Yep...the PCB designs are very complex, when your doing a 3TB drive on PCIe=
  :-)

Big FPGAs with ODP NAND's but it does get you there.


How many applications are there that really need more than 64GB of ram and =
yet don't also need a correspondingly crazy ammount of CPU.
> There have long been FPGAs with built-in DDR3 controllers as well as=20
> PCI-e controllers. To build a similar device, for example, something=20
> with multiple slots that can address more than 256GB of RAM would be nice=
..
>
> How expensive and difficult would this be? Most of the logic is=20
> already there, the only thing really is the electrical engineering=20
> (routing, layout, etc.) considerations and the memory addressing logic=20
> which doesn't seem too hard from what I know (I've built a simple=20
> memory controller on a Spartan 3E for my PIC32 in the past).
The problem is that both the speeds and the number of lines involved are ve=
ry large. For signal integrity reasons with modern memory modules you don't=
 really want to be putting more than two modules per channel and each chann=
el is going to have a lot of lines (the data bus along is 128 bits wide on =
PC memory modules).

That makes the PCB design decidedly difficult and a lot of layers will be n=
eeded.
That combined with the big BGAs means that prototyping costs will be very h=
igh.
--
http://www.piclist.com PIC/SX FAQ & list archive View/change your membershi=
p options at http://mailman.mit.edu/mailman/listinfo/piclist

This e-mail (and any attachments) is confidential and may be privileged.  A=
ny unauthorized use, copying, disclosure or dissemination of this communica=
tion is prohibited.  If you are not the intended recipient,  please notify =
the sender immediately and delete all copies of the message and its attachm=
ents.

--=20
http://www.piclist.com PIC/SX FAQ & list archive
View/change your membership options at
http://mailman.mit.edu/mailman/listinfo/piclist
.