The Raspberry Pi project was originally intended to promote basic computer science teaching in schools, but its low price and high quality have also made it popular among enthusiasts. Today, Raspberry Pi boards are used in various hobby projects, and developers are constantly improving the device's compatibility with Linux-based operating systems.
Single-board computers (SBCs) developed by the Raspberry Pi Foundation are designed for low-energy projects and affordable custom computing devices, but there's always room for improvement on the software side. Most RaspberryPi-compatible operating systems (including the official RaspberryPi operating system) use the Linux kernel, which has recently been updated with two patches designed to enhance functionality.
The first patch implements initial "suspend-to-idle" (s2idle) support for the Arm-based BCM2835SoC, which is the chip used by earlier models of RaspberryPi (Pi1 through Pi3). Developer Stefan Wahren focused on this specific SoC because it's less complex than those used in later models and has ample documentation.
LinuxS2idle is a pause state defined by the ACPI standard, a power management technology used by operating systems to manage energy in PCs and other computing devices. ACPI includes four different pause states (S0, S1, S3, S4), of which S4 is the hibernation state, which saves RAM contents to disk before shutting down.
S2idle can put the machine into "freeze" mode, stopping the device from running. The Raspberry Pi-focused patch saves a small amount of energy, just one-third of a watt. While this may seem trivial, it becomes even more significant when you consider the millions of Raspberry Pi devices currently in use.
The second patch adds a "very simple" implementation of NUMA (Non-Uniform Memory Access) emulation for the arm64 platform. NUMA is a well-known technology in the Linux world that optimizes memory access by dividing physical RAM into blocks. According to the patch developer, the memory controller used by the Raspberry Pi5 (BCM2712) can better exploit the parallelism of the physical organization of the memory chips through specific allocation strategies (such as interleaving).
The final result of the NUMA simulation is that the performance of the RaspberryPi5 board has been "significantly" improved. The results of Geekbench6 show that single-core performance has increased by 6% and multi-core performance has increased by 18%. The patch developer also noted that the default Linux allocation strategy is not staggered and that "further steps" are needed to achieve performance improvements in the Raspberry Pi 5 project.