From: Drew Eckhardt (drew@caesar.cs.colorado.edu)
Date: 06/28/93


From: drew@caesar.cs.colorado.edu (Drew Eckhardt)
Subject: Re: MIPS R3000 - 2nd update
Date: Mon, 28 Jun 1993 05:56:28 GMT

In article <1993Jun25.102001.6425@black.ox.ac.uk> wa95003@black.ox.ac.uk (Martin J Bligh) writes:
>In article <1993Jun25.052215.14306@colorado.edu> drew@cs.colorado.edu (Drew Eckhardt) writes:
>>In article <C914sM.98w@murdoch.acc.Virginia.EDU> doolitt@cebaf4.cebaf.gov (Larry Doolittle) writes:
>>
>>> CMOS RAM? How many banks of SIMMS?
>>
>>32 simm slots, which will take up to 4M 8 or 9 bit wide SIMMs.
>
>Would it be possible to mix and match different sizes of SIMM (1Mb / 4Mb)
>and have groups of SIMMS smaller that the 4 that is standard on most
>current PC motherboards?
>

If we were to use 32/36 bit wide JDEC SIMMS : it would be possible,
but I think that the emphasis on people's ability to use some
existing hardware (ie, parallel printers, memory, etc) will
preclude this.

With 8/9 bit wide SIMMS : definately not. One at a time would mean
a performance decrease by a factor of four, two at a time by a
factor at two, and once you do that your price/performance ratio is
going to be better if you get a 386sx.

(Actually, your best bet performance wise will be to add memories
eight at a time, since that way you can run two-way interleaved
which will cut the number of wait states in half)

-- 
Boycott USL/Novell for their absurd anti-BSDI lawsuit. | 
Condemn Colorado for Amendment Two.                    | Drew Eckhardt
Use Linux, the fast, flexible, and free 386 unix       | drew@cs.Colorado.EDU 
Will administer Unix for food                          |