LACIN: Linearly Arranged Complete Interconnection Networks
Ram\'on Beivide (1, 2), Crist\'obal Camarero (1), Carmen Mart\'inez (1), Enrique Vallejo (1), Mateo Valero (2) ((1) Universidad de Cantabria, SPAIN, (2) Barcelona Supercomputing Center, SPAIN)

TL;DR
LACIN introduces a novel complete graph-based interconnection network design that simplifies cabling and routing, facilitating scalable deployment from small VLSI systems to large supercomputers.
Contribution
The paper presents LACIN, a new set of complete graph implementations with identical port indexing, reducing complexity in cabling and routing for large-scale interconnection networks.
Findings
Reduces cabling complexity in large networks
Simplifies routing in hierarchical interconnection topologies
Eases deployment across various scales of parallel systems
Abstract
Several interconnection networks are based on the complete graph topology. Networks with a moderate size can be based on a single complete graph. However, large-scale networks such as Dragonfly and HyperX use, respectively, a hierarchical or a multi-dimensional composition of complete graphs. The number of links in these networks is huge and grows rapidly with their size. This paper introduces LACIN, a set of complete graph implementations that use identically indexed ports to link switches. This way of implementing the network reduces the complexity of its cabling and its routing. LACIN eases the deployment of networks for parallel computers of different scales, from VLSI systems to the largest supercomputers.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInterconnection Networks and Systems · Parallel Computing and Optimization Techniques · VLSI and FPGA Design Techniques
