Path: utzoo!utgpu!watmath!clyde!att!osu-cis!tut.cis.ohio-state.edu!unmvax!gatech!hubcap!Gary From: gld@cunixd.cc.columbia.edu (Gary L Dare) Newsgroups: comp.parallel Subject: Re: Superlinear Message-ID: <3812@hubcap.UUCP> Date: 9 Dec 88 17:42:02 GMT Sender: fpst@hubcap.UUCP Lines: 13 Approved: parallel@hubcap.clemson.edu In article <3801@hubcap.UUCP> mmh@ivax.doc.imperial.ac.uk wrote: >As a simple demonstration,.... [had to edit out excessive included text] >So 2 processors give you a speedup of 4 Q.E. Wait! You still have to search your promising branch thoroughly on the first processor; that's 11 steps, not 1. The fastest turnaround time if you have each branch ALREADY residing on seperate processors is 11 if they are searched simultaneously; master-slave, it's 13.-- ~~~~~~~~~~~~~~~~~~~~~~~~ je me souviens ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Gary L. Dare > gld@eevlsi.ee.columbia.EDU > gld@cunixd.cc.columbia.EDU "Free Canada, Trade Mulroney!" > gld@cunixc.BITNET