Summary
1. Economics is going to be the big driver in the supercomputer/enterprise space for 100GbE. 2. In the carrier sector, spectral efficiency associated with 100G will play a large role. 3. Obviously, the hope is that there will be a substantial amount of growth in both markets.
Analysis
In the supercomputer market, n by 10G, is now being done. The cost of 100GbE has to be cheaper than 10x10G before the new technology can start to happen. There are expectations by some industry analysts that volume demand will get the necessary movement on price in the enterprise.
It is a different situation in the service provider space. There are locations in which there are as many as 96 DWDM channels of capacity. One has a lot more spectral efficiency in putting in 96 channels at 100G than in having 10 overlays networks of 96 channels of 10G. In some cases, long-haul carriers do not necessarily have the fiber to do the latter or they do not want to spend the money for that result. So, there is an element of practicality on the public network side that does not appear to be a factor in the enterprise space.
