Parallel In-Place N-bit-Radix Sort

Good article about parallel in-place sort "This high performance linear-time O(n) algorithm outperforms STL sort() by more than 60X. Parallel Counting Sort benefited by 2-3X when running on a quad-core processor, accelerating from parallelization of the counting portion of the algorithm. ..combine In-Place N-bit-Radix Sort and Parallel Counting Sort to develop a Parallel In-Place N-bit-Radix Sort algorithm, using Intel's Threaded Building Blocks library. "