I have: Apple LLVM version 7.0.0 (clang-700.1.76) Target: x86_64-apple-darwin15....

I have:

    Apple LLVM version 7.0.0 (clang-700.1.76)
    Target: x86_64-apple-darwin15.0.0
    Thread model: posix

I did mention that the same source code when compiled with gcc runs faster in a Linux VM than when it is compiled with clang and run in OSX. That means, some of those optimization options either do not mean anything or do not work as well when using clang.