Li Benchmarks

md_energy_drift greenvalidity pass

Tier 2 · wall_time · N=N=256,steps=10000 · variant algo_registry · OS linux

passpass — perf claims allowed when ratio is green

Source: latest.csv:perf_present

Wall-clock row exists only — no explicit correctness signal yet.

Ratio vs best competitor: 1.037 (103.7% of julia speed) (table SOTA: li — Li leads; charts use julia = 1.0)
Best competitor value: 2.0285 s

No analytical verify rows in ingest yet. Run tier-1 with --verify so latest.csv exports verify_ulps / verify_within_1ulp.

Problem size: N=N=256,steps=10000 (family md_energy_drift)
Category: physics
Pillar: physics
Package: lic
Li / catalog oracle (mean ± σ): 2.0285 ± 0.059953 s (n=2) / 2.2029 ± 0.012338 s (n=2) (cpp)
Ratio vs catalog oracle: 0.9208×
Best competitor: li (2.0285 s)
Li relative speed vs SOTA: 1.037 (1.0 = julia speed)
Validity: validity pass
Threshold: 1.2×
Source: lic/benchmarks/workloads/tier2_physics/md_energy_drift

PH ids: PH-5b

Compare oracle: cpp

Relative speed vs best competitor (julia) — SOTA = 1.0, higher is better. Absolute s values are in the table below.

Language comparison
Lang	Mean ± σ	Runs	Unit	Variant	OS
li	2.0285 ± 0.059953	2	s	release	linux
cpp	2.2029 ± 0.012338	2	s	release	linux
rust	2.2093 ± 0.038779	2	s	release	linux
julia	2.1032 ± 0.036495	2	s	release	linux
Metric: wall_time (value = mean of timed runs)