![]() Our new comparison-based algorithm In-place Parallel Super Scalar Samplesort ( IPS 4o ), combines this technique with branchless decision trees. ![]() We also parallelize this approach taking dynamic load balancing and memory locality into account. ![]() Our main algorithmic contribution is a blockwise approach to in-place data distribution that is provably cache-efficient. Previously, the in-place feature often implied performance penalties. Somewhat surprisingly, part of the speed advantage is due to the additional feature of the algorithms to work in-place, i.e., they do not need a significant amount of space beyond the input array. We present new sequential and parallel sorting algorithms that now represent the fastest known techniques for a wide range of input sizes, input distributions, data types, and machines.
0 Comments
Leave a Reply. |