The OSMOSIS optical packet switch for supercomputers

RP Luijten, R Grzybowski - Optical Fiber Communication Conference, 2009 - opg.optica.org
The OSMOSIS Optical Packet Switch for Supercomputers Page 1 The OSMOSIS Optical
Packet Switch for Supercomputers Ronald P. Luijten Richard Grzybowski IBM Research …

Designing a crossbar scheduler for HPC applications

C Minkenberg, F Abel, P Muller, R Krishnamurthy… - Ieee …, 2006 - ieeexplore.ieee.org
A crucial part of any high-performance computing (HPC) system is its interconnection
network. Corning and IBM are jointly developing a demonstration interconnect based on …

Viable opto-electronic HPC interconnect fabrics

R Luijten, C Minkenberg, R Hemenway… - SC'05: Proceedings …, 2005 - ieeexplore.ieee.org
We address the problem of how to exploit optics for ultrascale High Performance Computing
interconnect fabrics. We show that for high port counts these fabrics require multistage …

Performance of a speculative transmission scheme for scheduling-latency reduction

I Iliadis, C Minkenberg - IEEE/ACM Transactions on Networking, 2008 - ieeexplore.ieee.org
Low latency is a critical requirement in some switching applications, specifically in parallel
computer interconnection networks. The minimum latency in switches with centralized …

On the routing and scalability of mzi-based optical beneš interconnects

M Kynigos, JA Pascual, J Navaridas, M Luján… - Nano Communication …, 2021 - Elsevier
Silicon Photonic interconnects are a promising technology for scaling computing systems
into the exa-scale domain. However, there exist significant challenges in terms of optical …

Grant‐Aware Scheduling Algorithm for VOQ‐Based Input‐Buffered Packet Switches

KE Han, J Song, DU Kim, JW Youn, C Park… - ETRI …, 2018 - Wiley Online Library
In this paper, we propose a grant‐aware (GA) scheduling algorithm that can provide higher
throughput and lower latency than a conventional dual round‐robin matching (DRRM) …

Speculative flow control for high-radix datacenter interconnect routers

C Minkenberg, M Gusat - 2007 IEEE International Parallel and …, 2007 - ieeexplore.ieee.org
High-radix switches are desirable building blocks for large computer interconnection
networks, because they are more suitable to convert chip I/O bandwidth into low latency and …

Optimizing the performance of a data vortex interconnection network

A Shacham, K Bergman - Journal of Optical Networking, 2007 - opg.optica.org
The definition of the data vortex architecture leaves broad room for decisions regarding the
exact design point required for achieving a desired performance level. A detailed simulation …

Obtaining the optimal configuration of high-radix combined switches

JA Villar, FJ Andujar, JL Sanchez, FJ Alfaro… - Journal of Parallel and …, 2013 - Elsevier
High-radix switches reduce network cost and improve network performance, especially in
large switch-based interconnection networks. However, there are some problems related to …

Towards Sub-microsecond Optical Circuit Switched Networks for Future Data Centers

JL Benjamin - 2020 - discovery.ucl.ac.uk
The combination of ever-growing data demand and the slowing down of Moore's law are
creating substantial pressure to today's Data Center Networks, forcing them to scale. On one …