Software

Crunching Large Graphs With Commodity Processors

Download Now Free registration required

Executive Summary

Crunching large graphs is the basis of many emerging applications, such as social network analysis and bio-informatics. Graph analytics algorithms exhibit little locality and therefore present significant performance challenges. Hardware multi-threading systems (e.g., Cray XMT) show that with enough concurrency, the authors can tolerate long latencies. Unfortunately, this solution is not available with commodity parts. Their goal is to develop a latency-tolerant system built out of commodity parts and mostly in software. The proposed system includes a run-time that supports a large number of lightweight contexts, full-bit synchronization and a memory manager that provides a high-latency but high-bandwidth global shared memory.

  • Format: PDF
  • Size: 374.7 KB