Re: Have you noticed that AMD went with a thicker gate oxide than Intel at 65nm? As I posted before, I think AMD emphasized low power at the expense of performance at 65nm. A relatively thick gate oxide would seem to track with that.
That would be a legitimate argument if AMD kept their performance constant. Typically, you would expect a new process to offer either better performance at equal power, or lower power at equal performance. And if it were to come with lower performance, you would at least expect vastly lower power.
But is 65nm really vastly lower power, or much higher performance at the same power level? As far as I can see, no.
At 90nm, AMD could manufacture 2.0GHz parts @ 35W, and with 65nm, they can handle 2.3GHz @ 45W.
At 90nm, AMD could manufacture 2.6GHz parts @ 65W, and with 65nm, they can handle 2.7GHz @ 65W.
90nm also has 89W nad 125W power levels, but there are no 65nm equivalents today, unless you go up to quad core with Barcelona.
Overall, it appears to me that 65nm comes with marginal power benefits, but hardly as much as someone might expect from a full process shrink. |
