Hacker News Reader

I don't see the point of computing the second derivative (not in the mathematical sense, in the everyday sense) here. Energy usage is a derivative of performance, which is a derivative of time spent on running the thing.

Why didn't the blog just compare the speed of those algorithms? Power consumption is just calculated by multiplying the runtime by a constant here, it's not measured by a power meter or anything....

View on HN

Wall clock speed does not correlate linear to power consumption (in the general case). To oversimplify, consider decoding singlethreaded on one core versus multithreaded on 8 or 20 cores.

In some special cases multiplying runtime might be enough to achieve some accuracy, but that’s not the whole story.

It would be interesting to see this experiment done so that the decode is done enough times for each format so the power consumption differences could actually be measured on a power/watt meter.

Yup, I know that they are not the same, but they are measuring wall clock, and claiming it is power consumption....

Where did the author use wall clock as a proxy for power consumption? The only time based thing I saw was power usage over time and that is still measuring power usage directly just explaining when in the process the most power was used.

Reply on news.ycombinator.com