Follow Slashdot stories on Twitter

 



Forgot your password?
typodupeerror
Businesses Open Source Google Hardware

Open Source RISC V Processor Gets Support From Google, Samsung, Qualcomm, and Tesla (seekingalpha.com) 135

An anonymous reader writes: Google, Qualcomm, and Samsung "are among 80 tech companies joining forces to develop a new open-source chip design for new technologies like self-driving vehicles," writes Seeking Alpha, citing a (pay-walled) report on The Information. "Western Digital and Nvidia also plan to use the new chip design for some of their products," while Tesla "has joined the RISC-V Foundation and is considering using the tech in its new chip efforts."

MIT Technology Review adds that while Arm had hoped to bring their low-power/high performance processors to AI and self-driving cars, "The company that masterminded the processor inside your smartphone may find that a set of free-to-use alternative designs erode some of its future success."

This discussion has been archived.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

Open Source RISC V Processor Gets Support From Google, Samsung, Qualcomm, and Tesla

Comments Filter:
  • by ctilsie242 ( 4841247 ) on Saturday March 31, 2018 @02:48PM (#56359657)

    We went through an era of tons and tons of CPUs. An open source CPU is very nice, and would be useful for it to be adopted, but is there something wrong about ARM based CPUs that they couldn't be used for this task? ARM is no slouch when it comes to performance, and it it is pretty thrifty when it comes to wattage.

    Is there something ARM can't do that a whole new CPU design is needed?

    • ARM won't eliminate the license fees.

    • License fees, plus you're stuck with what ARM gives you. Having your own core means you can customize it.

      • by Daemonik ( 171801 ) on Saturday March 31, 2018 @04:10PM (#56360029) Homepage

        ARM licenses their core chips, where manufacturers provide all the rest of the CPU's architecture, or ARM will license their architecture where companies can create their own cores around ARM's instruction set. So you're way off base as far as customization of ARM goes.

        The interesting part of this new RISC-V chip is will all these competing companies be able to set aside their IP claims or will they bury the chip in so many patent encumbrances that it never leaves the fab.

      • But you do know that iOS devices run on heavy customized ARMs, and most Android devices, too?

    • Yes, there is something that ARM hardware cannot do. It cannot directly run the existing x86_64 or i386 software.

      • by tepples ( 727027 )

        Yes, there is something that ARM hardware cannot do. It cannot directly run the existing x86_64 or i386 software.

        Neither can RISC-V. Both ARM and RISC-V must use interpretive emulation or static or dynamic recompilation to run an executable compiled for x86, x86-64, Z80, 65816, MC68000, SuperH, PowerPC, CLR, WebAssembly, or whatever other ISA.

        (In context, the question appears to have been intended as "What does RISC-V do that ARM does not?".)

        • I do see some tools, such as https://github.com/rv8-io/rv8 [github.com] , that seem to run x86_64 code in a simulation mode for RISC-V. Has anyone here tested this tool, or seen anything equivalent for ARM ? I've not had or made the opportunity to do so myself: my personal hardware budget is much smaller than it was at earlier times in my career.

          • by tepples ( 727027 )

            Unless I'm misreading rv8's description, it looks like rv8 works the other way around, to run RISC-V code on x86-64, not to run x86-64 on RISC-V.

    • by Megol ( 3135005 )

      You are seriously posting that question on slashdot? Open source means anything to you? That's the big one.
      And then there is the advantage of having an alternative to x86 and ARM that is widely supported, extensible and without license and patent (?) fees.

      • open source software is one thing.

        open source hardware means designed by tools and methodologies years behind the state of the art and lower performance.

        • by Megol ( 3135005 )

          And yet RISC V have added a lot of companies wanting to use it for performance critical tasks. That means using industry standard technology with industry standard software "compiling" the open source verilog/whatever based on an open ISA with open development.

          If I choose to use the closed Intel icc for compiling some open source software doesn't mean the software isn't open. Same applies to hardware design.

      • Open source can be great, when it's got a dedicated team behind it and stays motivated over time.

