Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!samsung!uunet!cbmvax!grr From: grr@cbmvax.commodore.com (George Robbins) Newsgroups: comp.sys.dec Subject: Re: pdp-11's Message-ID: <22673@cbmvax.commodore.com> Date: 25 Jun 91 05:10:08 GMT References: <1991Jun22.041102.1509@spcvxb.spc.edu> <1991Jun24.093746.48196@cc.usu.edu> <1991Jun24.160613.1515@spcvxb.spc.edu> Reply-To: grr@cbmvax.commodore.com (George Robbins) Distribution: comp Organization: Commodore, West Chester, PA Lines: 26 In article <1991Jun24.160613.1515@spcvxb.spc.edu> havemann_l@spcvxb.spc.edu writes: > In article <1991Jun24.093746.48196@cc.usu.edu>, slsw2@cc.usu.edu writes: > > > > I spent a lot of time looking at the QBus and UNIBUS some years ago. With > > block mode the QBus peaks at about 3 1/3 MB/s. UNIBUS peaks at 6 2/3 MB/s; > > a memory module can support this throughput using 70 ns static RAM. > > > > The main problem with UNIBUS as far as modern systems go is that it has a > > limited address range; 256KB as opposed to 4MB for the QBus. > > In the *modern* UNIBUS systems (/24/44/84/94), they have memory mapping - > allowing an address range of 2048K (4 Mb's). Yes, but the unibus itself is has only 2^18 address lines, limited each individual unibus to 256KB. This doesn't really matter much since most systems of either ilk keep main memory on a private memory interconnect of some sort. Q-bus is is cheaper both in system and peripheral implementation, the reasons for having dual flavor systems was partly performance and partly avilability of DEC peripherals for Unibus which at the time didn't have Q-bus equivalents. -- George Robbins - now working for, uucp: {uunet|pyramid|rutgers}!cbmvax!grr but no way officially representing: domain: grr@cbmvax.commodore.com Commodore, Engineering Department phone: 215-431-9349 (only by moonlite)