Datasheet / Specimen v0.1 · Raspberry Pi 5 · 2026-03-14

Measured,
not argued.

Hardware numbers from a Raspberry Pi 5 (Cortex-A76 @ 2.4 GHz, frequency scaling disabled), captured via the Pi Debug Probe over UART. Linux baseline measured on the same board with `cyclictest` and `dmesg`. Methodology in the kernel repo at docs/benchmarks.md.

§ 01 / headline
rpi5 · hardware
Interrupt latency
211 ns avg
hardware vector → bpf entry
10× vs Linux
Boot to init
99 ms
kernel timer to /init
5.8× vs Linux
BPF load
<1 µs avg
at 54 MHz resolution limit
25× vs Linux
Kernel image
10 MB
kernel8.img (release)
1.5× smaller
§ 02 / side-by-side
lower is better

On the same board,
on the same probe.

We didn't change the hardware; we changed the kernel. The advantage comes from a minimal interrupt path, an embedded rootfs, and a verifier that does its job at load time so the runtime path stays short.

Boot to init unit · ms
axiom
99 ms
linux
573 ms
Kernel image size unit · MB
axiom
10 MB
linux
15 MB
Kernel memory footprint unit · MB
axiom
22 MB
linux
60 MB
BPF load time (2 insn) unit · µs
axiom
1 µs
linux
25 µs
Interrupt latency (avg) unit · µs
axiom
0.211 µs
linux
2 µs
§ 03 / detail
exact values · raw

Interrupt latency · 100 samples

stat value
min203 ns
avg211 ns
max351 ns
samples100

Timer interrupt interval · 100 samples

stat value
min9 999 µs
avg9 999 µs
max10 000 µs
jitter≤ 1 µs

Side-by-side · authoritative table

metric axiomOS (rpi5) linux (rpi5) note
Boot to init99 ms573 msto userspace spawn
Kernel image10 MB~15 MBcompressed
Kernel memory~22 MB~60 MBimage + heap (axiom)
BPF load (2 insn)<1 µs24.80 µsavg of 10
Interrupt latency211 ns~2 µscyclictest
Latency max351 ns7 µsworst-case observed
§ 04 / methodology

platform

Raspberry Pi 5 · 8 GB

Cortex-A76 @ 2.4 GHz · governor pinned to performance · CPU frequency scaling disabled.

capture

Pi Debug Probe

CMSIS-DAP UART · 115 200 baud · kernel markers + userspace `/bin/benchmark`.

linux baseline

RPi OS 64-bit

Linux 6.12.62+rpt-rpi-2712 · cyclictest · 5 cold-boot runs.