zp-aos-single-field — aos-single-field
Claim
AoS sum one field vs parallel []u32 SoA under Zig 0.17.0 -Ofast on this Linux machine shows a clear before/after wall-clock gap.
How measured
- Harness:
packages/zperf/examples/bench/evidence_fill.zig(rulezp-aos-single-fieldcases) - Build:
zig build-exe -Ofast· optimize_mode=fast - Timing:
Io.Clockawake; warm=2; median of 9 rounds - before:
aos_sum_hp - after:
soa_sum_hp - ops=4000000
- Raw:
zp-aos-single-field.jsonl
Runtime (this evidence file)
| Field | Value |
|---|---|
| When | 2026-10-21 Asia/Shanghai (JSONL ts is UTC) |
| Zig | 0.17.0 · fast |
| Median before | ~4.801 ms |
| Median after | ~0.731 ms |
| ratio before/after | ~6.57× |
Lint mapping
zperf-lint zp-aos-single-field / aos-single-field. Default severity in rules.zig is off (the CLI does not report the rule); see evidence-policy for keep/escalate. Evidence exists and agrees directionally.
Verdict
Agree ~6.57× when only one field is hot (fat Element).
Limits
Other loops may touch all fields — lint is a review hint.