Benchmarks - aaronriekenberg/rust-parallel GitHub Wiki

Test System

  • 15-inch Macbook Air M2, 2023 (my personal laptop)
  • rust-parallel uses 8 parallel jobs by default on this machine
  • MacOS 14.3.1

Test Setup

Summary

  • rust-parallel is 1.28 times faster when the path cache is enabled (this is enabled by default)
  • rust-parallel is 1.53 times faster than xargs with 8 processes. Note that this use of xargs does not prevent output interleaving.
  • rust-parallel is 12.20 times faster than GNU parallel

Versions

$ rust-parallel -V
rust-parallel 1.17.0

$ parallel -V
GNU parallel 20240222

Results

Benchmark 1: seq 1 1000 | rust-parallel echo
  Time (mean ± σ):     157.8 ms ±   0.8 ms    [User: 221.4 ms, System: 606.8 ms]
  Range (min … max):   156.0 ms … 159.2 ms    18 runs

Benchmark 2: seq 1 1000 | rust-parallel --disable-path-cache echo
  Time (mean ± σ):     202.6 ms ±   1.3 ms    [User: 234.0 ms, System: 836.7 ms]
  Range (min … max):   200.7 ms … 204.8 ms    14 runs

Benchmark 3: seq 1 1000 | xargs -P8 -L1 echo
  Time (mean ± σ):     242.2 ms ±   1.1 ms    [User: 144.3 ms, System: 509.8 ms]
  Range (min … max):   240.6 ms … 243.9 ms    12 runs

Benchmark 4: seq 1 1000 | parallel echo
  Time (mean ± σ):      1.925 s ±  0.011 s    [User: 2.543 s, System: 3.530 s]
  Range (min … max):    1.910 s …  1.945 s    10 runs

Summary
  seq 1 1000 | rust-parallel echo ran
    1.28 ± 0.01 times faster than seq 1 1000 | rust-parallel --disable-path-cache echo
    1.53 ± 0.01 times faster than seq 1 1000 | xargs -P8 -L1 echo
   12.20 ± 0.09 times faster than seq 1 1000 | parallel echo