Looks at power use and energy efficiency in M3 Pro chips, deriving equations for energy use according to numbers of cores used and their role.
efficiency
Using assembly language test loops to understand the differences between M1 Pro and M3 Pro CPU cores casts new light on their differences.
Once you know how to configure an app to be able to use Game Mode, you can run better tests. Here are measurements of CPU and GPU performance for comparison between Full Screen and Game Mode.
The M2 Pro and Max gain an extra two Efficiency cores, compared to their M1 equivalents. What effect will that have on their performance, and what of the M2 Ultra?
Some threads are set to run in the background, and get allocated to the E cores. Could you run them in a VM, and effectively promote them to run on P cores instead?
How to work out how many threads and which cores are needed to achieve a compression rate up to 1.7 GB/s, and how to estimate power and energy.
When running some tasks confined to E cores, the original M1 chip from 2020 completes them significantly quicker than an on an M1 Pro. Here’s the detail.
Users and other processes have very limited control over which threads are run on which type of core. As Apple Silicon develops, this is an area set for change.
Does your M1 Mac run more slowly when it’s on battery power, or with Low Power mode enabled? An exploration of effects on its CPU cores provides an unexpected answer.
The E cores on the original M1 and M1 Pro chips appear to be managed quite differently, with respect to the performance of background processes at low QoS.
The Eclectic Light Company 