Eigen NEON port extended to ARMv8!

Soon after the VSX port, and as promised I have completed the ARMv8 NEON (a.k.a. Advanced SIMD) port. Basically this extends support to 64-bit doubles and also provides faster alternatives to division as ARMv8 has builtin instructions for division both for 32-bit floats and 64-bit doubles. Preliminary benchmarks (bench_gemm):
type Gain over scalar
float 252%
double 144%
std::complex<float> 270%
std::complex<double> 209%

The code can be found in https://bitbucket.org/eigen/eigen/pull-request/87/extend-neon-to-add-armv8-64-bit-double, and so far it has passed most tests -full test run has yet to be done.

What's left? Complete MathFunctions.h for both VSX/NEON and eventually start the MIPS MSA port (once I get my hands on a board/docs!).