        Unfortunately open source also has a lot of unchecked prima donnas that make a big splash do some shaky code and then ignore the project because they can't be bothered to bug fix or do maintenance or documentation. Or they abandon their project because they lose interest. Or they fork a thriving project and cause political disruption within it's supporters because they can't manage to get along with everyone e

    • >Is there something ARM can't do that a whole new CPU design is needed?

      It can imbue your computer with a horrible interrupt architecture and a funky set of instructions.
      There are other CPUs that can do that, but they aren't nearly as popular.

    • by lkcl ( 517947 ) <lkcl@lkcl.net> on Saturday March 31, 2018 @04:46PM (#56360177) Homepage

      Is there something ARM can't do that a whole new CPU design is needed?

      there's two main aspects to that. firstly: RISC-V has learned from the past 30 years of RISC processor design mistakes, and is approximately half the area for an equivalent level of performance. that in turn means that RISC-V is HALF THE POWER of an equivalent ARM design.

      secondly: ARM charges royalties for licensing their proprietary design, whereas anyone may adopt the *open* RISC-V design and, apart from needing to be fully conformant with the specification, will NOT be charged any royalties.

      thirdly - and i'm following the development mailing lists so will be watching closely to see how this pans out: open design tends to have more eyes and more transparency (but the RISC-V Foundation still operates behind closed doors and a cognitively-dissonant Charter so it's not a panacea), so despite the flaws there is a higher chance that security flaws warned of by engineering will NOT be over-ridden by marketing executives.

      so it's a triple whammy.

      • Let me ask you this. How, exactly, does Arm control their intellectual property? Surely the basic patents must have expired, and reverse engineering can't be that hard, given all that's known about their architecture. And I think it was established years ago that you can't copyright an instruction set.
        • by spth ( 5126797 )
          By now, the patents for the ARM architectures up to ARMv5 should indeed have expired (current is ARMv8). ARM needs to keep extending the instruction set with new patented stuff to keep control. So I guess you could make a free ARM-compatible code as long as you either always stay 20 years behind on the current ARM version, or try to come up with an incompatible extension of the ARM architecture. The first doesn't look good if you want to have free cutting-edge technology. The second one looses most of the b
    • by Anonymous Coward on Saturday March 31, 2018 @05:08PM (#56360285)

      Is there something ARM can't do that a whole new CPU design is needed?

      The problem that originally lead to creation of RISC-V is that ARM (the company) had a history of blocking university research based on ARM (the architecture). They'd let you theorize all you want, but create an actual implementation (e.g. FPGA) to test your theory, and ARM's lawyers would shut you down. Note: ARM certainly isn't unique in this -- Intel will also shut down researchers who create their own X86. The main difference is that X86 is such an awful architecture that nobody wants to do research with it!

      Berkeley needed a "real" modern architecture to experiment with. A "toy" architecture wouldn't support the type of research they wanted to do. Since they couldn't use an existing commercial architecture, they decided to create their own, and RISC-V was the result. The fact that RISC-V may now have commercial applications is a bonus, not the reason for it's creation.

    • ARM is actually quite old and suffers from a number of architectural shortcomings which can't be fixed for compatibility's sake. x86 gets a lot of flack for being complicated, but as ARM dates back to the 90's and has had a ton of extensions hacked in over the years, it isn't actually the minimalist, efficient powerhouse people think it is. You may ask well ask why the mobile market needed ARM when we had perfectly good x86 chips available.

      I'm not a hardware guy, but since encountering the Visual 6502 [visual6502.org] pro

    • The main thing that's 'wrong' with ARM is that ARM intentionally avoids fragmenting their ecosystem. They don't let you add extra instructions, because they want code compiled for ARMvX to work on any ARMvX core. You can license ARM cores (from ARM or other companies) and put other stuff on the same SoC, but you can't change core parts of the design. That is a great strength in some areas, but a weakness in others.
  • Who has the say and responsibility for the design and in making trade-offs in design? There are going to be plenty to make, and different applications will need different things. Just a starter list includes things like: power requirements, instruction set and special instruction, performance, area, I/O, memory, self-test, coprocessors, design technology and tools, fab technology, supporting libraries and tool kits, and so on. Who will support design integration at the application level? Who wins when

    • Take a look at how big companies develop Linux kernel modifications. It's not that hard. You do the things you want for yourself, and then you share those with the others.

