Wayne Thornton commented: 
https://gitlab.rtems.org/rtems/rtos/rtems/-/issues/5548#note_150788


I've done some significant work on the API and just ran the first hedged read 
test (smpdhrl01.exe) on a Skylake processor on my Latitude E7470. The purpose 
of the test is to determine whether the code is properly sending hedged reads 
on the memory bus. The closer to a 50/50 split, the better. Of course these 
results will fluctuate across runs due to tail latency, jitter, etc but so long 
as one channel is higher than the other but no so much as to be wonky, we know 
the code is doing what it should.

![Capture](/uploads/2dca985cc4e9ddda60a673627e040dba/Capture.PNG){width=837 
height=370}

-- 
View it on GitLab: 
https://gitlab.rtems.org/rtems/rtos/rtems/-/issues/5548#note_150788
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