But isn't this similar to what Savantu is saying? Intel and HP have been steadily decreasing the costs of Itanium through economies of scale and volumes, but over the last few years, GFLOPs has stayed relatively constant, doubling once with the introduction of Montecito. Meanwhile, x86 cores have seen dramatic increases in GFLOPs....
Fast forward to Tukwila, and it's obvious that Intel will improve IPF's value prop considerably. Not only will they double the cores and increase the clock, but they'll add plenty of memory bandwidth to help bandwidth constrained applications, of which there are many. That's fine, but won't Intel still be ahead with Nehalem? That's an interesting point, from which I have never been able to form a definitive opinion. Intel's x86 efforts seem to be on a fast trajectory, and I wonder if IPF will ever vault ahead.
Bingo and a big thank you!
That was the entire point of IPF : offering better performance per transistor.
OoO and serial execution were supposed to hit a complexity and thermal wall ; in-order ( moving the complexity to SW ) and parallelism were the foundations of the entire IPF saga.
IPF was ok until 2004 , from then on it fell hopelessly behind to x86 and even other RISCs.
HPC was a market which showed great promise to IPF , yet it managed to get the boot for not upping the frequency , cores , memory BW , you name it.
Paul constantly bragged how small and simple the IPF core is compared to other RISCs or x86 , yet , what's the point of that simplicity if it doesn't translate into higher clocks and lower power consumption ?
Not only that , but the more complex x86 cores managed to trash it performance wise while being cheaper to manufacture and burning far less power.
This must be the screwup of the century in semis when you consider the original goals and what they actually put up!
Since this is an investor forum I challenge you to an exercise : imagine Intel's finances if it hadn't been for Itanium.
Imagine :
-not spending $5-10B in R&D over the past 15 years for IPF
-not taking thousands of engineers from x86 ,slowing x86 development , delaying 64bit x86 and allowing AMD to have the upper hand
-not using thousands of SW engineers to create compilers , help port/optimize apps to IA64 , but using them to improve the x86 ecosystem.
Can you imagine where Intel would be now ?
Market Data 
Markets 
AI
