Fan out parallel array operations across cores

Open depombo opened this issue 5 years ago • 1 comments

AVM to avoid spinning up more than n (cpu core count) instances. map, each, find and all parallel array opcodes should generate n tasks for each cpu core instead of m tasks for each element in the array

Dec 14 '20 18:12 depombo

Implementation should take into account the results of https://github.com/alantech/alan/issues/387

Jan 21 '21 17:01 depombo