Results 1 -
6 of
6
Distributed Shortcut Networks: Layout-aware Low-degree Topologies Exploiting Small-world Effect
, 2013
"... Low communication latency becomes a main concern in highly parallel computers and supercomputers. Random network topologies are best to achieve low average shortest path length and low diameter in hop counts between nodes and thus low communication latency. However, random topologies lead to a prob ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Low communication latency becomes a main concern in highly parallel computers and supercomputers. Random network topologies are best to achieve low average shortest path length and low diameter in hop counts between nodes and thus low communication latency. However, random topologies lead to a problem of increased aggregate cable length on a machine room floor. In this context we propose low-degree non-random topologies that exploit the small-world effect, which has been typically well modeled by some random network models. Our main idea is to carefully design a set of various-length shortcuts that keep the diameter small while maintain an economical cable length. Our experimental graph analysis showed that our proposed topology has low diameter and low average shortest path length, which is considerably better than those of a counterpart 2-D torus and is near to those of a counterpart random topology with the same average degree. Meanwhile, the proposed topology has average cable length drastically shorter than that of the counterpart random topology. Our cycle-accurate network simulation results show that the proposed topology has lower latency by 15 % and almost the same throughput when compared to torus with the same degree.
Swap-and-randomize: A Method for Building Low-latency HPC Interconnects
, 2014
"... Random network topologies have been proposed to create low-diameter, low-latency interconnection networks in large-scale computing systems. However, these topologies are difficult to deploy in practice, especially when re-designing existing systems, because they lead to increased total cable length ..."
Abstract
- Add to MetaCart
Random network topologies have been proposed to create low-diameter, low-latency interconnection networks in large-scale computing systems. However, these topologies are difficult to deploy in practice, especially when re-designing existing systems, because they lead to increased total cable length and cable packaging complexity. In this work we propose a new method for creating random topologies without increasing cable length: randomly swap link endpoints in a non-random topology that is already deployed across several cabinets in a machine room. We quantitatively evaluate topologies created in this manner using both graph analysis and cycle-accurate network simulation, including comparisons with non-random topologies and previously-proposed random topologies.
Augmenting Low-latency HPC Network with Free-space Optical Links
, 2015
"... Various network topologies can be used for deploying High Performance Computing (HPC) clusters. The network topology, which connects switches in cabinets on a machine room floor, is typically defined once and for all at system deployment time. For a diverse application workload, there are downsides ..."
Abstract
- Add to MetaCart
(Show Context)
Various network topologies can be used for deploying High Performance Computing (HPC) clusters. The network topology, which connects switches in cabinets on a machine room floor, is typically defined once and for all at system deployment time. For a diverse application workload, there are downsides to having a single wired topology. In this work, we propose using free-space optics (FSO) in large-scale systems so that a diverse application workload can be better supported. A high-density layout of FSO terminals on top of the cabinets is determined that allows line-of-sight communication between arbitrary cabinet pairs. We first show that our proposal reduces both end-to-end network latency and total cable length when compared to a wired topology. We then demonstrate that the use of FSO links improves the embedding/partitioning capabilities of a wired topology. More specifically, we show that a recently proposed random low-latency topology can be augmented with a reasonable number of FSO links to support multiple k-ary n-cube and fat tree embedded topologies. Finally, we investigate power-aware on/off link regulation techniques and show how adding/reconfiguring FSO links leads to both performance and power efficiency improvements.
Layout-aware Expandable Low-degree Topology
"... Abstract—System expandability becomes a major concern for highly-parallel computers and datacenters, because their number of nodes gradually increases year by year. In this context we propose a low-degree expandable topology and its floor layout in which a cabinet or node set can be newly inserted b ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—System expandability becomes a major concern for highly-parallel computers and datacenters, because their number of nodes gradually increases year by year. In this context we propose a low-degree expandable topology and its floor layout in which a cabinet or node set can be newly inserted by connecting short cables to a single existing cabinet. Our graph analysis shows that the proposed topology has low diameter, low average shortest path length and short aggregate cable length comparable to existing topologies with the same degree. When incrementally adding nodes and cabinets to the proposed topology, its diameter and average shortest path length increase modestly. Flit-level network simulation results show that the proposed topology has lower latency for three synthetic traffic patterns as expected from graph analysis. Our event-driven network simulation results show that the proposed topology provides a comparable performance to 2-D torus even for bandwidth-sensitive parallel applications. Index Terms—Network expandability, network topologies, small-world networks, interconnection networks, high-performance computing. I.
Darkfiber Planning for Extensible HPC Network Design Under Uncertainties
"... Abstract—Cabling negatively affects not only the expandability of HPC systems, but also the reliability of their communications. In effect, the deployment of a supercomputer requires thousands of kilometers of cables, which are generally buried under the floor. Hence, moving or replacing these fiber ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Cabling negatively affects not only the expandability of HPC systems, but also the reliability of their communications. In effect, the deployment of a supercomputer requires thousands of kilometers of cables, which are generally buried under the floor. Hence, moving or replacing these fibers is impossible once a supercomputer is deployed. In this study, we propose to exploit an efficient cabling method to enable multiple topologies in a system expanded incrementally. This approach reduces the cost of implementing an HPC system stage after stage, while requiring a limited knowledge about the future target applications and the final size of the system. Index Terms—Cabling, interconnection networks, network topology, high-performance computing I.
Skywalk: a Topology for HPC Networks with Low-delay Switches
, 2014
"... With low-delay switches on the horizon, end-to-end latency in large-scale High Performance Computing (HPC) interconnects will be dominated by cable delays. In this context we define a new network topology, Skywalk, for deploying low-latency interconnects in upcoming HPC systems. Skywalk uses random ..."
Abstract
- Add to MetaCart
With low-delay switches on the horizon, end-to-end latency in large-scale High Performance Computing (HPC) interconnects will be dominated by cable delays. In this context we define a new network topology, Skywalk, for deploying low-latency interconnects in upcoming HPC systems. Skywalk uses randomness to achieve low latency, but does so in a way that accounts for the physical layout of the topology so as to lead to further cable length and thus latency reductions. Via graph analysis and discrete-event simulation we show that Skywalk compares favorably (in terms of latency, cable length, and throughput) to traditional low-degree torus and moderate-degree hypercube topologies, to high-degree fully-connected Dragonfly topologies, to the HyperX topology, and to recently proposed fully random topologies.