Jump to content

Processor affinity

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 131.111.8.101 (talk) at 16:09, 26 April 2003 (Shared Memory multiprocessor Architecture Scheduling Algorithm :: Proccessor Affinity). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

A modification of the naive central queue scheduling algorithm. Each thread in the queue has a tag indicating its prefereed / kin processor. At allocation time, each thread is allocated to ites kin processor. This can effectively reduce cache problems. However, it does not kerb the persistant load-balancing problem.

Retrieved from "https://en.wikipedia.org/w/index.php?title=Processor_affinity&oldid=1171516"