JSMeter Project
research.microsoft.com
research.microsoft.com
edit: full disclosure, I'll be interning at MSR (different group) in the summer.
The last sentence from the webpage: We hope our results will convince the JavaScript community to develop and adopt benchmarks that are more representative of real web applications.
I am a web developer and over the years I have suffered a lot and wasted a lot of time just because the different IE releases did not conform to the existing web standards. It just doesn't feel right when MS try to convince the JavaScript community about something while they ignored the recurring demands of the same community in order to push their proprietary standards and extend their monopoly.
I am not trying to defend my argument, but just trying to express the thought process that led me to the argument.
But the linked paper has absolutely nothing to do with standards. It deals with the speeds of different JavaScript engines and how representative speed benchmarks are of real web sites.
> It just doesn't feel right when MS try to convince the JavaScript community about something
As I said, it's best to look at MSR as a separate company. I spent a few weeks there a month ago, and the atmosphere is much more that of a university research lab than a software company.