BusSort: How Cache Optimization Doubles Sorting Performance

BusSort demonstrates that algorithmic innovation remains possible by aligning sorting design with modern CPU cache architecture. By processing data in L1-sized chunks rather than scattering writes across memory, it achieves 2x performance gains over Java's Quicksort while maintaining stability—a rare combination in high-performance sorting. For applications processing massive datasets, this offers both a performance breakthrough and a new paradigm for hardware-aware algorithm design.