Click here to Skip to main content
15,886,873 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
I'm looking for a way to get a Core Effective Frequency without access to SMU or using APIs. According to AMD:

Core Effective Frequency (without halted cycles) over the sampling period, reported in GHz. The metric is based on APERF and MPERF MSRs. MPERF is incremented by the core at the P0 state frequency while the core is in C0 state. APERF is incremented in proportion to the actual number of core cycles while the core is in C0 state.

I searched through performance counters, and while there are C1, C2, and C3 states, C0 that is required to calculate an effective frequency is missing. My question is, is it called differently in Performance counters, or it's just not there? If not, can this counter be created or imported? And if it's not possible too, is there any other way to get an effective frequency of the core?

What I have tried:

Tried to use C1 for the formula instead of C0, but it produce meaningless (unrealistic results, such as 7500MHz core frequency)
Posted
Updated 5-Feb-22 19:46pm

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900