Exploring the effect of noise on the performance benefit of nonblocking allreduce
Patrick M Widener, Kurt Brian Ferreira, Scott Levy, Torsten Hoefler · 2014
Relaxed synchronization offers the potential of maintaining application scalability by allowing many processes to make independent progress when some processes suffer delays. Yet, the benefits of this approach in important parallel workloads have not been investigated in detail. In this paper, we use a validated simulation approach to explore the noise mitigation effects of nonblocking allreduce in workloads where allreduce is a major contributor to total execution time. Although a nonblocking allreduce is unlikely to provide significant benefit to applications in the low-OS-noise environments expected in next-generation HPC systems, we show that it can potentially improve application runtime with respect to other noise types.