EvalNet: A Practical Toolchain for Generation and Analysis of Extreme-Scale Interconnects
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908928591265792 |
|---|---|
| author | Besta, Maciej Iff, Patrick Schneider, Marcel Blach, Nils Maissen, Alessandro Di Girolamo, Salvatore Domke, Jens Krattenmacher, Jascha Lakhotia, Kartik Monroe, Laura Petrini, Fabrizio Gerstenberger, Robert Hoefler, Torsten |
| author_facet | Besta, Maciej Iff, Patrick Schneider, Marcel Blach, Nils Maissen, Alessandro Di Girolamo, Salvatore Domke, Jens Krattenmacher, Jascha Lakhotia, Kartik Monroe, Laura Petrini, Fabrizio Gerstenberger, Robert Hoefler, Torsten |
| contents | The diversity of communication paths in a network, especially non-minimal paths, is a key enabler of performance at extreme scales. We present EvalNet, a toolchain for scalable generation and analysis of over 25 important network topologies, such as Slim Fly, PolarFly, and Orthogonal Fat Trees, with a strong focus on path diversity metrics. EvalNet provides an extensive and fine-grained analysis of shortest and non-shortest paths, including their multiplicities, lengths, and interference. It supports exact measurement and visualization of bandwidth and throughput between every router pair, enabling unprecedented insight into routing potential. EvalNet also includes detailed models for construction cost and power consumption, and interfaces seamlessly with established simulators, which we tune to support large-scale evaluations on low-cost hardware. Using EvalNet, we deliver the widest and most comprehensive path diversity study to date, demonstrating how path diversity underpins throughput and scalability, and facilitating progress towards new frontiers in extreme-scale network design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2105_12663 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | EvalNet: A Practical Toolchain for Generation and Analysis of Extreme-Scale Interconnects Besta, Maciej Iff, Patrick Schneider, Marcel Blach, Nils Maissen, Alessandro Di Girolamo, Salvatore Domke, Jens Krattenmacher, Jascha Lakhotia, Kartik Monroe, Laura Petrini, Fabrizio Gerstenberger, Robert Hoefler, Torsten Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Performance The diversity of communication paths in a network, especially non-minimal paths, is a key enabler of performance at extreme scales. We present EvalNet, a toolchain for scalable generation and analysis of over 25 important network topologies, such as Slim Fly, PolarFly, and Orthogonal Fat Trees, with a strong focus on path diversity metrics. EvalNet provides an extensive and fine-grained analysis of shortest and non-shortest paths, including their multiplicities, lengths, and interference. It supports exact measurement and visualization of bandwidth and throughput between every router pair, enabling unprecedented insight into routing potential. EvalNet also includes detailed models for construction cost and power consumption, and interfaces seamlessly with established simulators, which we tune to support large-scale evaluations on low-cost hardware. Using EvalNet, we deliver the widest and most comprehensive path diversity study to date, demonstrating how path diversity underpins throughput and scalability, and facilitating progress towards new frontiers in extreme-scale network design. |
| title | EvalNet: A Practical Toolchain for Generation and Analysis of Extreme-Scale Interconnects |
| topic | Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Performance |
| url | https://arxiv.org/abs/2105.12663 |