Performance Evaluation of Parallel Sortings on the Supercomputer Fugaku

Sorting is one of the most basic algorithms, and developing highly parallel sorting programs becoming increasingly important in high-performance computing because number CPU cores per node modern supercomputers tends to increase. In this study, we have implemented two multi-threaded algorithms based on samplesort compared their performance supercomputer Fugaku. The first algorithm divides an input sequence into multiple blocks, sorts each block, then selects pivots by sampling from block at regular intervals. Each partitioned using pivots, partitions different blocks are merged a single sorted sequence. second differs only selecting where binary search used select such that elements partition equal. We compare with sequential multiway merging algorithms. demonstrate BlockQuicksort (a quicksort accelerated reducing conditional branches) for selection tree shows consistently high speed efficiency various data types sizes.