* Combine <8 and 8-16 cases into one case. * Adopt mask-based approach for the <16 length city fast path (idea of Van Phu Do). * Slightly improved code layout. * Update perf number.
* Combine <8 and 8-16 cases into one case. * Adopt mask-based approach for the <16 length city fast path (idea of Van Phu Do). * Slightly improved code layout. * Update perf number.