TSC scaling feature - confusion on documentation.

TSC scaling feature - confusion on documentation.

I'm confused about the internal meaning of the product of HostTSC and the TSC multiplier being shifted right 48 bits before being added to the TSC offset. I am also confused about the binary layout of the field.

If for example host frequency was 2.5 ghz, and I wanted a guest reflection of 2.6, my ratio would be 1.04. According to the very short documentation on this field:

Specifically, an affected read from the timestamp co
unter first computes the product of the value of the
IA32_TIME_STAMP_COUNTER MSR and the value of the TS
C multiplier. It then shifts the value of the
product right by 48 bits and loads EAX:EDX with the
sum of that shifted value and the value of the TSC
offset.

Assuming that the final value must be a whole number, what is the meaning of this?

 

2 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

Hello John,

This document online may provide some hint for your case: https://www.ccsl.carleton.ca/~jamuir/rdtscpm1.pdf.

-Thai

Leave a Comment

Please sign in to add a comment. Not a member? Join today