benbrown/peltier.io
2
1
Fork 0
mirror of https://github.com/bdbrown4/peltier.io.git synced 2026-11-07 10:58:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

bench: GitHub Actions CI — trust-layer checks, no-net gates, runner calibration

Browse Source 
Closes the CI-reachable slice of the Phase 1 infra gaps:
- trust-layer job: cargo test + clippy -D warnings + fmt
- target-gates-no-net: fetches pinned targets (new targets/fetch.sh),
  regenerates + verifies corpora, runs 'just gates tokei'
  mechanically, and executes the bench workload inside a
  --network=none container (SPEC 3.1/10 no-net requirement)
- runner-calibration (informational): A/A + injection harness measures
  the shared runner's noise floor per run, evidence uploaded as an
  artifact — environments are judged empirically, not assumed
- perf-probe (informational): reports which perf event sources work

docs/infra.md maps each remaining hardware requirement (pinned cores,
governor/SMT control, separate-uid trust layer) to the bench-metal
self-hosted runner setup a human can complete in ~15 min.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
This commit is contained in:
Claude
2026-07-07 00:13:21 +00:00
parent 19e83d878a
commit 52089c0451
12 changed files with 375 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/bench-runner/src/stats.rs
+23 -6
View File
@@ -54,7 +54,10 @@ pub fn bootstrap_ratio_ci(
confidence: f64,
seed: u64,
) -> RatioCi {
assert!(baseline.len() >= 2 && candidate.len() >= 2, "need >=2 runs per side");
assert!(
baseline.len() >= 2 && candidate.len() >= 2,
"need >=2 runs per side"
);
assert!((0.0..1.0).contains(&confidence));
let mut rng = XorShift64::new(seed);
let mut ratios = Vec::with_capacity(iters);
@@ -82,7 +85,12 @@ pub fn bootstrap_ratio_ci(
/// Percentile-method bootstrap CI of a single sample's median, for
/// per-side evidence in ledger rows.
pub fn bootstrap_median_ci(sample: &[f64], iters: usize, confidence: f64, seed: u64) -> (f64, f64, f64) {
pub fn bootstrap_median_ci(
sample: &[f64],
iters: usize,
confidence: f64,
seed: u64,
) -> (f64, f64, f64) {
assert!(sample.len() >= 2 && (0.0..1.0).contains(&confidence));
let mut rng = XorShift64::new(seed);
let mut medians = Vec::with_capacity(iters);
@@ -106,7 +114,9 @@ mod tests {
#[test]
fn median_ci_brackets_median() {
let s: Vec<f64> = (0..40).map(|i| 1.0 + 0.01 * ((i * 7) % 11) as f64).collect();
let s: Vec<f64> = (0..40)
.map(|i| 1.0 + 0.01 * ((i * 7) % 11) as f64)
.collect();
let (m, lo, hi) = bootstrap_median_ci(&s, 1000, 0.95, 9);
assert!(lo <= m && m <= hi);
}
@@ -120,15 +130,22 @@ mod tests {
#[test]
fn aa_ci_straddles_one() {
// Same distribution both sides: the CI must contain 1.0.
let sample: Vec<f64> = (0..40).map(|i| 1.0 + 0.01 * ((i * 7) % 11) as f64).collect();
let sample: Vec<f64> = (0..40)
.map(|i| 1.0 + 0.01 * ((i * 7) % 11) as f64)
.collect();
let ci = bootstrap_ratio_ci(&sample, &sample, 2000, 0.95, 42);
assert!(ci.lo <= 1.0 && ci.hi >= 1.0, "A/A CI must straddle 1.0, got {ci:?}");
assert!(
ci.lo <= 1.0 && ci.hi >= 1.0,
"A/A CI must straddle 1.0, got {ci:?}"
);
}
#[test]
fn detects_injected_regression() {
// Candidate 5% slower with mild noise: speedup CI entirely < 1.
let base: Vec<f64> = (0..40).map(|i| 1.0 + 0.002 * ((i * 3) % 7) as f64).collect();
let base: Vec<f64> = (0..40)
.map(|i| 1.0 + 0.002 * ((i * 3) % 7) as f64)
.collect();
let cand: Vec<f64> = base.iter().map(|t| t * 1.05).collect();
let ci = bootstrap_ratio_ci(&base, &cand, 2000, 0.95, 42);
assert!(ci.hi < 1.0, "5% regression must be detected, got {ci:?}");