Back in the early days of GNU Parallel a job could be processed within just 3 ms.
These days there are many more checks and much more flexibility has been added - and that costs. So I was curious how the performance of GNU Parallel has changed over time. www.gnu.org/s/parallel/process-time-j8-1.7ghz-300-1000.pdf This was measured on my 4 hyperthreaded cpus (= 8 "cores") forced to run 1.7GHz, so the timings may be lower if you have a faster cpu or if you do not use hyperthreading. So there are a couple of increases that stand out: * 20101122 included a complete rewrite to object orientation. Without this rewrite a lot of the following development would have been much harder. * 20140722 made it possible to use Perl expressions as replacement strings. Without this the elegant '--rpl' would not have been possible. All in all you should expect around 10 ms for starting a job locally using GNU Parallel. /Ole
