[clang] Speedup line offset mapping computation

Clang spends a decent amount of time in the LineOffsetMapping::get(...)
function. This function used to be vectorized (through SSE2) then the
optimization got dropped because the sequential version was on-par performance
wise.

This provides an optimization of the sequential version that works on a word at
a time, using (documented) bithacks to provide a portable vectorization.

When preprocessing the sqlite amalgamation, this yields a sweet 3% speedup.

This is a recommit of 6951b723 with endianness
and unsigned long vs uint64_t issues fixed (hopefully).

Differential Revision: https://reviews.llvm.org/D99409