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