Lucian Silistru commented on a discussion: 
https://gitlab.rtems.org/rtems/rtos/rtems/-/issues/5486#note_142482


I tried to and turns out the frequency ratios are not enough for the issue; it 
was a simulator issue not updating mtime correctly on harts other than 0 when 
hart 0 is in wfi.

As an aside, what I did find was that there were ~92 instructions between the 
mtime reads in the pc trace. While very unlikely (silicon will add a lot of 
other latencies) some cpus we use do have >100:1 mcycle:mtime frequency ratios.

So, not an issue for now. Can close this.

-- 
View it on GitLab: 
https://gitlab.rtems.org/rtems/rtos/rtems/-/issues/5486#note_142482
You're receiving this email because of your account on gitlab.rtems.org.


_______________________________________________
bugs mailing list
[email protected]
http://lists.rtems.org/mailman/listinfo/bugs

Reply via email to