By: Jukka Larja (roskakori2006.delete@this.gmail.com), January 1, 2021 9:58 pm
Room: Moderated Discussions
Gabriele Svelto (gabriele.svelto.delete@this.gmail.com) on January 1, 2021 3:31 pm wrote:
> Jukka Larja (roskakori2006.delete@this.gmail.com) on January 1, 2021 10:43 am wrote:
> > Trying to google about how well the unofficial support works, I get lot of hits about people saying that
> > yes, it works, without any proof. I don't see people with a test DIMMs known to produce single bit errors
> > making sure the unofficial support works, or making sure it works in every CPU or at least gives some easy
> > to see error somewhere if it doesn't (I'm sure someone somewhere has tested something, but it gets lost
> > in the noise. Anecdotes are only useful if there's enough of them to be statistically significant).
> >
> > I really like what AMD is doing with CPUs, but unofficial ECC support just
> > annoys me. It's supposed to give me peace of mind and eliminate one source
> > of random problems. "Unofficial" really doesn't work great with that goal.
>
> I wrote an article on how to monitor ECC memory on Linux. On my Ryzen machine I could inject
> errors just by overclocking the memory. I used Crucial CT16G4WFD8266 DIMMs, clocking them over
> 3000MHz would cause them to throw out single-bit errors which were corrected and reported.
Thanks, that's very nice. However, it doesn't tell me much about why is AMD calling it "unofficial" support. Will 1 in 4 CPU have non-working ECC? 1 in 100? Or will Windows refuse to enable ECC error reporting if support isn't official? Is it the same for new Zen 3 Ryzens?
In most cases, I just rather buy an actual server CPU.
-JLarja
> Jukka Larja (roskakori2006.delete@this.gmail.com) on January 1, 2021 10:43 am wrote:
> > Trying to google about how well the unofficial support works, I get lot of hits about people saying that
> > yes, it works, without any proof. I don't see people with a test DIMMs known to produce single bit errors
> > making sure the unofficial support works, or making sure it works in every CPU or at least gives some easy
> > to see error somewhere if it doesn't (I'm sure someone somewhere has tested something, but it gets lost
> > in the noise. Anecdotes are only useful if there's enough of them to be statistically significant).
> >
> > I really like what AMD is doing with CPUs, but unofficial ECC support just
> > annoys me. It's supposed to give me peace of mind and eliminate one source
> > of random problems. "Unofficial" really doesn't work great with that goal.
>
> I wrote an article on how to monitor ECC memory on Linux. On my Ryzen machine I could inject
> errors just by overclocking the memory. I used Crucial CT16G4WFD8266 DIMMs, clocking them over
> 3000MHz would cause them to throw out single-bit errors which were corrected and reported.
Thanks, that's very nice. However, it doesn't tell me much about why is AMD calling it "unofficial" support. Will 1 in 4 CPU have non-working ECC? 1 in 100? Or will Windows refuse to enable ECC error reporting if support isn't official? Is it the same for new Zen 3 Ryzens?
In most cases, I just rather buy an actual server CPU.
-JLarja