"BOLT" post-link optimizer gives 15% speed boost to Clang

[Johan Engelen]

Hi all,
   "Post-link optimization", what? Yes, indeed, optimization 
_after_ the _linker_ has generated a _binary_.
Read about this interesting work and the discussion here: 
https://lists.llvm.org/pipermail/llvm-dev/2018-October/126985.html

When applied to clang, the performance gain is 15% faster 
execution (note, that's the result of applying BOLT on a clang 
binary that was already built with PGO and LTO !)

Cheers,
   Johan