Intel's FB-DIMM, any kind of RAM will work for your controller?

  • Thread starter Thread starter Yousuf Khan
  • Start date Start date
I think the "increased latency" is with respect to the usual (in PCs)
one or two unbuffered DIMMs. In this case, the FB-DIMMs do indeed
have a greater latency.
Click to expand...

Sure but compared with registering independently on every DIMM and hoping
that they all talk on the same edges... or close enough so that it works??
It's not clear to me if, in a large memory system, say 8 ranks per channel,
accesses to the farthest DIMMs are going to have extra cycles of latency
added but if the clock frequency can be jacked up significantly, does it
matter much?
Keep in mind that there will really be no choice once you've bought
your mobo. The CPU socket will either be for a CPU to use traditional
DIMMs or (with 66% fewer memory pins) to use FB-DIMMs. You will never
ever stand there with both types of memory modules in hand and have to
decide which to plug in.
Click to expand...

CPU socket? Oh we're talking AMD as the "standard" now?:-) Daytripper
mentioned he's not sure the FB-DIMM is going to make it to the desktop
anyway. Makes me wonder how the pricing is going to fall out with the
market fragmentation - to date we've all -- desktop through to server --
benefited from that model till now. Could get awkward for CPU on-die
memory controllers too if we need to have different CPUs according to the
memory type.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??
 
George Macdonald said:
CPU socket? Oh we're talking AMD as the "standard" now?:-) Daytripper
mentioned he's not sure the FB-DIMM is going to make it to the desktop
anyway. Makes me wonder how the pricing is going to fall out with the
market fragmentation - to date we've all -- desktop through to server --
benefited from that model till now. Could get awkward for CPU on-die
memory controllers too if we need to have different CPUs according to the
memory type.
Click to expand...

Oh, I think it's all much ado. We'll keep the desktop to server DRAM
interface commonality for a long time. Afterall, how many new types of DRAM
come out in a given amount of time? I'd say a new standard every 3 to 5
years? Hardly a breakneck frequency. People will continue to design new DRAM
controllers based on upcoming standards, and they will also put backwards
compatibility into these controllers for previous generations of DRAM.

Yousuf Khan
 
George Macdonald said:
Daytripper
mentioned he's not sure the FB-DIMM is going to make it to the desktop
anyway. Makes me wonder how the pricing is going to fall out with the
market fragmentation - to date we've all -- desktop through to server --
benefited from that model till now. Could get awkward for CPU on-die
memory controllers too if we need to have different CPUs according to the
memory type.
Click to expand...

Intel may see this as an opportunity to increase the ASPs on "Xeon"
CPUs - in other words, on CPUs for servers. I think it'll be a cold
day in hell when this shows up on personal desktops.
 
Oh, I think it's all much ado. We'll keep the desktop to server DRAM
interface commonality for a long time. Afterall, how many new types of DRAM
come out in a given amount of time? I'd say a new standard every 3 to 5
years? Hardly a breakneck frequency. People will continue to design new DRAM
controllers based on upcoming standards, and they will also put backwards
compatibility into these controllers for previous generations of DRAM.
Click to expand...

On the "frequency", od standards, we had a close call with DRDRAM. Was it
a "standard" or not?... it came close at least. I don't see how backwards
compatibility is something they can even think of - different signalling is
just different.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??
 
George Macdonald said:
On the "frequency", od standards, we had a close call with DRDRAM. Was it
a "standard" or not?... it came close at least. I don't see how backwards
compatibility is something they can even think of - different signalling is
just different.
Click to expand...

Well, they've had chipsets in the past which implemented compatibility with
both EDO and SDR rams. Then later we had chipsets which did both SDR and
DDR1 compatibility. Why should it be difficult to put dual DDR1 and DDR2
capabilities? It detects which type of ram it's connected to and switches to
the circuitry for that particular type of RAM.

