Li Benchmarks

num_fft_r2c greenvalidity pass

Tier 1 · wall_time · N=n=512 · 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: 0.868 (86.8% of rust speed) (table SOTA: rust — best competitor; charts use rust = 1.0)
Best competitor value: 0.0177 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=512 (family num_fft_r2c)
Category: micro
Pillar: numerics
Package: lic
Li / catalog oracle (mean ± σ): 0.0204 ± 0.001903 s (n=48) / 0.019 ± 0.001566 s (n=45) (cpp)
Ratio vs catalog oracle: 1.0737×
Best competitor: rust (0.0177 s)
Li relative speed vs SOTA: 0.868 (1.0 = rust speed)
Validity: validity pass
Threshold: 1.2×
Source: lic/benchmarks/workloads/tier1_micro/num_fft_r2c

PH ids: PH-5b

Compare oracle: cpp

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

Language comparison
Lang	Mean ± σ	Runs	Unit	Variant	OS
li	0.0204 ± 0.001903	48	s	release	linux
cpp	0.019 ± 0.001566	45	s	release	linux
rust	0.0177 ± 0.000927	56	s	release	linux
julia	0.0188 ± 0.001404	57	s	release	linux
Metric: wall_time (value = mean of timed runs)