hull@hao.UUCP (Howard Hull) (12/23/84)
In <282@bragvax.UUCP> David DiGiacomo says, concerning <18341@lanl.ARPA>: > > Multiplexing these lines only defeats the purpose > > behind going to 64 bits to begin with. > Not necessarily true-- most current (and future) 32 bit microprocessors > and system buses use multiplexed addresses and data. There is very > little performance penalty; addresses and data are naturally separated > in time so they can share a bus effectively. In a response to an earlier net.micro article of mine, Ken Shoemaker of Intel also pointed this out. It was not so much Ken's particular wording of the matter (nor yours) that convinced me that the degree of multiplexing (or lack of it) was not a good figure of merit. The crux of the matter is that *all* VLSI chips use multiplexing *internally* to save on silicon real estate and optimize the architechture. There is a tradeoff between space for buses and space for logical functions. Carrying the resultant state of the internal multiplexing to the outside world does not hurt the overall performance. It only means that external hardware may have to be used to decode the bus traffic, and that I can't dubug it as easily using only an oscilloscope :-) Howard Hull {ucbvax!hplabs | allegra!nbires | harpo!seismo } !hao!hull