A Randomized Parallel Sorting Algorithm with an Experimental Study

Abstract

Previous schemes for sorting on general-purpose parallel machines have had to choose between poor load balancing and irregular communication or multiple rounds of all-to-all personalized communication. In this paper, we introduce a novel variation on sample sort which uses only two rounds of regular all-to-all personalized communication in a scheme that yields very good load balancing with virtually no overhead. Moreover, unlike previous variations, our algorithm efficiently handles the presence of duplicate values without the overhead of tagging each element with a unique identifier. This algorithm was implemented in Split-C and run on a variety of platforms, including the Thinking Machines CM-5, the IBM SP-2, and the Cray Research T3D. We ran our code using widely different benchmarks to examine the dependence of our algorithm on the input distribution. Our experimental results illustrate the efficiency and scalability of our algorithm across different platforms. In fact, it seems to outperform all similar algorithms known to the authors on these platforms, and its performance is invariant over the set of input distributions unlike previous efficient algorithms. Our results also compare favorably with those reported for the simpler ranking problem posed by the NAS Integer Sorting (IS) Benchmark.1998 Academic Press, Inc.

A Practical Quicksort Algorithm for Graphics Processors

“…For benchmarking we used the following distributions which are defined and motivated in [22]. These are commonly used yardsticks to compare the performance of different sorting algorithms.…”

Equihash: Asymmetric Proof-of-Work Based on the Generalized Birthday Problem

“…Whereas the quicksort is traditional choice for singlethread applications, a number of its variations as well as that of bucket sort, radix sort, sample sort, and many others have been proposed, as they all differ in scalability, computational time, communication complexity, and memory bandwidth. The implementations on a CPU, a multi-core cluster [26], a GPU [46], and even FPGA have been reported. a) Proof of Proposition 7: For our purpose a modification of bucket sort, also called a sample sort, suffices.…”

Multi-Core Program Optimization: Parallel Sorting Algorithms in Intel Cilk Plus

“…Different parallel sorting algorithm such as bi-tonic sort [15,16], column sort [20], parallel merge sort [12], parallel radix sort [21] and randomized parallel sor ting [18] has been developed. In [9] a parallel sorting algorithm using Graphics Processing Units (GPU's) has been devised.…”