On Thu, Oct 29, 2026 at 07:29:17PM +0200, Jarkko Sakkinen wrote: > - 93% drop in the combined variance. > - 2.2% increase in the total task time.
Testing in a wide range of chunk sizes (and multiple repetitions) was also done in order to make sure that the bench itself is working correctly. These figure are crazy good IMHO :-) Br, Jarkko
