"VCSELs, vertical-cavity surface-emitting lasers, are a lot colsoer to the
mark. These tiny lasers, which have become widely available only in the
past year, are incredibly exciting. They bring the advantages of photonics
-- high bandwidth, low power -- down to the board and even chip level.
Everyone is racing to put them to work.
"A VCSEL is like a tiny, 10- by 10-micron-square laser that can easily be
stuck on a silicon chip. Where before you might have had a wide-ribbon
cable connecting two boards, now you can use an array of VCSELs that
communicate via light. Because VCSELs are so tiny, you can pack them in for
incredible bandwidths -- hundreds of GBytes per second per square
centimeter. And doing so requires much less power than driving conventional
wires.
One of my cousins and her husband are working in this field. In particular,
Scott Corzine coauthored a book on semiconductor lasers last year. In any
case, this is interesting news to add to the file.
The category to file it under is a concept I heard from Marc Weiser of PARC
and ubicomp fame: conservation of bits/cubic meter. All these wavelengths:
from meter-wave to IR laser, have to coexist in finite space. Thus, there
are real limits to the density of information between two places -- high
ones, but limits nonetheless.
That's what turns munchkin-bandwidth back into a scarce commodity. If you
recall my rant from some months back, the only real constraint is that they
ain't makin any more real estate: and when you shoehorn a new munchkin into
already-covered territory, you owe some folks a share of the gains. So
competition should force diversification of media: but can we create single
ad-hoc messaging protocol which will span the lot of them? What is the
equivalent of MX routing for HTTP messages when there's no global DNS
anymore?
Rohit