Quote Originally Posted by baffledmollusc View Post
Yes, really.

Say you get a benchmark score of 80 FLOPS, iterations, whatever. Say it took 30 seconds, and the CPU used an average power of 50W over that time. So

Performance per Watt = benchmark result / (average power * time / time)

= 80 FLOPS / (50W * 30s / 30s)
= 80 FLOPS / 50W
= 1.6 FLOPS / W
= 1.6 FLOPS per Watt

The reason I wrote it that way is average power * time = energy, and to get a power you have to divide by time taken.

Although now I look at it, I'm prepared to agree that while correct, it's not the most straightforward approach. I think the issue is I always think in terms of energy, and convert that to whatever later.
Your equation negates time duration, thus assuming a constant Power consumption, when it's truly a mean average. At any rate, showing the irrelevance of time within an energy relationship seems rather odd, especially since reality doesn't match this linear relationship.

Even the FLOPS itself is a fitted curve.