Replies to post #4575 on Intel Corp (INTC)

[DewDiligence]

>> Where does [TMTA] go from here? From four way to eight way VLIW? That will raise power significantly more than it will raise performance because it will be far beyond the point of diminishing returns for ILP yet much of the active portion of the processor will double in width… <<

Yes, there will be diminishing returns from doubling the width of the VLIW due to the limits on exploiting ILP. But the performance gain from the 128-bit Crusoe to the 256-bit Astro (TM8000) will likely be at least 1.5X for a given clock frequency. Moreover, the frequency itself is likely to increase by 40-50% relative to the fastest Crusoe. Hence the multiplicative improvement from both the increase in instruction width and the increase in clock frequency will likely be on the order of 2.1-2.3X.

>> A wider VLIW also means more NOPs… <<

That’s another way of saying the same thing you said above –that there will be diminishing returns due to the limitations of ILP.

>> It looks like TMTA will need to compete on price.<<

Agreed. But price is one area where Astro will shine. For OEMs, Astro will have a compelling price/value tradeoff relative to Centrino, and it should be more than able to hold its own versus competing products from AMD, VIA, and others.

>> Foundry based manufacturing, a relatively large die, and low ASPs hardly sounds like the recipe for a "home run"<<

You are confusing the company with the stock. From the current stock price, TMTA, the company, merely has to do modestly well for my TMTA stock holding to turn into a bona fide “home run.” Regards, Dew