|
|
|
|
|
|
by ltratt
4235 days ago
|
|
|
Benchmarking practises are currently poor, almost without exception. For peak VM performance, we have started to use Kalibera/Jones's method http://kar.kent.ac.uk/33611/7/paper.pdf (we reimplemented the statistical computations at http://soft-dev.org/src/libkalibera/ to make it more accessible). I don't think this method is the end of the story, but it's a definite improvement: we were surprised at some of the odd effects it highlighted (non-determinism was not what I was expecting). It's definitely changed how I think about benchmarking. |
|
|