Path: utzoo!utgpu!jarvis.csri.toronto.edu!cs.utexas.edu!samsung!usc!snorkelwacker!spdcc!esegue!johnl From: johnl@esegue.segue.boston.ma.us (John R. Levine) Newsgroups: comp.arch Subject: Re: Inverted Page Tables Message-ID: <1990Feb23.022235.1178@esegue.segue.boston.ma.us> Date: 23 Feb 90 02:22:35 GMT References: <9708@spool.cs.wisc.edu> <20270@cfctech.cfc.com> <11112@encore.Encore.COM> <753@dgis.dtic.dla.mil> <3606@uceng.UC.EDU> <757@dgis.dtic.dla.mil> <4852@scolex.sco.COM> <29718@brunix.UUCP> <6998@celit.fps.com> <43367@ames.ar Reply-To: johnl@esegue.segue.boston.ma.us (John R. Levine) Followup-To: comp.misc Organization: Segue Software, Cambridge MA Lines: 19 In article <8115@pt.cs.cmu.edu> lindsay@MATHOM.GANDALF.CS.CMU.EDU (Donald Lindsay) writes: >The inverted table (+ hash table and chains) mostly gets in the way >when the software wants aliasing. Since the hardware designers knew >that AIX does aliasing, could you explain why they still went with >the inverted approach? The ROMP hardware was designed some years before any AIX work began. When I first started to talk to IBM about the software work that evolved into AIX, the ROMP and Rosetta were already being fabricated. It is my impression, not backed up by any hard facts, that the original intention was for the ROMP's operating system to be more like the System/38's with a single level store, and they went with Unix when it became clear that the original plan was too hard and had too limited a market. This is straying from architectural issues. Followups elsewhere. -- John R. Levine, Segue Software, POB 349, Cambridge MA 02238, +1 617 864 9650 johnl@esegue.segue.boston.ma.us, {ima|lotus|spdcc}!esegue!johnl "Now, we are all jelly doughnuts."