Abstract
We introduce PASGAL (Parallel And Scalable Graph Algorithm Library), a parallel graph library that scales to a variety of graph types, many processors, and large graphs. One special focus of PASGAL is the efficiency onlarge-diameter graphs, which is a common challenge for many existing parallel graph processing systems due to the high overhead in synchronizing threads when traversing the graph in the breadth-first order. The core idea in PASGAL is a technique calledvertical granularity control (VGC) to hide synchronization overhead by careful algorithm redesign and new data structures. We compare PASGAL with existing parallel implementations on several fundamental graph problems. PASGAL is always competitive on small-diameter graphs, and is significantly faster on large-diameter graphs.
All Related Versions
Funding Information
  • Google Research Scholar Program
  • UCR Regents Faculty Fellowship
  • National Science Foundation (CCF-2103483,CCF-2238358,CCF-2339310,IIS-2227669)