Tom Yager isn't watching the same industry that I am - he's high on the iTanic:
The road ahead isn’t about 8GHz Xeons or 32-core Opterons. It won’t be about hardware at all. It will be about the $100,000 commercial development suites that will perform automated, distributed build, run, observe, and optimize cycles until native code flows through every possible combination of processor types. And for another $50,000, tools will instrument a commercial app to optimize itself based on changing deployment environments. In this scenario, it might take Microsoft (Profile, Products, Articles) three months just to build a major release of Windows, harnessing the off-hours cycles of every machine on the Redmond campus, but the result would be an OS that could chop a big shop’s system requirements by a third or more.
I’m bullish on IA-64 because a dream world of compilers that take their sweet time to build and optimize but that produce mind-blowing code will surface there first. Everything learned there will transfer to other architectures, however, and we’ll end up with a naturally occurring matrix of CPU types and deployment patterns that provides customers with meaningful choices.
I've had pretty long conversations with our VM team about the IA-64 - they agree that the itanium is just a horrible chip for JITed code. Intel designed this chip back when they thought that C++ was the future of computing. In the succeeding decade, Java and the MS CLR have come to the forefront, affirming the vision that we had in the Smalltalk community a long time ago. More importantly, it demonstrates that the industry isn't moving to anything like what Yager posits. The huge compile farms that Yager speaks of are most certainly not the future of general application development.
Of course, this is the same guy who knew that Apple wasn't moving to intel, so - what should we expect?