Improving MPI Collective I/O Performance With Intra-node Request Aggregation
| Autor: | Kang, Qiao, Lee, Sunwoo, Hou, Kai-yuan, Ross, Robert, Agrawal, Ankit, Choudhary, Alok, Liao, Wei-keng |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1109/TPDS.2020.3000458 |
| Popis: | Two-phase I/O is a well-known strategy for implementing collective MPI-IO functions. It redistributes I/O requests among the calling processes into a form that minimizes the file access costs. As modern parallel computers continue to grow into the exascale era, the communication cost of such request redistribution can quickly overwhelm collective I/O performance. This effect has been observed from parallel jobs that run on multiple compute nodes with a high count of MPI processes on each node. To reduce the communication cost, we present a new design for collective I/O by adding an extra communication layer that performs request aggregation among processes within the same compute nodes. This approach can significantly reduce inter-node communication congestion when redistributing the I/O requests. We evaluate the performance and compare with the original two-phase I/O on a Cray XC40 parallel computer with Intel KNL processors. Using I/O patterns from two large-scale production applications and an I/O benchmark, we show the performance improvement of up to 29 times when running 16384 MPI processes on 256 compute nodes. Comment: 12 pages, 7 figures |
| Databáze: | arXiv |
| Externí odkaz: |
|