been available on x86 for a while and memory protection has been available on... well, I seem to remember that was the big feature the 286 had over the 8086, and it was only new to PCs at that point. That's a rather peculair thing to brag about, especially as the SPARC chip has always had it since it's inception.

      Whatever though. I am kind of in two minds about this. Yaaay cool new sparc chip! ew, Oracle.

      This processor includes encryption support... An ISA that no one uses!

      • Re: (Score:1)

        by Anonymous Coward

        You don't know what you're writing about. And the SPARC V9 ISA is great: one instruction cycle for every instruction, free instruction slot for any instruction after a branch, zero cycles. 32 64-bit registers, 256 virtual 64-bit register with the hardware register windows. Flat memory model. Great performance, especially for hand written assembler code, unbelievably fast.

        Oh, and did I mention UltraSPARC is great? In case I did not, it is great. Because the ISA is really slick. Because it rulez!

    • Comment removed based on user account deletion
      • And I don't think they're referring to "text" and "data" pages since that has been in Sparc since before the V8/V9.

        • And I don't think they're referring to "text" and "data" pages since that has been in Sparc since before the V8/V9.

          And, if I recall, the VAX and BSD before that - I seem to remember futzing around with those for the linking loader project in my systems programming class that used our VAX-785 running 4.3BSD back in the mid 1980s. (Yes, I'm old.)

  • Comment removed based on user account deletion

    • Re: (Score:2)

      by Lumpy ( 12016 )

      I see you never begged at the feet of Silicon Graphics....

      Sun on a throne? Sun were amateurs compared to SGI in making your customer kneel.

    • Re: (Score:2)

      by kriston ( 7886 )

      I don't think Fujitsu, Texas Instruments, Atmel, or Cypress Semi would agree with you on the opulence of the SPARC architecture. It has had a very vibrant community of licensors for a long time. The hyperSPARC, TurboSPARC, and SPARC64 VI aren't even Sun products, to name a few.

  • If Oracle can follow up upon the hype in the PR and actually deliver competition for the Xeon, then the customers in the server market will benefit.

    .
    On the other hand, Oracle still has the unquestioned ability to shoot itself in the foot with the predatory pricing models apparently associated with it.

  • Cost & Support! From the summary, this is described as a new effort to bring the SPARC processor cost down to where it can compete with Intel's high end parts.

    High cost + no installed base = flop (megaflop?)

    I remember back around 2002 when we got a fancy SPARC server at work that was multi-processor, big ram sun fire. The thing cost in the neighborhood of $40k. We also got an x86 server for about $2500 at the same time. When I ran large circuit simulation jobs on the x86 server, they ran about twice as

  • Low cost chip, high cost support (Score:5, Interesting)

    by ErichTheRed ( 39327 ) on Thursday July 30, 2015 @12:11PM (#50215619)

    I'm sure the hardware itself will be cheap. Oracle's hardware is like IBM's mainframes -- they'll practically give away the hardware if you'll burn up MIPS on a regular basis. Even if "give away" is thousands per socket, it's a drop in the bucket compared to the fees for support and any OS licensing. Our relatively large company is a decent sized Oracle DB customer (lots and lots of hosted J2EE enterprisey applications) and the maintenance fees alone, just to be able to run the software, are eye watering.

    The problem is that licensing like that keeps all but the most well heeled customers off SPARC, and hence the popularity will never get much higher than it is. Ever since Linux on x86 became a viable alternative, companies without a real need to run SPARC and by extension Solaris on SPARC are migrating away. Even Debian dropped support for its SPARC port.

    Whether it's the high cost keeping people off SPARC, or the niche nature of Itanium keeping people off Itanium, a system architecture needs a critical mass of customers with a continued need to run on it to be successful.

    • Re:Low cost chip, high cost support (Score:4, Interesting)

      by fuzzyfuzzyfungus ( 1223518 ) on Thursday July 30, 2015 @12:58PM (#50216163) Journal
      What I find a bit weird about SPARC's near-total obscurity is that(please correct me if I'm wrong on the details; but to the best of my understanding from what I've read) the ISA is available for use on a royalty-free basis, and there are even a few BSD or GPL verilog implementations out there. That's even less encumbered than MIPS(which has some patents that the owners like to wave around on a couple of useful instructions).

      My naive expectation would have been that SPARC on such liberal terms would show up a bit more often embedded in various chips that need some sort of CPU to do housekeeping, as the ISA of security and/or nationalism driven 'indigenous technology' efforts, and potentially even as the cheaper-than-ARM option for application processors.

