DETERMINISTIC SAMPLE SORT FOR GPUS

We demonstrate that parallel deterministic sample sort for many-core GPUs (GPU BUCKET SORT) is not only considerably faster than the best comparison-based sorting algorithm for GPUs (THRUST MERGE [Satish et.al., Proc. IPDPS 2009]) but also as fast as randomized sample sort for GPUs (GPU SAMPLE SORT [Leischner et.al., Proc. IPDPS 2010]). However, deterministic sample sort has the advantage that bucket sizes are guaranteed and therefore its running time does not have the input data dependent fluctuations that can occur for randomized sample sort.

Parallel Shellsort Algorithm for Many-Core GPUs with CUDA

Sorting is a classic algorithmic problem and its importance has led to the design and implementation of various sorting algorithms on many-core graphics processing units (GPUs). CUDPP Radix sort is the most efficient sorting on GPUs and GPU Sample sort is the best comparison-based sorting. Although the implementations of these algorithms are efficient, they either need an extra space for the data rearrangement or the atomic operation for the acceleration. Sorting applications usually deal with a large amount of data, thus the memory utilization is an important consideration. Furthermore, these sorting algorithms on GPUs without the atomic operation support can result in the performance degradation or fail to work. In this paper, an efficient implementation of a parallel shellsort algorithm, CUDA shellsort, is proposed for many-core GPUs with CUDA. Experimental results show that, on average, the performance of CUDA shellsort is nearly twice faster than GPU quicksort and 37% faster than Thrust mergesort under uniform distribution. Moreover, its performance is the same as GPU sample sort up to 32 million data elements, but only needs a constant space usage. CUDA shellsort is also robust over various data distributions and could be suitable for other many-core architectures.