Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!caip!nike!ucbcad!ucbvax!jade!lapis!oster
From: oster@lapis.berkeley.edu (David Phillip Oster)
Newsgroups: net.periphs,net.micro,net.wanted
Subject: Re: 192000 on a Mac, (was update on **real** 19200 CRT)
Message-ID: <1108@jade.BERKELEY.EDU>
Date: Sun, 17-Aug-86 22:04:38 EDT
Article-I.D.: jade.1108
Posted: Sun Aug 17 22:04:38 1986
Date-Received: Tue, 19-Aug-86 04:02:13 EDT
References: <671@mordred.purdue.UUCP> <71@winfree.UUCP> <2349@cbosgd.UUCP> <604@ulowell.UUCP> <15071@ucbvax.BERKELEY.EDU> <855@usl.UUCP>
Sender: usenet@jade.BERKELEY.EDU
Reply-To: oster@lapis.berkeley.edu.UUCP (David Phillip Oster)
Organization: University of California, Berkeley
Lines: 20
Keywords: Amiga,Macintosh, calculator gymnastics, scrolling speed
Xref: watmath net.periphs:1185 net.micro:15385 net.wanted:9435

In article <855@usl.UUCP> elg@usl.UUCP (Eric Lee Green) writes:
>A Macintosh won't run at 19200 baud. To scroll the screen, it needs to
>move 32K of RAM. I would estimate it takes at least 20 clock cycles
>per word to move it, which would be roughly 320,000 clock cycles for...

The actual figures are:
Ram, maximum of 22k screen ram.
10 clock cycles per word (use MOVEM instructions:
@1	MOVEM (a0)+,a2-a6/d1-d7	;64 clock
	MOVEM a2-a6/d1-d7,(a1)+ ;64 clocks
	DBF	d0,@1		;10 clocks
				= 138 clocks to move 54 bytes
				= 55936 to move the whole screen,
almost 6 times faster than Eric Green calculated, and plenty fast enough
to keep up at 19200.  In fact, one of the design goals of the mac was that
it be fast enough to simultaneously write to the floppy, read characters
at 19200, and display them on the screen!
--- David Phillip Oster		-- "The goal of Computer Science is to
Arpa: oster@lapis.berkeley.edu  -- build something that will last at
Uucp: ucbvax!ucblapis!oster     -- least until we've finished building it."