      Clearly that hasn't actually happened, and it's mostly ARM in SoCs and application processors(with PPC holding out in certain automotive and networking niches for some reason; and MIPS in router SoCs and the occasional Chinese vanity project); so ARM's license fees must just not sting that much.

      Building SPARC parts that go toe to toe with Xeons would obviously be a much more ambitious project(as well as an act of directly fucking with Intel's juciest margins, which they probably won't take very kindly); but I am surprised by the fact that SPARC is so rare among the zillions of devices that have no need for x86 compatibility and are mostly about delivering performance in the gap between beefy microcontrollers and weak desktops for as little money as possible.
      • It may seem wierd, but it is entirely rational.

        Sure the ISA is open, but that is just for the CPU. A meaningful inplementation needs all the stuff that goes around it, and, as with all electronics, volume is king.

        Theoretically, as you say, someone who needs a CPU to embed could choose Sparc. Then they could set about developing the rest of the system. But when they place an order, they better have a vlome market - or they would be better of with an alternative by a very large margin.

        The existing Sparc

        • Now if a Sparc product was to target the mobile phone market?

          Yeah, there's already been embedded SPARC processors, I talked to some guys at a job fair a long (long) while back who had built a digital camera around one. The problem is, they're just not cheap enough.

      • Re: (Score:1)

        by cb88 ( 1410145 )
        Intel Bay Trail has a sparc embedded as its ME controller cpu... ;D

        https://recon.cx/2014/slides/Recon%202014%20Skochinsky.pdf

  • It's dead Jim (Score:3, Informative)

    by Tough Love ( 215404 ) on Thursday July 30, 2015 @12:20PM (#50215713)

    It's dead Jim. [debian.org]

    That's the debian verdict. Oracle may have other ideas, but if drinking that koolaid, caution is advised.

    • Somebody modded my post troll, almost certainly an Oracle employee. However, the linked mail is a fact, and the current situation is a fact, no astroturfing will change that. To you the mod: sad to be you.

  • If they want to do a hardware thing, they should invest the time in making a multicore processor which solves a problem no one else is solving. Maybe a processor specifically designed for microkernels and untrusted code. Maybe an FPGA that implements CAM's + complex SQL functions on the fly in circuitry, as needed? You know, stuff people other than Oracle might actually have a use for? Then they could sell that stuff and make money.
  • As I can see, the article was posted on Friday July 31, 2015 (not sure whether Slashdot is showing me local time)... So it's today?

  • Translation for ordinary people (Score:4, Funny)

    by Kjella ( 173770 ) on Thursday July 30, 2015 @12:44PM (#50216001) Homepage

    Instead of costing an arm and a leg, Oracle's new chip will only cost you a couple fingers and a toe.

  • But there would be no need for this chip (Score:3)

    by blang ( 450736 ) on Thursday July 30, 2015 @01:09PM (#50216281)

    If only Oracle revised their licencing policies.
    It is impossible to build a cost-effective production ready system with industry standard components, such as proliant blades, vmware, etc, because of only 1 thing: Oracle's hostile licensing policies and metrics. First is the 25 users minimum per processor license. Then there is the fact, that you have to license the full physical server, unless you deploy on very specific Oracle VM hypervisor configuration. And these days, you can't get blades with less than 4 cores. SO if you need a few Oracle software products, you will easily spend more than half a million. So now we have all these shops, trying to streamline their IT into easy to provision private clouds, only to find out that they have to toss it all away.

  • Long live Sparc!

    Wait, what?!?

  • I was a big SPARC fan. I've still got two old Sun Netra sparc64 1u servers in my basement. I used to have used sun workstions, and even had MidnightBSD running on some Sparc64 systems early into my project.

    The problem is that when Sun was sold to Oracle, they closed up patches, documentation on old hardware and anything useful for supporting old Sun hardware. That meant that the used market dried up. They then put out only super expensive systems and got rid of workstations. This caused developers to lose

  • It doesn't matter how much better any new CPU design is. Unless you've got a billion dollars a year to invest in making it better, you're simply not going to keep up with Intel, and it will soon be obsolete. And unless you're selling hundreds of millions of copies of that CPU, you likely don't have a billion dollars a year to invent in R & D. Unfortunately, CPU chips are a textbook case of a "natural monopoly" i.e. "A natural monopoly is a monopoly in an industry in which it is most efficient (involving

Slashdot Top Deals

Your password is pitifully obvious.

Close