Subject: | |
From: | |
Reply To: | |
Date: | Fri, 2 Apr 1999 10:35:30 CST |
Content-Type: | text/plain |
Parts/Attachments: |
|
|
>
>David Gillett wrote:
>
>> Wayne Ramlogan <[log in to unmask]> asked:
>> >Is it possible to mix RAM; EDO and SDRAM PC100 or EDO and SDRAM
... snip ...
>> My personal conjectures (somebody correct me if I'm wrong) are as
>> follows:
>>
>> 1.) Your edo is "rated" 60-70 nanoseconds.
>> 2.) Your sdram is "rated" 6-10 nanoseconds.
>> 3.) Your memory bus runs at one constant speed.
>> 4.) This one constant speed with mixed mem. modules would have to
>> approximate the speed of the slowest module.
>>
>> Hence you would be running sdram rated at 6-10 ns at something like
>> 60-70 ns, a potential waste of resources. Fine for a short test period
>> (if it works: I never take stuff like this for granted). Definitely not
>> recommended in the long run.
>
> This might be true IFF the ns rating of SDRAM was measuring the exact
>same thing as the ns rating of FPM and EDO does. But if it did, it
I give up. What _are_ the ns ratings of EDO, SDRAM, etc measuring???
>would be wasteful to use SDRAM in a machine with an FSB any slower than
>about 500 MHz or so; the fact that SDRAM is routinely used with FSB
>speeds of 66-100 MHz makes it pretty clear that you cannot just compare
>ns ratings across types this way.
Yeah, I thought I might be getting myself in trouble here.
Lets see if I can further "lock and load" and draw a perfect aim on my
foot <grin>.
Is it in any way reasonable to conceptualize TOE (Time Of Execution)
for a simple fetch instruction as:
TOE = Tb + Tma +Tb
where Tb is time required for transfer on the mem. bus and
Tma is time required for memory access (address resolution, etc) ?
If this is massively inaccurate, do you have a better model?
In my insane dream, the Tma for, say, 60 ns EDO, when divided by
the Tma for 10 ns SDRAM, _approximated_ the ratio of the 2
ratings (60/10). Crazy, huh?
Maybe I can learn something here ...
Prosit,
David N.
**********************************************************************
** David Nasser ** [log in to unmask] **
** Univ. Mo. St. Louis ** **
**********************************************************************;
Curious about the people moderating your
messages? Visit our staff web site:
http://nospin.com/pc/staff.html
|
|
|