Path: utzoo!attcan!uunet!know!cs.utexas.edu!sun-barr!newstop!exodus!exodus-bb!khb From: khb@chiba.Eng.Sun.COM (Keith Bierman - SPD Advanced Languages) Newsgroups: comp.arch Subject: Re: speculative execution Message-ID: Date: 9 Oct 90 17:52:43 GMT References: <1990Oct9.162639.23516@rice.edu> Sender: news@exodus.Eng.Sun.COM Organization: Sun MegaSystems Lines: 21 In-reply-to: preston@titan.rice.edu's message of 9 Oct 90 16:26:39 GMT In article <1990Oct9.162639.23516@rice.edu> preston@titan.rice.edu (Preston Briggs) writes: You could probably do it in hardware too (that it, go shooting off down some code path before knowing a condition), but I expect compilers can do a better job. Think in terms of trace scheduling. At the Hot Chips forum (and at M/S too, from the preprogram notes) LSI gave some details its "Lightning" chip. By having hw support one can execute instructions before knowing if they are legal. The MF/trace machine lost big time when they predicted wrong .... this limits the length of speculative traces, and the applications for which you get speedup. Compilers can't do everything ;> -- ---------------------------------------------------------------- Keith H. Bierman kbierman@Eng.Sun.COM | khb@chiba.Eng.Sun.COM SMI 2550 Garcia 12-33 | (415 336 2648) Mountain View, CA 94043