Newsgroups: comp.arch
Path: utzoo!henry
From: henry@utzoo.uucp (Henry Spencer)
Subject: Re: Software vs Hardware BitBlt (was: Self Modifying Code)
Message-ID: <1988Jul26.145106.5459@utzoo.uucp>
Organization: U of Toronto Zoology
References: <789@amethyst.ma.arizona.edu>
Date: Tue, 26 Jul 88 14:51:06 GMT

In article <789@amethyst.ma.arizona.edu> chris@spock (Chris Ott) writes:
>     Why assume that the graphics memory and the CPU memory are the same? ...

Because I thought we were talking about low-end systems.  (Okay, I admit,
I know of low-end systems that have separate graphics memories, but one
should think twice about the cost-effectiveness.)

>... a 32 bit BitBlt
>chip is going to be much cheaper than a 32 bit microprocessor. 

Oh?  Why?

(I can see a simple BitBlt chip being cheaper than a bloated, baroque 32-bit
micro.  But cheaper than a simple 32-bit micro?  Why?)

>     I wouldn't be so sure. Where I work, we have both IRISes and Suns. The
>Suns have software graphics and the IRISes have hardware graphics. [The
>Irises are faster for polygon graphics.]

Believe me, I know this; we have an Iris too.  Have you *priced* the
difference, though?  Also, I was talking BitBlt, not polygon graphics;
they are *not* the same thing.

>...remember that Sun _does_ supply a graphics
>board, if you want to pay extra for it...

Correct me if I'm wrong, but I believe that graphics board is only for
their color display subsystem, and (like the Iris hardware) specializes
in polygon graphics.

>     Finally, remember, the Suns (at least the 3/280) is running a 25Mhz
>68020, while the IRIS is only running a 16Mhz 68020. If the IRISes were
>running at 25Mhz, like the Suns, they'd be even faster yet.

For the price of the Iris graphics hardware, you could do a lot more to
a 68020 than just boost the clock speed a few MHz.
-- 
MSDOS is not dead, it just     |     Henry Spencer at U of Toronto Zoology
smells that way.               | uunet!mnetor!utzoo!henry henry@zoo.toronto.edu