A CUDA-MPI Hybrid Bitonic Sorting Algorithm for GPU Clusters
| Autor: | Tia Newhall, Sam White, Niels Verosky |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Proxmap sort
Sorting algorithm Bitonic sorter Computer science Sorting Shellsort Parallel computing External sorting Hybrid algorithm Bitonic sorting Adaptive sort Integer sorting Data_FILES In-place algorithm Sorting network sort Algorithm design Bucket sort Merge sort Counting sort Algorithm Block sort |
| Zdroj: | ICPP Workshops |
| DOI: | 10.1109/icppw.2012.82 |
| Popis: | We present a hybrid CUDA-MPI sorting algorithm that makes use of GPU clusters to sort large data sets. Our algorithm has two phases. In the first phase each node sorts a portion of the data on its GPU using a parallel bitonic sort. In the second phase the sorted subsequences are merged together in parallel using a reduction sorting network implemented in MPI across the cluster nodes. Performance results comparing our sorting algorithm to sequential quick sort yield speed-up values of up to 9.8 for sorting 4GB of data on a 32 node GPU cluster. We anticipate even better speed-up values using our algorithm on larger data sets and larger sized clusters. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|