🚀 go-pugleaf

In article <1992Apr10.201106.9217@news2.cis.umn.edu> wisdom@leghorn.cs.umn.edu  
(Scott Wisdom) writes:
| In article <1992Apr10.091036.3083@whetstone.uucp> whetstone!johnc@ms.uky.edu  
| (John Coppinger) writes:
| > My question is this: is the 88K really that fast?  Does Motorola really  
know  
| > something about RISC that Sun doesn't?  How does Motorola get 75+ MIPS out  
of  
| > their RISC when Sun is working pretty hard to squeeze 30 out of SPARC?  I'm  
| not  
| > a processor freak, so I don't really know about this stuff.  Can someone  
| > enlighten me?
| I think it's pretty fast. From what I understand the 88100 (88000?) wasn't  
all  
| that great. Motorola has been working on the 88110 for quite some time now  
| (=years) and it is SUPPOSED to make up for many of the 88100's shortcomings.  
| One thing I would like to know is what kind of 3d graphics support does the  
| 88110 have? On chip Z-buffering? Does anyone know? There have been references  
| to 3d hardware support.

The 88110 is a superscalar processor which can issue up to 2
instructions per cycle.  It has 2 integer execution units, a
load/store unit, floating-point add/mul/div units, and a graphics
unit.  It also integrates two cache/MMU pairs (one for data, one for
instructions) on chip. 

The graphics unit performs operations on multiple pixels, similar
to the operations supplied in the i860 graphics unit.  They can be used
for implementing Gouraud shading and Z-buffer masking. 

--
	Tim Olson
	Advanced Micro Devices
	tim@amd.com