Announcement

Collapse
No announcement yet.

AMD Ryzen 9 3900X Linux CPU Frequency Scaling Governor Benchmarks

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

  • #11
    Originally posted by davidbepo View Post
    no power usage numbers?
    "The power consumption between the modes weren't compared due to the WattsUp Pro meters being busy on other systems and this testing was done prior to the recent Windows/Linux power discoveries; in fact, this testing was from back in July albeit slipped under the radar for publishing these figures...The next round of Ryzen CPUFreq benchmarks will also be looking at the performance-per-Watt metrics, but generally from our past findings have shown those to be close as well."

    I only have 2~3 working WattsUp Pro meters. Unfortunately the company went out of business like 2 or 3 years back. I've tried buying several used ones off eBay and the like, but they all are borked. There is a known problem where after lots of extended use, they begin reporting like ~0 Watt usage.
    Michael Larabel
    https://www.michaellarabel.com/

    Comment


    • #12
      Originally posted by numacross View Post

      According to AMD the maximum temperature for 3900X is 95°C. My 3700X only hit that while forcing manual overclock in prime95 AVX2 on the stock cooler, as I was experimenting. It did not crash but reduced clocks instead.

      After days of playing I found out that stock settings resulted in the best ST performance while having marginally worse MT than all-core OC (which reduced ST). With current BIOSes overclocking the CPU looks to be simply not worth it on Zen 2
      I'm not overclocking it. Only using XMP profile for RAM (3600MHz / CL16).

      Comment


      • #13
        Originally posted by shmerl View Post
        Did anyone encounter reboots during heavy load? My Ryzen 9 3900X / Asrock X570 Taichi (firmware 2.0) starts rebooting when CPU temperature reaches somewhere between 70°C and 80°C. For example when building Linux kernel.
        I'd run a memtest86 for a few passes to see if you have some bad RAM. The only time I've encountered reboots during heavy loads was a bad stick of RAM.

        Comment


        • #14
          Originally posted by AndyChow View Post

          I'd run a memtest86 for a few passes to see if you have some bad RAM. The only time I've encountered reboots during heavy loads was a bad stick of RAM.
          Thanks. That's the one that comes with SystemRescueCD? Is there some version of it that works with UEFI, or they are all legacy BIOS?

          I.e. the one I know is memtest86+: https://www.memtest.org

          Comment


          • #15
            Originally posted by Michael View Post

            "The power consumption between the modes weren't compared due to the WattsUp Pro meters being busy on other systems and this testing was done prior to the recent Windows/Linux power discoveries; in fact, this testing was from back in July albeit slipped under the radar for publishing these figures...The next round of Ryzen CPUFreq benchmarks will also be looking at the performance-per-Watt metrics, but generally from our past findings have shown those to be close as well."

            I only have 2~3 working WattsUp Pro meters. Unfortunately the company went out of business like 2 or 3 years back. I've tried buying several used ones off eBay and the like, but they all are borked. There is a known problem where after lots of extended use, they begin reporting like ~0 Watt usage.
            ah, okay but i hope the next round is soon

            Comment


            • #16
              Originally posted by shmerl View Post
              Did anyone encounter reboots during heavy load? My Ryzen 9 3900X / Asrock X570 Taichi (firmware 2.0) starts rebooting when CPU temperature reaches somewhere between 70°C and 80°C. For example when building Linux kernel.
              Some of the early firmware was setting the voltage higher than it needed to be on the asrock boards. That could be the issue. See if there is a bios update.

              Aside from that, make sure the cooler is mounted well and coming in good contact with the chip. Also check air flow with your case.

              Comment


              • #17
                Originally posted by shmerl View Post
                I'm not overclocking it. Only using XMP profile for RAM (3600MHz / CL16).
                Well you are overclocking your RAM since the maximum official speed for Ryzen 3000 is 3200MHz. I'd try going 3200CL14 if your sticks can manage and testing both configurations with prime95 Large FFTs.

                I stopped trusting memtest because when I was tuning my RAM it ran fine for a few hours while prime95 detected errors after just 2 minutes of running

                Comment


                • #18
                  Something is terribly wrong with Ryzen 3000 CPUs under Linux or CPU governors.

                  There must not be a big difference between tasks which run for a long time (e.g. video encoding), yet Michael has shown that Ondemand and Performance governors differ by up to 10% which is simply insane.

                  Comment


                  • #19
                    Originally posted by numacross View Post

                    Well you are overclocking your RAM since the maximum official speed for Ryzen 3000 is 3200MHz. I'd try going 3200CL14 if your sticks can manage and testing both configurations with prime95 Large FFTs.

                    I stopped trusting memtest because when I was tuning my RAM it ran fine for a few hours while prime95 detected errors after just 2 minutes of running
                    Is stressapptest enough for that? I run it a few times, and it was fine.

                    Comment


                    • #20
                      Originally posted by shmerl View Post
                      Is stressapptest enough for that? I run it a few times, and it was fine.
                      I have no experience with that particular software, but from their readme: "It is moderately good at catching bad memory cells and cache coherency issues". I consider a nightly run of prime95 large FFTs enough for "proving" RAM stability.

                      Comment

                      Working...
                      X