Linus Torvalds (torvalds@linux-foundation.org) on 2/9/10 wrote:

>
>If I had to take a wild guess, I'd guess that the POWER7
>4-way SMT improves throughput by no more than ~40%. Iirc,
>the 2-way one on POWER6 was a roughly 30% specint_rate
>improvement, but I don't think POWER7 is going to get all
>that much more from its four threads (if even that). Why?
>Both because of diminishing returns, and simply because
>it's OoO and lower latencies, thus likely to keep its
>integer resources relatively busier even with a single
>thread.
>

I actually think POWER6 benefited more.
JS12 with 3.8GHz POWER6 CINT and RATE with 2 cores 4 copies
CINT 16.1
RATE 45.9

and the
p570 with 4.7GHz POWER6 CINT and RATE with 2 cores 4 copies
CINT 21.6
RATE 60.9

Now that is 41% if my brain still works, maternity leave is harder than working, and damn a screaming kid can screw with your brain :)

So IMHO POWER7 with it's 4 SMT threads must be getting quite a bit more than 41%.

// Jesper