[rescue] 128 bits...

[Jonathan C. Patschke]

On Fri, 7 Feb 2003, Dave McGuire wrote:

> > a bit huge... I am fascinated by the idea of a CPU that addresses
> > directly into secondary storage, data files exists as address
> > locations, not inodes or sectors/tracks/platters on a SCSI ID...
>
>    George Adkins and I were discussing something along these lines a few
> months ago.  An architecture like that has some interesting
> possibilities.

And interesting problems.  I suspect you'd want object like that aligned
at certainly memory addresses (segments, if you will), sort of like how
IP networks are aligned at the all-zeros address of a certain mask.
With many of these interesting memory-mapped objects, you'd quickly
exhaust the address space (Assuming a maximum filesize of 4GB, you could
have no more than billion files, assuming a larger filesize decreases
the address space exponentially).

The alternative would to have a gigantic lookup table, which would
consume space in itself, and bring with it all the problems of directory
management (fragmentation, etc.).

You could, I suppose, virtually map things at nice offsets, and
physically map them against a table (a la TLB), but you'd still have to
do a lot of song-and-dance behind the scenes.

-- 
Jonathan Patschke  *)  "The clue phone is ringing, and it's for you."
Thorndale, TX      (*                                 --Dave McGuire