A C++ compiler is not guaranteed/required to inline the comparison (just very likely to do so if it's small). Can you explain what advantage you see in doing things the qsort way over a (possibly but not necessarily comparison-inlined) templated sort function? What difference does it make to have multiple (differently typed) std::sort instantiations vs just one type-agnostic one (qsort-style)?

If the comparisons are expensive enough to warrant not inlining them, then I very strongly doubt you'll find a meaningful speed difference between qsort and std::sort. I don't know if you're concerned about code size and instruction cache etc., but I doubt that matters if comparisons are expensive.