[extropy-chat] Plastic promises dense data store

[Dan Clemmensen]

Eugen Leitl wrote:

>On Fri, Nov 28, 2003 at 11:50:04AM -0500, Dan Clemmensen wrote:
>  
>
>>I just measured a standard 3.5" disk drive. It's just about exactly 
>>300cc, including its
>>PCB and connectors. You can buy a 350GB version, so yes, the density is 
>>already higher.
>>    
>>
>
>The density is relatively irrelevant (how much cool stuff could
>you do with a rodent equivalent?), it's the latency (several ms vs
>several ns of RAM, a factor of one million) and the bandwidth (some 0.1 
>GByte/s vs. 6 GByte/s, a factor of one thousand).
>
>It would be nice to have a TByte of RAM, but it would be far
>nicer still to have a 10^12 cell assembly, each capable of
>a 10^10/s refresh (the individual switches now could do half
>a THz).
>
>But no can do with rotating bits, magnet domains.
>
>
>  
>
True. But this is a multidimensional problem. In the classical 
informatin management
domain, we can use hierarchical memory techniques to drive the effective 
latency down.
At the TB level, we can employ a bunch of disks in parallel to reduce 
the effective latency.

The point is that you can actuall create a TB storage system for 
<$1000US, quantity 1, today.

I don't think that "plastic mem" will operate in the ns range. Memory in 
this range is specialize,
e.g. ZBT, FCRAM, or RLDRAM, and it is not hi-density. DDR mem can reach 
1GB/s throughput,
but has latencies about 10ns.

"Plastic mem" is likely to fill a gap in the hierarchy. Problems that 
are amenable to a hierarchial
memory may benefit.

As a separate issue, massive storage requirements are generally also 
"write-once" instead of RW.
To he extent that this is true, a printer is already capable of creating 
cheap extensible storage.
assuming a 20% overhead for ECC, we have 1200dpi can store  a mabagit 
per square inch.
This is one megabyte fo eight square inches, or 10 megabytes on an 
8.5"x11" page.