generation Alder Lake processors Intel introduced a radical change which it didn’t sit well with Linux. For those lost, Alder Lake has released a hybrid architecture that combines high and low performance cores in the same package. The chip giant focused its work on Windows, leaving Linux as a second course, making Microsoft’s system clearly superior to Alder Lake in initial comparisons.
Of course, this news did not go unnoticed by the Linux kernel developers, who went to work to at least close the gap. The first blow came with Linux 5.16, which included a patch that significantly improved performance by making more intelligent use of high-performance cores. The situation improved a little more in Linux 5.18, although without completely surpassing Windows, with the introduction of features and support for technologies included specifically for Alder Lake.
Many months after the release of Alder Lake processors, Intel continues to contribute to Linux to improve performance. Ricardo Neri, engineer Dedicated to Linux, Intel has released a new patch that is said to improve task scheduling between P (high performance) and E (low performance) cores..
Neri explained that “Intel processors that support Intel Turbo Boost Max 3.0 use ‘asym_packing’ to assign higher priority to higher clocked processors.” However, it artificially assigns lower priority to higher-numbered SMT siblings to ensure they are used last. This results in unnecessary job migrations across SMT domains.”
“On processors with a mixture of higher frequency SMT cores (P cores) and lower frequency non-SMT cores (E cores), the lower priority CPU transfers tasks from the higher priority cores if there is more than one. Brother SMT busy.”
“Don’t use different priorities for each SMT sibling. Instead, modify the ‘asym_packing’ load balancer to recognize SMT cores with more than one busy sibling and allow lower priority CPUs to perform tasks. Removing these artificial priorities prevents unnecessary migrations and allows lower priority cores to check all SMT siblings for the busiest queue.“.
Despite his position as an engineer, Neri’s explanation is simple enough to understand that the purpose of the patch is to make smarter use of low- and high-performance cores when processing tasks, low performance cores get a larger share when a high performance core is found to be busy. The expected consequence of applying the patch is that Linux will be able to take better advantage of Alder Lake processors and possibly future Raptor Lake processors.
Intel contributing directly to Linux is not new, as it has been one of the main contributors to the kernel for a very long time. In other words, Intel has a lot of weight in Linux development, even if the relationship with the hard core of kernel developers hasn’t always been idyllic.
