Announcement

Collapse
No announcement yet.

New Ryzen Is Running Solid Under Linux, No Compiler Segmentation Fault Issue

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

  • #41
    For the sake of convenience, I hope my CPU is ok. I'll have to test this shell script at some point just to make sure. I have had a handful of hard resets, where it has been difficult for me to know if that's related to my OC or this defect.
    I'm guessing if the CPU is in fact faulty then the "kill-ryzen.sh" ought to work on stock clocks and voltages?

    Since stability issues are still pretty rare for me, I might just keep the CPU until "Zen 2" is released and sell my current one. To my understanding, this problem doesn't affect Windows users so I could probably sell the CPU to someone else I may build a PC for. I'm hoping Zen 2 will be more energy-efficient and be able to OC higher. If the overall performance remained the same, I'd be fine with that.

    Comment


    • #42
      Originally posted by schmidtbag View Post
      For the sake of convenience, I hope my CPU is ok. I'll have to test this shell script at some point just to make sure. I have had a handful of hard resets, where it has been difficult for me to know if that's related to my OC or this defect.
      I'm guessing if the CPU is in fact faulty then the "kill-ryzen.sh" ought to work on stock clocks and voltages?

      Since stability issues are still pretty rare for me, I might just keep the CPU until "Zen 2" is released and sell my current one. To my understanding, this problem doesn't affect Windows users so I could probably sell the CPU to someone else I may build a PC for. I'm hoping Zen 2 will be more energy-efficient and be able to OC higher. If the overall performance remained the same, I'd be fine with that.
      I haven't heard anything at all about a windows userspace app triggering it, so you probably would be ok to sell it to a strictly windows user.

      Comment


      • #43
        Originally posted by schmidtbag View Post
        To my understanding, this problem doesn't affect Windows users so I could probably sell the CPU to someone else I may build a PC for.
        The problem is reproducible in Windows by running the test scripts in WSL. It is just much easier to trigger for Linux users. How this will change in the future if websites start to stress the web browsers' JIT compilers more is anyone's guess.

        But if you are affected, you can RMA the CPU to AMD and they will send you a working replacement.

        Comment


        • #44
          Originally posted by nomadewolf View Post

          If it was a bug, it probably was fixed with microcode, as a silicon fix would take way longer IMO.
          It's already been proven that it's not microcode. The RMA'd chips have the same same microcode which is what's embedded in AGESA 1.0.0.6.a - if it was as simple as that, AMD would have dropped the microcode like it's hot and fixed this a long time ago.

          Instead, it's still being brought up in the news because it's still broken (yet, they still keep mum about this issue).

          Comment


          • #45
            The idea that there are defective processors on the market right now mixed in with the fixed processors is sickening. I'm unsure if AMD is hoping that most users will never encounter the fault so as to avoid triggering a full product recall, thus the RMA process to address only the few affected users, or if there is some software fix planned or expected further into the future.

            At this stage, if you're unsure that you'll be able to secure one of those recent week manufactured Ryzen processors, the risk factor states that you're going to go knock on Intel's door for an while. AMD's Marketing & PR teams likely already understand that, and their silence regarding a correction other than through RMA leads me believe that any software fix for the legacy Ryzen processors will be a very long time away, if ever.

            Comment


            • #46
              My RMAed Ryzen 7 1700 is in transit now. It stayed in Pudong Airport, Shanghai for about 12 days.
              Hurry up FedEx.

              Comment


              • #47
                Originally posted by duby229 View Post

                I haven't heard anything at all about a windows userspace app triggering it, so you probably would be ok to sell it to a strictly windows user.
                I'm waiting for my RMA chips back (both my 1700 and 1700X are affected with the SEGV BUG). Both those machines also fail to run the Ashes of the Singularity - Escalation built in benchmark in Vulkan or DX12 mode (DX11 is OK) crashing to desktop (disabling SMT gives it stability) .

                Couple of people reported this issue as well.
                Last edited by Funks; 25 August 2017, 12:19 PM.

                Comment


                • #48
                  I have both mce (I have random freezes when PC is in the IDLE*) and segfault (< 5 minutes after ryzen-kill.sh test) issues in my 2 PC (first one with Ryzen 5 1600X and second with Ryzen 5 1500X). I bought two CPUs in april. It looks like I will need send both CPUs to RMA, but during RMA process I will not have a working PC and it's irrating because I also use my home PC for a work...

                  * - log related to mce issue:
                  Code:
                  Aug 12 15:44:18 Venom kernel: [    0.378025] mce: [Hardware Error]: Machine check events logged
                  Aug 12 15:44:18 Venom kernel: [    0.378025] mce: [Hardware Error]: CPU 7: Machine Check: 0 Bank 5: bea0000000000108
                  Aug 12 15:44:18 Venom kernel: [    0.378025] mce: [Hardware Error]: TSC 0 ADDR 1ffff8fcb69e6 MISC d012000101000000 SYND 4d000000 IPID 500b000000000
                  Aug 12 15:44:18 Venom kernel: [    0.378025] mce: [Hardware Error]: PROCESSOR 2:800f11 TIME 1502545454 SOCKET 0 APIC 9 microcode 8001126
                  Last edited by nadro; 25 August 2017, 01:07 PM.

                  Comment


                  • #49
                    Originally posted by chithanh View Post
                    The problem is reproducible in Windows by running the test scripts in WSL. It is just much easier to trigger for Linux users. How this will change in the future if websites start to stress the web browsers' JIT compilers more is anyone's guess.

                    But if you are affected, you can RMA the CPU to AMD and they will send you a working replacement.
                    If I'm going to sell a custom Ryzen PC to someone with the intent of them sticking with Windows, the probability of them running WSL (let alone run a compiler for several minutes at a time) is pretty much a 0% chance. But, thanks for the warning and heads-up anyway - still an interesting tidbit.

                    Comment


                    • #50
                      Originally posted by BillBroadley View Post
                      For those us of who haven't upgraded yet. How do we buy a known good Ryzen from week 30 or newer?
                      There is a very good chance that all the pre-week-25 Ryzens are sold out already in most places. There is pretty high demand for Ryzen CPUs worldwide. If you buy one now, I would assume it would very likely be a newer one, especially if you buy from Amazon or other big vendor that goes through a high volume of product. If you buy in person / in a physical shop, you can have a look at the CPU through the window in the box and see the number for yourself, to be certain. Even if you buy online and get one of the older CPUs, you can send it to AMD and they will replace it with a new one.

                      Comment

                      Working...
                      X