ok@quintus.uucp (Richard A. O'Keefe) (08/06/88)
In article <1988Aug3.153239.8988@utzoo.uucp> henry@utzoo.uucp (Henry Spencer) writes: >I'm not sure I'd bet on 1.2u CMOS beating the 29000, though: that processor >is *really good* at saturating memory bandwidth. Which leads into my (ignorant) questions: What commercially available boxes use the Am29k? Any idea how many have been installed? How close to 17MIPS do they _really_ get?
daveh@cbmvax.UUCP (Dave Haynie) (08/11/88)
in article <251@quintus.UUCP>, ok@quintus.uucp (Richard A. O'Keefe) says: > In article <1988Aug3.153239.8988@utzoo.uucp> henry@utzoo.uucp (Henry Spencer) writes: >>I'm not sure I'd bet on 1.2u CMOS beating the 29000, though: that processor >>is *really good* at saturating memory bandwidth. > Which leads into my (ignorant) questions: > What commercially available boxes use the Am29k? Any idea how many > have been installed? How close to 17MIPS do they _really_ get? AMD right now, at least, is marketing it as an imbedded controller. If the market believes that, you'd probably find it in a laser printer or similar application, rather than in a UNIX box or some-such. It is an interesting chip -- I like the design philosophy. Instead of the "let's throw out the micro-execution unit and hardwire our instructions" theme of most RISCy chips, the 29K folks said "let's throw out the macro-execution unit and make the micro-execution unit grow up a little". -- Dave Haynie "The 32 Bit Guy" Commodore-Amiga "The Crew That Never Rests" {ihnp4|uunet|rutgers}!cbmvax!daveh PLINK: D-DAVE H BIX: hazy "I can't relax, 'cause I'm a Boinger!"