You have worked this out before so I wonder if you could just remind me what in your considered opinion the annual cpu development costs of Itanium were at its peak and now ?
At the recent peak (Tukwila physical design concurrent with Poulson uarch development) it was probably on the order of $200m-$300m per year. Now it is probably less than $10m (Kittson now seems to be a rebadged/speed bumped, hidden feature enabled Poulson) which is basically manufacturing/test support. AFAIK FTC moved onto other things about a year ago when HP refused to fund a 22 nm Kittson.
Considering how fast the Unix market is fading away it looks like it might have been a good call. Certainly IBM seems anxious to cut back on its semi/processor R&D costs.
I remember when I worked on the Merced chipset, and I had to deal with the Merced CPU team. Just the CPU team alone was 500 people. (The chipset team was considerably smaller, maybe like 100 at most.) Of course, most of those people were new hires, the result of a hiring boom in the mid-to-late 90's thanks to the dot-com bubble and the rise of Intel's fortunes.
That was probably the peak.
I have no idea how many people now work on Kittson, but I'd imagine it's a small fraction of the number that worked on Poulson, which in turn was a fraction of that which worked on Tukwila, etc. Where Itanium goes from here, you can probably guess.