Path: utzoo!attcan!uunet!lll-winken!lll-tis!helios.ee.lbl.gov!pasteur!ames!sgi!daisy!david
From: david@daisy.UUCP (David Schachter)
Newsgroups: comp.arch
Subject: Re: Self-modifying code
Message-ID: <1404@daisy.UUCP>
Date: 19 Jul 88 18:16:01 GMT
References: <5254@june.cs.washington.edu> <76700032@p.cs.uiuc.edu> <1090@ficc.UUCP> <1988Jul18.231158.19500@utzoo.uucp>
Reply-To: david@daisy.UUCP (David Schachter)
Organization: Daisy Systems Corp., Mountain View, Ca.
Lines: 21

In article <1988Jul18.231158.19500@utzoo.uucp> henry@utzoo.uucp (Henry Spencer) writes:
>The dynamic-compilation implementations on
>the Blit et al run the memory at nearly full speed for the usual cases
>of BitBlt; it is fundamentally impossible to do better.  Commodore et al
>find hardware implementations attractive because they don't know how to
>write good software.

I disagree.  It is not necessarily true that good software blit code can
run as fast as hardware supported blit operations.  Sometimes, maybe, but
not always.  Henry's claim "it is fundamentally impossible to do better"
doesn't fly.  What about a CPU with a 16 bit bus competing with a blit
chip with 64 bit access to the frame buffer?  What about a CPU that must
fetch instructions on the same bus used for data?


Henry's statement is over-broad.


					-- David Schachter

#include "disclaimer.legal"
#include "funny.quote"