Lanxon writes "It's true: 'Effects of cocaine on honeybee dance behavior,' 'Fellatio by fruit bats prolongs copulation time,' and 'Are full or empty beer bottles sturdier and does their fracture-threshold suffice to break the human skull?' are all genuine scientific research papers, and all were genuinely published in journals or similar publications. Wired's presentation of a collection of the most bizarrely-named research papers contains seven other gems, including one about naval fluff and another published in The Journal of Sex Research."
Why not rewrite everything in assembly? This comparison comes to a conclusion without any facts to back it up. As others have pointed out there is development time and compile time associated with C++... and what about ongoing development? Where does 10-1 come from? Are you assuming they aren't doing any optimization or using any sort of accelerator? I've personally re-written code in C++ from php, and then done the comparison. In our case, we decided the extra maintainability was worth the approx 10-20% increase in speed we saw.
Maybe creating little short lived black holes is not such a good idea given the penalty for failure. Bleeding edge experiments can and do go wrong:Demon Core.