That time I wasted weeks hand optimizing assembly because I benchmarked on random data – Vidar's Blog
Once upon a time I worked in the field of Java Optimizations.
The target system was a distributed data processing platform that ran across hundreds of thousands of machines. At such scales, a 0.5% improvement would easily make up my salary going forward, and 2% was a good result for the half.
That doesn’t mean it was easy. Never have I ever seen such a highly optimized Java codebase. Not before, not since.
Every low hanging fruit had long since been picked clean. For example, there was minimal u...
Read more at vidarholen.net