🚀 go-pugleaf

In article <3v71fl$gmh@warp.cris.com>, dkomo@cris.com writes:
|> Curtis Bass <cbass%intmeds1.utmb@mhost.utmb.edu> wrote:
|> >medcalf@ppc5.svo.dfw.ibm.com (Jeff Medcalf (214) 280-5970 IBM SDO) wrote:

|> >>But what no one has yet said is *what* determines the bitness of a
|> >>processor?

|> >The 8086/8088 had 16-bit registers. It was a 16-bit
|> >processor. Ditto for the 286. The 386 had 32-bit registers. It was
|> >a 32-bit processor. Ditto for the 486 and Pentium.

|> >Likewise, the 68000 had 32-bit registers. It was a 32-bit processor.

|> Not according to Motorola.  Here's a quote from the M68000 Programmer's 
|> Reference Manual:

[ quote trimmed ]

There's never been a generally agreed-upon definition of bitness.
Intel likes bigger bitnesses; they called the 8-bit data bus 8088 a
16-bit processor.  Using the same rules, one would call the 68000 a
32-bit processor.  Motorola used more conservative rules.  Since then,
the need for marketing hype has dissuaded them from that responsible
stance. 

Chris

-- 
Speaking only for myself, of course.
Chris Wood    christw@lexis-nexis.com   ChrisCWood@aol.com