Announcement

Collapse
No announcement yet.

NUVIA To Make Serious Play For New CPUs In The Datacenter, Hires Linux/OSS Veteran

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • NUVIA To Make Serious Play For New CPUs In The Datacenter, Hires Linux/OSS Veteran

    Phoronix: NUVIA To Make Serious Play For New CPUs In The Datacenter, Hires Linux/OSS Veteran

    Making waves this afternoon is word of the NUVIA server CPU start-up landing its series A funding round and thus making more information known on this new silicon start-up...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Yay! More ARM systems that will not have complete shit bootloaders and can boot ARM distros without having a custom image and kernel update script made for each of them.

    Comment


    • #3
      Typo:

      Originally posted by phoronix View Post
      Jon Masters, the the Chief Arm Architect and Distinguished Engineer of Red Hat,

      Comment


      • #4
        Originally posted by starshipeleven View Post
        Yay! More ARM systems that will not have complete shit bootloaders and can boot ARM distros without having a custom image and kernel update script made for each of them.
        That reminds me - I'd better make sure all of my kernel patches still apply on 5.4 and dig out my script to pack uboot images for depthcharge...

        Comment


        • #5
          Originally posted by starshipeleven View Post
          Yay! More ARM systems that will not have complete shit bootloaders and can boot ARM distros without having a custom image and kernel update script made for each of them.
          Unfortunately so. The ARM ecosystem is a non-coherent mess.
          Which is fine for the odd embedded system, but non-functional in the COTS buy/replace field.
          I do welcome more players to the SoC arena, but in reality,
          this is nothing more than a slapping-together-yet-another-soc type business.

          Edit: I do hope I'm wrong and I do hope this effort will bring some sanity into the ARM ecosystem without loosing much of its flexibility.
          Last edited by milkylainen; 16 November 2019, 04:04 AM.

          Comment


          • #6
            Seems there are job opportunities for CPU architects from Samsung who were laid off recently. And they haven't revealed the ISA they are using yet. It would be of no surprise to anyone if they were using ARM, but maybe they are going the OpenPOWER route? I mean they left some room for surprises there. If they went with ARM they could have announced it right away. Anyway, it is surprising that they can attract all this talent. The success of non-X86 CPU designs in the server space was rather limited so far and even AMD needs longer than anticipated to gain some ground against Intel in this segment. If anything great comes out of this, I hope it trickles down to the consumer segment sooner or later.

            Comment


            • #7
              Originally posted by milkylainen View Post
              in reality, this is nothing more than a slapping-together-yet-another-soc type business.
              According to Anandtech:
              it looks like the company is aiming to create a new server SoC with a new custom CPU microarchitecture, essentially a new ground-up design


              However, that still sounds like speculation, rather than an official statement of any kind. But I'd have to ask why such talented, veteran CPU designers would've gotten together just to slap together a me-too SoC with off-the-shelf IP. It doesn't make sense to me, on a number of different levels.

              Comment


              • #8
                I'm having a couple of questions (in case someone is more educated about this):

                1) How is this any different that the plethora of other datacenter CPU startups that seem to pop up like mushrooms after the rain and then never deliver (last news was that 64-core ARM cpus are having trouble in the market because the latest AMD's 64-core server parts are simply faster)?

                2) So is anyone even going to care unless these chips aren't at least 50% faster than what's on the market now?

                3) How will software be written for these architectures if all of our development laptops and desktops machines are running x86 (because x86 CPUs are powerful and compile fast)? And don't deceive yourself by thinking it is just a recompile... what do you do when you have a bug appearing on target machine that you can't reproduce on platform that you are developing on because someone decided that either floating point corner cases or atomic/synchronization operations behave slightly differently there ...

                Comment


                • #9
                  Originally posted by pkese View Post
                  1) How is this any different that the plethora of other datacenter CPU startups that seem to pop up like mushrooms after the rain
                  You mean like these guys?

                  Tachyum is enabling human brain-scale AI and advancing the entire world to a greener era, by delivering Tachyum Prodigy - The World’s First Universal Processor


                  Good question. I am similarly skeptical. The market doesn't seem to want new & ambitious CPUs, and anything else has trouble offering enough value to displace incumbents. Big datacenter & cloud operators don't want to take a chance on a little startup that might go under, leaving them high and dry. But, without such big customers, I doubt they can reach enough sales volume to keep the doors open.

                  Originally posted by pkese View Post
                  2) So is anyone even going to care unless these chips aren't at least 50% faster than what's on the market now?
                  I don't know what the number is, but the value proposition has really got to be there. I'd have thought some of the existing ARM server CPUs would be gaining some real traction, by now, due to their inherent energy efficiency advantage. But, it doesn't seem to be the case...

                  Originally posted by pkese View Post
                  3) How will software be written for these architectures if all of our development laptops and desktops machines are running x86 (because x86 CPUs are powerful and compile fast)?
                  Eh, you're not the customer. They're trying to sell these to the likes of Google or Facebook. Someone with a complete software stack of their own.

                  I guess a seemingly generic ARM or RISC-V chip could appeal to a cloud hosting operator, but they'd have to deliver true application-level binary compatibility, for that to even be an option.

                  Comment


                  • #10
                    Originally posted by pkese View Post
                    I'm having a couple of questions (in case someone is more educated about this):

                    1) How is this any different that the plethora of other datacenter CPU startups that seem to pop up like mushrooms after the rain and then never deliver (last news was that 64-core ARM cpus are having trouble in the market because the latest AMD's 64-core server parts are simply faster)?

                    2) So is anyone even going to care unless these chips aren't at least 50% faster than what's on the market now?

                    3) How will software be written for these architectures if all of our development laptops and desktops machines are running x86 (because x86 CPUs are powerful and compile fast)? And don't deceive yourself by thinking it is just a recompile... what do you do when you have a bug appearing on target machine that you can't reproduce on platform that you are developing on because someone decided that either floating point corner cases or atomic/synchronization operations behave slightly differently there ...
                    I might not be more qualified to answer these, but here are some points nevertheless:

                    ad 1) There is not much difference, besides that their lead architects have a proven track record to actually achieve things.

                    ad 2) Aye, I see also problems for any other non-X86-ISA CPU to get meaningful market share in a short time. People start to care if they deliver some huge benefits and porting their apps to make use of these benefits isn't too hard or costs too much.

                    ad 3) Cross-compiling is possible even today (as is done with ARM and x86), proper testing might be a different beast though. I've read of emulators which mimick the chip you are developing for in software. Prototyping with an FPGA might also be an option.

                    Comment

                    Working...
                    X