We have designed a radix sort algorithm for vector multiprocessors and have implemented the algorithm on the CRAY Y-MP. On one processor of the Y-MP, our sort is over 5 times faster on large sorting problems than the optimized library sort provided by CRAY Research. On eight processors we achieve an additional speedup of almost 5, yielding a routine over 25 times faster than the library sort. Using this multiprocessor version, we can sort at a rate of 15 million 64-bit keys per second. Our sorting algorithm is adapted from a data-parallel algorithm previously designed for a highly parallel Single Instruction Multiple Data (SIMD) computer, the Connection Machine CM-2. To develop our version we introduce three general techniques for mapping data-parallel algorithms ontovector multiprocessors. These techniques allow us to fully vectorize and parallelize the algorithm. The paper also derives equations that model the performance of our algorithm on the Y-MP. These equations are then used t...

: We propose that sorting be considered an important benchmark for both scientific and commercial applications of supercomputers. The purpose of a supercomputer benchmark is to exercise various system components in an effort to measure important performance characteristics. In the past numerous benchmarks have been defined in an effort to measure the performance issues associated with numeric computing. These benchmarks stressed arithmetic operations (in particular, floating-point arithmetic). In recent years supercomputers manufactures have started to look closer at non-numeric processing tasks, such as databases and information retrieval. The ability to operate on large amounts of non-numeric data will be crucial in the future. This paper discusses the appropriateness of sorting as a benchmark for non-numeric computing tasks. The paper describes previous work in this area and defines a set of architecture independent sorting benchmarks. Contact: Kurt Thearling phone: (6...