Prior to creating TOPBENCH, I performed a lot of research on what a benchmark is, what people expect of one, how previous popular benchmarks worked, how emulators are created, and so on. This research was important because I didn’t want to have to make any changes to TOPBENCH once people started contributing information to the database. Changing the metric code automatically invalidates the gathered scores, so I felt I had only one shot at metric development. Luckily for me, all of my targets are in the past — they’re not changing. And I have almost 3 decades (damn, I’m getting old) of experience working with them first as a user, then as a gamer, then assembler programmer, so I had a pretty solid idea of what I was shooting for.
I’ve gathered my research in this section; use the navigation links in the above Research menu bar to visit each page.