Workshops Archive

PortWarp: A Cycle-Accurate GPU-Accelerated HPC Network Simulator Using Port-per-Thread Model


Workshop: PMBS26: The 17th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computer Systems

Authors: Jun Tan and Boning Li (Rensselaer Polytechnic Institute), Kevin Brown (Argonne National Laboratory), Zhiling Lan (University of Illinois Chicago), and Christopher Carothers (Rensselaer Polytechnic Institute)

Abstract: The cycle-accurate modeling methodology, used by popular tools such as BookSim2, Gem5, and SST, has become a de facto standard for modeling HPC networks and systems. However, single-threaded cycle loops limit the system size and time scales that can be explored. In this work, we developed PortWarp, a new cycle-accurate approach that efficiently models exascale-class HPC network designs by leveraging GPU accelerators. Because the thread-per-port mapping is hardware-agnostic, the identical validated build achieves 445x speedup on an NVIDIA H100 and 513x speedup on a B100 GPU, with the additional gain coming entirely from newer hardware. Per-port-occupancy instrumentation confirms that in the saturation regime where those speedups are realized, nearly every port-thread performs useful work each cycle. Overall, we are encouraged by PortWarp's performance gains and believe this modeling approach could be applied to other HPC computer systems modeling domains.


Back to PMBS26: The 17th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computer Systems Archive Listing

Back to Full Workshop Archive Listing