I was wondering what criteria is/was used to determine what benchmarks to include when running a benchmark report on a particular machine. Specifically, running:
After running this on my work machine, I noticed the top benchmark was an Intel Core i7-3770 CPU @ 3.40 GHz (8 cores) running 64-bit Linux. Surely there are better (i.e. higher WolframMark "score") architectures out there to compare, right? After briefly searching the web and other forums for other people using the benchmarking package, I noticed the same benchmarks for comparison on other posted reports. Have the CPU benchmarks not been updated to current technology? Perhaps if I had a better architecture I might see my results show up above this benchmark? Has anyone done this?
Those example measurements in the Benchmarking package are useless. They haven't changed in ages. They are exactly the same even in the oldest version I have installed, which is 10.0 from 2014.
If you open up the package source, or evaluate
you will see that there are some results from 2010 / M8.0 and some form 2014 / M10.0
Mathematica's performance has improved a lot between 8.0 and 10.0, and again a lot since
Furthermore, did the benchmarks themselves change? We do not know. Thus comparisons are quite meaningless.
The benchmarking package is interesting if you compare two computers with the same M version, or compare successive versions of M (and manually verify that the benchmarks have not changed). But even then, it is probably in need of some updates ...
If there are enough interested people, it would be more useful to start a community benchmarking project, with open discussion/feedback to ensure quality and versioning to ensure reproducibility.
That would indeed be a cool idea! A very broad test-set, but might be tricky to make it compatible with older versions I guess? Or provide a N/A when it can not be ran?
Karl Unterkofler used to run MMA benchmarking site in the MathGroup days.