1numexpr - Fast numerical array expression evaluator for Python and NumPy.
2
3The numexpr package evaluates multiple-operator array expressions many times
4faster than NumPy can. It accepts the expression as a string, analyzes it,
5rewrites it more efficiently, and compiles it to faster Python code on the fly.
6It's the next best thing to writing the expression in C and compiling it with a
7specialized just-in-time (JIT) compiler, i.e. it does not require a compiler at
8runtime.
9
10Also, numexpr has support for the Intel VML (Vector Math Library) -- integrated
11in Intel MKL (Math Kernel Library) --, allowing nice speed-ups when computing
12transcendental functions (like trigonometrical, exponentials...) on top of
13Intel-compatible platforms. This support also allows to use multiple cores in
14your computations.
15