Benchmarking Intel-based Numpy packages

Intel has their own distribution (modified version) of Numpy, Scipy, and scikit-learn packages. They claim that these packages are optimized from those existing packages. To prove this claim, I made a little following benchmark. I used two similar machines MBP 2012 and Lenovo G580. Both have similar specs, i7-3520 processors, and 16GB RAM. The following code I used to benchmark.

My Laptop Buying Experience

I am not the first person who bought laptop in my family. The first person is my sister, who bought her first laptop in early university time. I was shocked how can she buy the laptop, but I borrow it during my job training in the university.

My current laptop family: MBP, Xperia S, G580

My first laptop purchase was eMachine D725. In that time, the price is IDR 6000000. The story was started when I got scholarship from one of Bank from Indonesia government in late my university time. I add my saving account and ask my father to add too to buy the laptop as I do my final project for university graduation. I was pleased with the performance of D725. At the time of buying, it is preinstalled with Linpus, then I install Windows XP and finally Ubuntu 12.04 is the main OS till now.