Closed cmolson closed 2 years ago
After further investigation, the only part of the change that made this work was:
/ maximum time to collect our samples / limit = TSC + 2 1000 clockCyclesPerLatencyUnit();
Which ended up limiting the timeout in cem_unlock.
I will close this and we can come up with a more appropriate change.
I added the ability for the latency to be sub-microsecond. I found with a setting of 4 (0.25us) I was able to crack both 8690719 and 8690720 CEMs that I have here on my bench.
The default is still set to 1, so there should be no noticeable change. I think it is worth it for people with the P1 CEMs like mine to try this out.