Authors: Reece Neff, Marco Minutoli, and Antonino Tumeo (Pacific Northwest National Laboratory (PNNL)) and Michela Becchi (North Carolina State University)
Abstract: Influence Maximization is an important graph algorithm that is gaining traction in areas where social networks and other related graphs are processed and analyzed. The long runtime of the algorithm opened the door for optimizations, but is challenging to parallelize and port onto novel architecture due to its irregular and memory-hungry behavior. Our work implements influence maximization on the Xilinx Vitis Unified Software Platform for FPGA in a heterogeneous work sharing CPU-FPGA system. Our preliminary testing shows up to a 3.96x speedup while consuming up to 5.15x less energy than a CPU-only implementation.
Best Poster Finalist (BP): no
Poster summary: PDF
Back to Poster Archive Listing