[comp.sys.intel] DRAM controllers

sam2y@spot.cs.virginia.edu (Steven A. Moyer) (01/16/91)

I have a question concerning DRAM controllers that maybe someone can help
me with.  In particular, DRAM controllers for page-mode DRAMs.

During fast page reads RAS is held low while CAS is toggled as column
addresses are applied.  When an access requires that a new row be read
from the DRAM array, the DRAM controller state machine (at least the
one that I am working with) enters a precharge state which requires 
several CPU clock cycles.

My question is, what occurs during this precharge state?

Since the state after the precharge state is the idle state, it doesn't
appear to be part of the row access.  My guess is that maybe writes only
affect the buffer which holds the most recently read row, and that during
precharge this buffer is written back.  I would like to know for sure.

Thanks for any help.
--

+--------------------------------------------------------------------+
| Steven Moyer                   |       THIS SPACE FOR RENT         |
| University of Virginia         |                                   |
|                                | "Just a rebel without a clue..."  |
| E-mail: sam2y@virginia.edu     |                - The Replacements |
+--------------------------------------------------------------------+

sam2y@batik.cs.Virginia.EDU (Steven A. Moyer) (01/18/91)

This is just a quick followup to withdraw my question concerning the
operation of the DRAM controller.  My question turned out to be the
product of an over-simplified reference.  Thanks.
--

+--------------------------------------------------------------------+
| Steven Moyer                   |       THIS SPACE FOR RENT         |
| University of Virginia         |                                   |
|                                | "Just a rebel without a clue..."  |
| E-mail: sam2y@virginia.edu     |                - The Replacements |
+--------------------------------------------------------------------+

adamr@unigold.UUCP (Adam Ravid) (01/19/91)

I heard Intel has a new 9600 modem, capable of 38.4K with MNP and all.
Pract. Periph. also has a new 9600 modem, with apprently the same features.
Supposedly, the intel has a faster chip - supposedly the intel is better.

Can anybody explain to me why it is better?  I mean without getting too
techincal....  Thanks.

----------------------------
adamr@unigold.sr.com
cbcscaar@ma.secs.csun.edu