SC Conference - Activity Details

Surendra Byna  (Illinois Institute of Technology)

Yong Chen  (Illinois Institute of Technology)

Xian-He Sun  (Illinois Institute of Technology)

Rajeev Thakur  (Argonne National Laboratory)

William Gropp  (University of Illinois at Urbana-Champaign)

I/O Performance

Thursday,  11:30AM - 12:00PM

Room Ballroom E

Parallel I/O prefetching is considered to be effective in improving I/O performance. However, the effectiveness depends on determining patterns among future I/O accesses swiftly and fetching data in time, which is difficult to achieve in general. In this study, we propose an I/O signature-based prefetching strategy. The idea is to use a predetermined I/O signature of an application to guide prefetching. To put this idea to work, we first derived a classification of patterns and introduced a simple and effective signature notation to represent patterns. We then developed a toolkit to trace and generate I/O signatures automatically. Finally, we designed and implemented a thread-based client-side collective prefetching cache layer for MPI-IO library to support prefetching. A prefetching thread reads I/O signatures of an application and adjusts them by observing I/O accesses at runtime. Experimental results show that the proposed prefetching method improves I/O performance significantly for applications with complex patterns.

The full paper can be found in the IEEE Xplore Digital Library and ACM Digital Library