Yousuf Khan
 
Well, they've had chipsets in the past which implemented compatibility with
both EDO and SDR rams. Then later we had chipsets which did both SDR and
DDR1 compatibility. Why should it be difficult to put dual DDR1 and DDR2
capabilities? It detects which type of ram it's connected to and switches to
the circuitry for that particular type of RAM.
Click to expand...

Different voltage swings, different (IO) voltages, and I don't think DDR1 used
ODT. And then you have the whole dimm socket keying issue.

In a heavily commoditized market it'd unnecessarily drive up the chipset and
platform implementation costs to accommodate both technologies with a single
solution...

/daytripper
 
Well, they've had chipsets in the past which implemented compatibility with
both EDO and SDR rams. Then later we had chipsets which did both SDR and
DDR1 compatibility. Why should it be difficult to put dual DDR1 and DDR2
capabilities? It detects which type of ram it's connected to and switches to
the circuitry for that particular type of RAM.
Click to expand...

Obviously it depends onhow big a jump there is between the technology of
the two memory channels - SDRAM and DDR-SDRAM are not too far apart in
terms of signalling - a few extra pins for source synch clocking and a few
others which were used slightly differently. OTOH we never saw a dual
DRDRAM and SDRAM chipset - too different... would certainly require
independent pins. I'm not up on the details of FB-DIMM interfacing but I'd
think it'd be different enough.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??
 
George said:
Obviously it depends onhow big a jump there is between the technology of
the two memory channels - SDRAM and DDR-SDRAM are not too far apart in
terms of signalling - a few extra pins for source synch clocking and
a few others which were used slightly differently. OTOH we never saw
a dual DRDRAM and SDRAM chipset - too different... would certainly
require independent pins. I'm not up on the details of FB-DIMM
interfacing but I'd think it'd be different enough.
Click to expand...

Well, there were different voltages for SDR and DDR, so it wasn't exactly
the simple jump that from SDR to DDR that you describe. Plus you needed
different sockets for each type. And in most cases you couldn't use both
types of RAM at the same time because of the voltage issue.

As for SDR and RDR together, must I remind you of the infamous Intel MTH?
Okay, I didn't say that it had to be a successful chipset (or even a good
chipset), but you did see the capability of using either type of memory at
one point in time. :-)

Yousuf Khan
 
George Macdonald said:
I'm not up on the details of FB-DIMM interfacing but I'd
think it'd be different enough.
Click to expand...

George, FB-DIMM uses only a third as many pins as regular DIMMs.
Different enough? You betcha!
 
Well, there were different voltages for SDR and DDR, so it wasn't exactly
the simple jump that from SDR to DDR that you describe. Plus you needed
different sockets for each type. And in most cases you couldn't use both
types of RAM at the same time because of the voltage issue.
Click to expand...

You needed different sockets because there were more pins - voltage swing
is easy if it's just a jumper on the mbrd and certainly does not disqualify
what I said.
As for SDR and RDR together, must I remind you of the infamous Intel MTH?
Okay, I didn't say that it had to be a successful chipset (or even a good
chipset), but you did see the capability of using either type of memory at
one point in time. :-)
Click to expand...

Hmm well first it didn't work and then it had nothing to do with the
chipset - there were even DIMMs with the DRDRAM/SDRAM right on the module.
It was a "Rube" add-on and nobody with any appreciation of PC performance
would have used it.

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??
 
George said:
You needed different sockets because there were more pins - voltage
swing
is easy if it's just a jumper on the mbrd and certainly does not
disqualify what I said.
Click to expand...

No, but as you can see people are continuously finding clever ways of being
able to support two types of RAM on a single chipset.
Hmm well first it didn't work and then it had nothing to do with the
chipset - there were even DIMMs with the DRDRAM/SDRAM right on the
module. It was a "Rube" add-on and nobody with any appreciation of PC
performance would have used it.
Click to expand...

Like I said, it didn't have to be good chipset, nor a successful chipset,
and I guess it really doesn't have to be a pretty, professional-looking
chipset either. :-)

Yousuf Khan
 
Back
Top