Board- and rack-scale optical interconnection architectures for disaggregated data centers

This paper introduces a new interface of an optical pin for Printed Circuit Boards (PCBs), the V-shape cut type which is an innovation from the 90-degree cut type optical pin. The effectiveness is determined by optical characteristics through OptiCAD and by experiment. The simulation used a model of ray tracing analysis which is a one to two (split) connection function model. For the experiment, a Polymer Optical Fibre (POF) V-shape optical pin has been fabricated. It was found that the V-shaped optical pin has a multi-branched function and is applicable to optical interconnection. Full Text: PDF ReferencesMikami, O., et al. Optical pin interface for 90-deg optical path conversion coupling to Printed Wiring Board. in Region 10 Conference (TENCON), 2016 IEEE. 2016. IEEE. CrossRef DeCusatis, C., Data center architectures, in Optical Interconnects for Data Centers. 2017, Elsevier. p. 3-41. CrossRef Duranton, M., D. Dutoit, and S. Menezo, Key requirements for optical interconnects within data centers, in Optical Interconnects for Data Centers. 2017, Elsevier. p. 75-94. CrossRef ITOH, Y., et al., Optical Coupling Characteristics of Optical Pin with 45° Micro Mirror for Optical Surface Mount Technology. Journal of The Japan Institute of Electronics Packaging, 2001. 4(6): p. 497-503. CrossRef Uchida, T. and O. Mikami, Optical surface mount technology. IEICE Transactions on Electronics, 1997. 80(1): p. 81-87. CrossRef Papakonstantinou, I., et al., Low-cost, precision, self-alignment technique for coupling laser and photodiode arrays to polymer waveguide arrays on multilayer PCBs. IEEE Transactions on Advanced Packaging, 2008. 31(3): p. 502-511. CrossRef Nakama, K., et al., Optical connection device. 2006, Google Patents. DirectLink Ramaswami, R., K. Sivarajan, and G. Sasaki, Optical networks: a practical perspective. 2009: Morgan Kaufmann. DirectLink Tong, X.C., Advanced materials for integrated optical waveguides. 2014: Springer. CrossRef

Download Full-text

A low-latency high-port count optical switch with optical delay line buffering for disaggregated data centers

Optical Interconnects XVIII ◽

10.1117/12.2289813 ◽

2018 ◽

Author(s):

George Mourgias-Alexandris ◽

Miltiadis Moralis-Pegios ◽

Nikos Terzenidis ◽

Konstantinos Vyrsokinos ◽

Nikos Pleros

Keyword(s):

Data Centers ◽

Delay Line ◽

Optical Switch ◽

Low Latency ◽

Optical Delay Line ◽

Optical Delay ◽

Disaggregated Data

Download Full-text

Optically Connected Memory for Disaggregated Data Centers

2020 IEEE 32nd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) ◽

10.1109/sbac-pad49847.2020.00017 ◽

2020 ◽

Author(s):

Jorge Gonzalez ◽

Alexander Gazman ◽

Maarten Hattink ◽

Mauricio G. Palma ◽

Meisam Bahadori ◽

...

Keyword(s):

Data Centers ◽

Disaggregated Data

Download Full-text

Energy Efficiency and Scalability of Multi-plane Optical Interconnection Networks for Computing Platforms and Data Centers

Optical Fiber Communication Conference ◽

10.1364/ofc.2012.ow3j.4 ◽

2012 ◽

Cited By ~ 3

Author(s):

Piero Castoldi ◽

Nicola Andriolli ◽

Isabella Cerutti ◽

Odile Liboiron-Ladouceur ◽

Pier Giorgio Raponi

Keyword(s):

Energy Efficiency ◽

Interconnection Networks ◽

Data Centers ◽

Optical Interconnection ◽

Computing Platforms

Download Full-text

Energy-efficient space-time optical interconnection architectures for data centers

2013 15th International Conference on Transparent Optical Networks (ICTON) ◽

10.1109/icton.2013.6602925 ◽

2013 ◽

Author(s):

Piero Castoldi ◽

Isabella Cerutti ◽

Pier Giorgio Raponi ◽

Nicola Andriolli ◽

Odile Liboiron-Ladouceur

Keyword(s):

Energy Efficient ◽

Data Centers ◽

Space Time ◽

Optical Interconnection

Download Full-text

DRMaestro: orchestrating disaggregated resources on virtualized data-centers

Journal of Cloud Computing Advances Systems and Applications ◽

10.1186/s13677-021-00238-6 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Marcelo Amaral ◽

Jordà Polo ◽

David Carrera ◽

Nelson Gonzalez ◽

Chih-Chieh Yang ◽

...

Keyword(s):

Data Centers ◽

Data Transfer ◽

Resource Provisioning ◽

Optimal Placement ◽

Sense Data ◽

Network Load ◽

Disaggregated Data ◽

Support Resource ◽

The Impact ◽

Complicated Task

AbstractModern applications demand resources at an unprecedented level. In this sense, data-centers are required to scale efficiently to cope with such demand. Resource disaggregation has the potential to improve resource-efficiency by allowing the deployment of workloads in more flexible ways. Therefore, the industry is shifting towards disaggregated architectures, which enables new ways to structure hardware resources in data centers. However, determining the best performing resource provisioning is a complicated task. The optimality of resource allocation in a disaggregated data center depends on its topology and the workload collocation. This paper presents DRMaestro, a framework to orchestrate disaggregated resources transparently from the applications. DRMaestro uses a novel flow-network model to determine the optimal placement in multiple phases while employing best-efforts on preventing workload performance interference. We first evaluate the impact of disaggregation regarding the additional network requirements under higher network load. The results show that for some applications the impact is minimal, but other ones can suffer up to 80% slowdown in the data transfer part. After that, we evaluate DRMaestro via a real prototype on Kubernetes and a trace-driven simulation. The results show that DRMaestro can reduce the total job makespan with a speedup of up to ≈1.20x and decrease the QoS violation up to ≈2.64x comparing with another orchestrator that does not support resource disaggregation.

Download Full-text