https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118250
--- Comment #3 from Filip Kastl <pheeck at gcc dot gnu.org> --- With the modification I plan for Stage 1 the DP alg will be as powerful as the greedy alg here. By LLVM code being better I suppose you mean this lower bound check: cmp eax, 1 jle .L4 Yeah, it would be nice to come up with a way to get rid of it.