Performance engineering will be riskier than Moore’s Law ever was. Companies may not know the benefits of their efforts until after they’ve invested substantial programmer time. And speed-ups may be sporadic, uneven, and unpredictable. But as we reach the physical limits of microprocessors, focusing on software performance engineering seems like the best option for most programmers to get more out of their computers.
WHY IT MATTERS: this is a well known fact, developers are lazy as often the hardware is more powerful than what they need to do the job. But as we reach limits of hardware and as AI improves it seems that we may be able to throw software at the problem and have machine algorithms to improve the performance of systems. The impacts are high, from allowing less powerful hardware to run your app or reducing the cost in high volume applications (think data centers or the billions of internet of things devices).
Read the full paper onScience or just the abstract to get an overview here:
https://science.sciencemag.org/content/368/6495/eaam9744