Re: AGP question -> DIMM - Chipset compatibility

[NZG <ngustavson@emacinc.com>]

On Tuesday 29 March 2005 16:26, Bryan J.Smith wrote:
> NZG wrote:
> > This may be true, in my realm I never see DRAM address lines that are
> > not however.(at least not on one DIMM)
>
> Sure you have.
> 32/36 IC x4-bit and Even 16/18 IC x8-bit Buffered/Registered are all
> over.
> That's 128-bits of aggregate IC data paths on a single DIMM.
I need to look into this, I may be mistaken.

> Now that statement is utterly false.
> Intel regularly builds memory controllers that are completely different
> for the same CPUs.
> AMD, on the other hand, has always been a bit more flexible in its
> chipset memory compatibility.
No, not utterly false, we just live in two different worlds.
I'm an embedded engineer, and the processors I work with don't always conform 
to the same set of rules.
The last 3 processors I have designed with are:
The Freescale MCF5282 Microprocessor
The AMD SC520 Microcontroller
The (now AMD formerly National) Geode GX1 processor with 5530 chipset

The first two are microcontrollers, and have their DRAM (yes DRAM not SRAM) 
controllers built into the IC. No options there.

The GX1 is a pentium MMX base that has only one compatible chipset, the 5530, 
and it doesn't matter anyway because the Memory controller is actually 
located on the processor itself, not the chipset. This processor has a 64 bit 
wide memory data bus which can be connected directly to a DIMM.(Although we 
typically use SODIMM's in our designs)

> It's a world of difference in the "front-side bottleneck" of the PC
> world.
Very true, admittatly I am not as up to speed on this aspect of it, but am 
learning quickly as my family keeps asking me to build PC's. (from barebones 
kits)

NZG

-
To unsubscribe, send email to majordomo@silug.org with
"unsubscribe silug-discuss" in the body.