daveb@geac.UUCP (David Collier-Brown) (07/28/88)
In article ... henry@utzoo.uucp (Henry Spencer) writes: | I agree that it's possible to break the hardware in such a way that a | software BitBlt is inherently slow. I prefer unbroken hardware myself. From article <1152@ficc.UUCP>, by peter@ficc.UUCP (Peter da Silva): | "I agree that it's possible to break the hardware in such a way that a | hardware BitBlt is inherently slow. I prefer unbroken hardware myself." Ok, we have a disagreement, but not over self-modifying code... peter continues: | I have always been uncomfortable with the idea of having your main CPU | throwing all those display bits around anyway... hell, given the price | of the 68030 it might pay Sun to stick an extra one in there to unload | *all* of the display management from the main CPU. If you will have a look at Foley & Van Dam[1], you will notice a cycle of main cpu software -> added hardware assist -> auxiliary special-purpose cpu -> auxiliary general-purpose cpu -> upgrading of the auxiliary cpu to a "main" cpu and then around the circle again. This tends to imply that there are ***AT LEAST*** two solutions to the cost-performance equation for graphics displays. Maybe we can agree to disagree? (not that this discussion wasn't interesting and fruitful, just that its starting to sound a little acrimonious...) --dave c-b [1] A computer graphics textbook, currently setting on my shelf at home. Eggs expected any day now. -- David Collier-Brown. {mnetor yunexus utgpu}!geac!daveb Geac Computers Ltd., | Computer science loses its 350 Steelcase Road, | memory, if not its mind, Markham, Ontario. | every six months.
jkrueger@daitc.ARPA (Jonathan Krueger) (08/03/88)
In article <3089@geac.UUCP> daveb@geac.UUCP (David Collier-Brown) writes: > If you will have a look at Foley & Van Dam[1], you will notice a >cycle of main cpu software -> added hardware assist -> auxiliary >special-purpose cpu -> auxiliary general-purpose cpu -> upgrading of >the auxiliary cpu to a "main" cpu and then around the circle again. Also noted in Bell, Mudge, & McNamara, "Computer Engineering: A DEC view of hardware systems design", Digital Press: 1978, page 201: "An observation that display and other specialized processors evolve in a fashion called the `wheel of reincarnation'" Which observation they attribute to Myer and Sutherland, "On the Design of Display Processors", Communications of the ACM, 11(6):410-414, June 1968. How to divide up the work between general (central) and special purpose hardware? Depends on relative costs of computation versus communication. 68020's made computation cheaper. Blitters made communications cheaper. And all tradeoffs depend on where you are on the wheel of reincarnation. Ready for another spin, anyone? -- Jonathan Krueger uunet!daitc!jkrueger jkrueger@daitc.arpa (703) 998-4777 Inspected by: No. 15