![]() ![]() Thankfully powermetrics quickly disabuses of that gross error: 100% active residency of an E core running at maximum frequency uses around 100 mW, and the same active residency of a P core running at its higher maximum frequency uses ten times that amount, 1000 mW.īecause macOS controls the frequency of E cores on different M1 chips differently, your results won’t be consistent across different Mac models. Activity Monitor is oblivious of that, and doesn’t correct its CPU values to allow for frequency changes.Ī little study of the figures given for energy show they’re essentially the same as CPU, and that, regardless of frequency or core type, full active residency of a core counts as 100% CPU and 100 energy units, just as they would on an Intel processor with its identical cores. Although this is fiddly, the effort is worth it: with the single thread, the E cores run at a frequency of about 972 MHz, but with two threads that increases to their maximum of 2064 MHz. To discover how Activity Monitor is coming to those false results, you’ll need to run the command tool powermetrics to discover the frequencies the two E cores were running at, and their actual power consumption. So running twice the amount of code on E cores alone takes the same amount of energy, according to Activity Monitor. Running two threads has a total energy of 1940, at 970 per thread. The single thread has a total energy of 1931 units.s, at 1931 per thread.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |