Benchmarks

Test System

• 15-inch Macbook Air M2, 2023 (my personal laptop)
• rust-parallel uses 8 parallel jobs by default on this machine
• MacOS 14.2.1

Test Setup

• Run echo on 1000 strings 1 to 1000
• Benchmarks run using hyperfine testing tool
• Link to benchmark script

Summary

• rust-parallel is 1.41 times faster when the path cache is enabled (this is enabled by default)
• rust-parallel is 2.12 times faster than xargs with 8 processes. Note that this use of xargs does not prevent output interleaving.
• rust-parallel is 11.90 times faster than GNU parallel

Versions

$ rust-parallel -V
rust-parallel 1.14.0

$ parallel -V
GNU parallel 20240122

Results

Benchmark 1: seq 1 1000 | rust-parallel echo
  Time (mean ± σ):     163.2 ms ±   0.9 ms    [User: 216.8 ms, System: 593.0 ms]
  Range (min … max):   161.1 ms … 164.7 ms    17 runs

Benchmark 2: seq 1 1000 | rust-parallel --disable-path-cache echo
  Time (mean ± σ):     229.7 ms ±   1.4 ms    [User: 259.2 ms, System: 886.7 ms]
  Range (min … max):   227.5 ms … 232.1 ms    13 runs

Benchmark 3: seq 1 1000 | xargs -P8 -L1 echo
  Time (mean ± σ):     346.7 ms ±   1.8 ms    [User: 153.3 ms, System: 516.1 ms]
  Range (min … max):   342.5 ms … 349.3 ms    10 runs

Benchmark 4: seq 1 1000 | parallel echo
  Time (mean ± σ):      1.943 s ±  0.021 s    [User: 2.539 s, System: 3.510 s]
  Range (min … max):    1.922 s …  1.997 s    10 runs

Summary
  seq 1 1000 | rust-parallel echo ran
    1.41 ± 0.01 times faster than seq 1 1000 | rust-parallel --disable-path-cache echo
    2.12 ± 0.02 times faster than seq 1 1000 | xargs -P8 -L1 echo
   11.90 ± 0.14 times faster than seq 1 1000 | parallel echo