Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Posting-Version: version B 2.10.2 9/18/84; site ucbvax.ARPA Path: utzoo!watmath!clyde!burl!ulysses!cbosgd!ucbvax!info-vax From: info-vax@ucbvax.ARPA Newsgroups: fa.info-vax Subject: MicroVax Message-ID: <4109@ucbvax.ARPA> Date: Thu, 10-Jan-85 00:38:06 EST Article-I.D.: ucbvax.4109 Posted: Thu Jan 10 00:38:06 1985 Date-Received: Fri, 11-Jan-85 23:23:26 EST Sender: daemon@ucbvax.ARPA Organization: University of California at Berkeley Lines: 19 From: stew%lhasa.UUCP@harvard.ARPA From a recent article in Computer Technology Review by three senior engineers from DEC: "At the CPU board level, the performance of the MicroVAX I is superior to the VAX-11/730 at about half its power consumption and printed circuit board space. Depending on the application, the performcance of the MicroVAX I is about 60% of the VAX-11/750 at about 20% of its cost. An original design constraint that influenced that influenced a number of decisions in the design process was a short time-to-market. The main results were the selection of an existing systems package and extremely tight limits on the design of the CPU." The article continues with quite a long, technical discussion of the implementation. It claims a 70% cache hit rate, further improved by block-mode transfers and an instruction prefetch queue. Stew