Brummel
aea3758742
Three drift items from ailang-architect, plus one false-positive
surfaced during verification:
1. DESIGN.md silent on closure-pair 4.14x finding (21'b).
Decision-10 ratified: "Workload scope of the 1.3x target"
paragraph scopes the retirement gate to linear/tree/poly-ADT
workloads; closure-pair carve-out documented as
representational cost (closure cell + env struct = 2 allocs
per step) until a slab/pool answer ships.
2. bench/compile_check.py corpus drift. Three fixtures added
(bench_compute_intsum, bench_compute_collatz,
bench_list_sum_explicit), re-baselined. Now 12 fixtures x
2 ops = 24 compile-time metrics.
3. baseline.json convention not codified. Note field gains
"max-of-distribution gets wider band than percentile"
convention discovered in 21'd.
4. (verification finding) bench_compute_intsum cross_lang
tolerances at 15%/12% fire on subprocess-spawn jitter for
sub-millisecond fixtures. Widened to 35% across all five
intsum metrics; convention recorded in baseline_cross_lang
note field (sub-ms fixtures need looser bands).
All three bench gates re-run sequentially after edits:
bench/check.py — 63 metrics; 63 stable
bench/compile_check.py — 24 metrics; 24 stable
bench/cross_lang.py — 25 metrics; 25 stable
Total: 112 metrics under regression coverage, all green.
288 tests passing, 3 ignored. No Rust changes.
107 lines
2.4 KiB
JSON
107 lines
2.4 KiB
JSON
{
|
|
"version": 1,
|
|
"captured": "2026-05-09",
|
|
"captured_via": "bench/compile_check.py",
|
|
"note": "Compile-time bench. `check_ms` is `ail check FILE`; `build_O0_ms` is `ail build --opt=-O0 FILE`. Wall-clock includes subprocess spawn (~5-10 ms on Linux) and, for build, the clang link step. Tolerances are tuned for noise on a quiet developer machine, not as the language correctness bar.",
|
|
"check_ms": {
|
|
"hello": {
|
|
"baseline_ms": 0.79,
|
|
"tolerance_pct": 25
|
|
},
|
|
"list_map_poly": {
|
|
"baseline_ms": 0.99,
|
|
"tolerance_pct": 25
|
|
},
|
|
"local_rec_capture": {
|
|
"baseline_ms": 0.84,
|
|
"tolerance_pct": 25
|
|
},
|
|
"borrow_own_demo": {
|
|
"baseline_ms": 0.95,
|
|
"tolerance_pct": 25
|
|
},
|
|
"nested_pat": {
|
|
"baseline_ms": 1.77,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_list_sum": {
|
|
"baseline_ms": 0.99,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_tree_walk": {
|
|
"baseline_ms": 1.08,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_closure_chain": {
|
|
"baseline_ms": 0.86,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_hof_pipeline": {
|
|
"baseline_ms": 0.99,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_compute_intsum": {
|
|
"baseline_ms": 0.86,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_compute_collatz": {
|
|
"baseline_ms": 0.94,
|
|
"tolerance_pct": 25
|
|
},
|
|
"bench_list_sum_explicit": {
|
|
"baseline_ms": 0.92,
|
|
"tolerance_pct": 25
|
|
}
|
|
},
|
|
"build_O0_ms": {
|
|
"hello": {
|
|
"baseline_ms": 63.52,
|
|
"tolerance_pct": 20
|
|
},
|
|
"list_map_poly": {
|
|
"baseline_ms": 66.12,
|
|
"tolerance_pct": 20
|
|
},
|
|
"local_rec_capture": {
|
|
"baseline_ms": 65.18,
|
|
"tolerance_pct": 20
|
|
},
|
|
"borrow_own_demo": {
|
|
"baseline_ms": 65.56,
|
|
"tolerance_pct": 20
|
|
},
|
|
"nested_pat": {
|
|
"baseline_ms": 68.26,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_list_sum": {
|
|
"baseline_ms": 66.07,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_tree_walk": {
|
|
"baseline_ms": 67.16,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_closure_chain": {
|
|
"baseline_ms": 64.59,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_hof_pipeline": {
|
|
"baseline_ms": 65.53,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_compute_intsum": {
|
|
"baseline_ms": 63.1,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_compute_collatz": {
|
|
"baseline_ms": 64.92,
|
|
"tolerance_pct": 20
|
|
},
|
|
"bench_list_sum_explicit": {
|
|
"baseline_ms": 64.76,
|
|
"tolerance_pct": 20
|
|
}
|
|
}
|
|
}
|