Re: PROBLEM: Probabilistic segfault on AMD hardware with INVLPGB

[Rik van Riel]

On Tue, 2026-07-07 at 13:18 +0100, Matt Fleming wrote:
> Hi Rik and Henrik,
> 
> I've got a small C reproducer that triggers this within the first
> round
> on Cloudflare's AMD Turin machines:
> 
>   https://gist.github.com/mfleming/ca26ad3f8d65a12d23d62fb176480fc1
> 
> Build:
> 
>   gcc -O2 -Wall -Wextra -pthread -static -o repro-invlpgb repro-
> invlpgb.c
> 
> Run:
> 
>   ./repro-invlpgb --batch --rounds 20 --jobs 32 -d 5 -w 8 -m 2 -s 512
> -q
> 

Now that's interesting. I ran it for 100 rounds on
a 158 core Turin system, without hitting the issue.

I'll play around with it some more to see whether
I can make it happen by varying the parameters,
but now I'm also wondering whether hardware
differences might be at play.

-- 
All Rights Reversed.