Evaluating Trade-offs in Potential Exascale Interconnect Topologies
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
This study looks at the high-level trade-offs for interconnect architectures that are likely to be available in HPC machines in the 2021-2022 timeframe. The study uses multiple simulation models to look at the effects of varying machine size, injection bandwidth and topology for a selected set of benchmark communication patterns. The studies show the sensitivity of various applications to these network parameters. This study can help inform decisions on node size versus number of nodes, which topology is most efficient for our applications, how much injection bandwidth to provision, etc. These simulations only look at interconnects with maximally configured global bandwidth, and studies of networks configured with less will be the subject of future milestones.
- Research Organization:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC52-07NA27344
- OSTI ID:
- 1468904
- Report Number(s):
- LLNL-TR-756549; 944065
- Country of Publication:
- United States
- Language:
- English
Similar Records
Performance trade-offs in reconfigurable networks for HPC
Reconfigurable Hybrid Interconnection for Static and DynamicScientific Applications