home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!sun-barr!cs.utexas.edu!torn!utzoo!henry
- From: henry@zoo.toronto.edu (Henry Spencer)
- Subject: Re: MVC and MVCL (was Re: RISC Mainframe)
- Message-ID: <BrrBvA.E0w@zoo.toronto.edu>
- Date: Tue, 21 Jul 1992 21:04:21 GMT
- References: <1992Jul14.181115.1@eagle.wesleyan.edu> <e83w02h719R301@JUTS.ccc.amdahl.com> <BrM7Mw.DIp@zoo.toronto.edu> <1992Jul19.212901.8857@bcars64a.bnr.ca>
- Organization: U of Toronto Zoology
- Lines: 21
-
- In article <1992Jul19.212901.8857@bcars64a.bnr.ca> schow@bqneh3.bnr.ca (Stanley T.H. Chow) writes:
- >>Of course, a RISC bigot like me :-) would say that this means your machine
- >>is unbalanced: the hardware has useful capabilities that the software is
- >>unable to exploit in a general-purpose way. A straight byte-for-byte copy
- >>is not the only thing one might want to do at top speed...
- >
- >Ah, I see you belong to the rewrite-code-for-each-new-machine school
- >of programming. Otherwise, how do you write optimal loops that depend
- >on the cache line transfer size?
-
- One obvious possibility is to generate them automatically, perhaps even
- on the fly, perhaps just in a shared library.
-
- The fact is, rewriting the code -- in some way, not necessarily involving
- human effort or maintaining multiple versions -- *makes it run faster*.
- If it's worth the trouble, you find a way to do it. If it's worthwhile
- for bcopy, it's probably worthwhile for (some) other things for at least
- some customers... if the machine will let you.
- --
- There is nothing wrong with making | Henry Spencer @ U of Toronto Zoology
- mistakes, but... make *new* ones. -D.Sim| henry@zoo.toronto.edu utzoo!henry
-