An Important Note On The Alder Lake Mobile Power/Performance With Linux 5.19

After dealing with the Intel Alder Lake P GuC firmware breakage around Linux 5.19 Git that is now to be addressed by the upstream Intel developers, it was on to performance testing the shiny new Core i7 1280P with this kernel due to be released as stable within the next two weeks... For those concerned about maximum performance, there was a glaring performance regression for this Alder Lake P on the new kernel being released as stable later this month. Well, a default change in performance/behavior at least but the power efficiency / performance-per-Watt tended to be better on this new kernel.

Now having an Intel Core i7 1280P locally for Alder Lake P Linux testing in the form of the MSI Prestige 14Evo A12M-23 as an Intel "Evo" certified notebook, I've been running many Linux benchmarks and exploring it across different software configurations. If Linux 5.19 wasn't bad enough for the GuC firmware breakage, the very same device has a significant performance regression with the out-of-the-box state for current Linux 5.19 Git relative to Linux 5.18 stable... But does appear to be an intentional change trading lower performance for better power efficiency. For benchmarks it has led to lower performance across dozens of workloads.

The very same laptop, the same software aside from swapping out the kernels from the Ubuntu Mainline Kernel PPA. When running Linux 5.18 vs. Linux 5.19 Git as of 13 July, here's the side-by-side comparison:

Scheisse! For the most part, the Linux 5.19 kernel is measurably slower on this brand new Intel Evo laptop relative to Linux 5.18... Though as about to be shown, the power efficiency tends to come out ahead of 5.18. Let's dig into some of these tested workloads.