      • The requirements and consequences are pretty different between:

        >>make world
        and
        >>fab chip --with $$$$$

        One of those is trivially and cheaply repeatable, variable, and testable. The other is not.

    • That is before you get to manufacturing. Who will fab them? In what technology? Who will qualify parts? Who will stock the inventory? Who closes the loop between hardware defects and design?

      These cores will not be used as standalone CPU devices. They will be integrated in an application-specific SoC design that each company will have fabbed for themselves according to their own needs.

    • by Desler ( 1608317 )

      The point of this is not for one central party to manufacture some canonical RISC-V CPU. The point is having a base design than be tweaked if need and then added to a SoC, etc. by the designer to be fabbed by a foundry. Just like how ARM does not actually manufacture it’s core but licenses ISAs and core designs to third parties.

      • Your point is well taken. Even so that only makes part of the problem go away. I don't see how one design is going to do it all even if you can mate it with different I/O, ram, etc. I doubt they can parameterize the design sufficiently to cover the range of uses this seems to be intended to cover. I expect there will have to be multiple variants to choose from, and the associated design support, etc.

        But hey, if there is one thing we're short of its processor core IP. :|

        • by Desler ( 1608317 )

          One design won’t do it all. That’s why people will take the base design and tweak it their specific application. Just like how Apple and Qualcomm take the base ARM64 ISA and make their own CPU designs.

    • Alright, so you can have open source linux contributions from large companies.

      Meanwhile, Qualcomm is basically a patent troll with a sideline in silicon design. They never operate in good faith, and they have a long and inglorious track record of getting a standard that, surprise! they have a patent on, or simply using their patents to screw their competitors and collaborators with lawsuits. When they're not using their patents, they're just not serving users, they don't bother to innovate unless it's to sq

  • Bizarre article (Score:5, Informative)

    by Richard W.M. Jones ( 591125 ) <`rich' `at' `annexia.org'> on Saturday March 31, 2018 @03:30PM (#56359849) Homepage
    I've been working for a couple of years on Fedora and Linux on RISC-V [fedoraproject.org] and the "Seeking alpha" article is the strangest thing. The RISC-V Foundation offers BSD-licensed specs and multiple CPU designs (and a lot more besides [lwn.net]). WD, Google, and many more are members. But they are not in any real sense "joining forces to develop a new open-source chip design". The design and chips are already out there, you can make your own FPGA or (if you're very rich) ASIC and have been able to for years. WD are going to switch all their hard drives to RISC-V soon. Google are likely interested because it could be used for their TPUs of their own design. "Joining forces" just means the companies subscribed to the Foundation for a very nominal fee, back-of-the-sofa loose change for these companies.
    • by Megol ( 3135005 )

      I assumed there were a new effort towards a RISC V design with acceleration hardware suitable for self-driving vehicles (whatever that would be).

      • Not that anyone has talked about in public, and I've been following RISC-V for a long while.
        • Well, occasionally “new tech news” can just mean it was “news” to the tech journalist who just now heard about it. Or perhaps he had an article quota to fill, and he didn’t really check whether the companies’ new subscriptions were of any import.

  • This is just the chip design. We would still need ASUS, MSI, Gigabyte, Intel (I would LOL if they released a board for a competing chip), etc, to provide a working platform to integrate these into. A standard socket, PGA or LGA, or soldered on to each board. Maybe we'll see them in a littany of SoC or SBC designs first, that seems much more likely honestly.

    • Nope. You are thinking "broad desktop market" whereas the intended use case for these CPUs is that they will be mounted - likely in SoC form - on small, specific modules.
  • ARM generally makes nearly nothing on a CPU/SoC. Some were less than a penny (US) and the max were closer to a dime. Many companies, Intel, Apple, and such have paid their fee and they're done.

    So exactly WTF was ARM expecting long run? ARM is very good at low power. Very, very good in fact. But high functioning isn't their forte. ARM core designs are slow moving beasties. If a company needs a faster solution they need to be as heavy into the solution as building their own 64bit ARM a full year before anyo

There's no future in time travel.

Working...