@online{Lenzen_arXiv1607.00298,
TITLE = {CLEX: {Y}et Another Supercomputer Architecture?},
AUTHOR = {Lenzen, Christoph and Wattenhofer, Roger},
LANGUAGE = {eng},
URL = {http://arxiv.org/abs/1607.00298},
EPRINT = {1607.00298},
EPRINTTYPE = {arXiv},
YEAR = {2016},
MARGINALMARK = {$\bullet$},
ABSTRACT = {We propose the CLEX supercomputer topology and routing scheme. We prove that CLEX can utilize a constant fraction of the total bandwidth for point-to-point communication, at delays proportional to the sum of the number of intermediate hops and the maximum physical distance between any two nodes. Moreover, % applying an asymmetric bandwidth assignment to the links, all-to-all communication can be realized $(1+o(1))$-optimally both with regard to bandwidth and delays. This is achieved at node degrees of $n^{\varepsilon}$, for an arbitrary small constant $\varepsilon\in (0,1]$. In contrast, these results are impossible in any network featuring constant or polylogarithmic node degrees. Through simulation, we assess the benefits of an implementation of the proposed communication strategy. Our results indicate that, for a million processors, CLEX can increase bandwidth utilization and reduce average routing path length by at least factors $10$ respectively $5$ in comparison to a torus network. Furthermore, the CLEX communication scheme features several other properties, such as deadlock-freedom, inherent fault-tolerance, and canonical partition into smaller subsystems.},
}