Network topologies for large-scale compute centers: It's the diameter, stupid!
(Presentation - presented in San Jose, CA, USA, Aug. 2016, Invited talk at the IEEE Hot Interconnects 2016 )
Abstract
We discuss the history and design tradeoffs for large-scale topologies in high-performance computing. We observe that datacenters are slowly following due to the growing demand for low latency and high throughput at lowest cost. We then introduce a high-performance cost-effective network topology called Slim Fly that approaches the theoretically optimal network diameter. We analyze Slim Fly and compare it to both traditional and state-of-the-art networks. Our analysis shows that Slim Fly has significant advantages over other topologies in latency, bandwidth, resiliency, cost, and power consumption. Finally, we propose deadlock-free routing schemes and physical layouts for large computing centers as well as a detailed cost and power model. Slim Fly enables constructing cost effective and highly resilient datacenter and HPC networks that offer low latency and high bandwidth under different HPC workloads such as stencil or graph computations.
Documents
download slides:
Recorded talk (best effort)
BibTeX
@misc{hoefler-hoti16, author={Torsten Hoefler}, title={{Network topologies for large-scale compute centers: It's the diameter, stupid!}}, year={2016}, month={Aug.}, location={San Jose, CA, USA}, note={Invited talk at the IEEE Hot Interconnects 2016}, source={http://www.unixer.de/~htor/publications/}, }
