Microsoft Technology Licensing, LLC

Hitesh Ballani

Paolo Costa

Christian L Belady

Winston Allen Saunders

Douglas M Carmean

Kai Shi

Thomas Karagiannis

Antony Rowstron

Lisa Ru-feng Hsu

Lisa Ru-Feng Hsu

Daniel Jonathan Finchley Cletheroe

Istvan Haller

Foteini Karinou

Sophie Gloria Lange

Krzysztof Jozwik

Charles Walter Boecker

Christopher Wilson

Richard James Baca

Gilberto Brambilla

Raphael Eric Alfred Behrendt

Marcos Kawazoe Aguilera

Richard John Black

Antony Ian Taylor Rowstron

Benn Charles Thomsen

Gregory O'Shea

Thomas M Talpey

Birjodh S Tiwana

Eno Thereska

Mahesh Balakrishnan

Virajith Jalaparti

A system for efficiently interconnecting computing nodes can include a plurality of computing nodes and a plurality of network switches coupled in parallel to the plurality of computing nodes. The system can also include a plurality of node interfaces. Each computing node among the plurality of computing nodes can include at least one node interface for each network switch among the plurality of network switches. The plurality of node interfaces corresponding to a computing node can be configured to send data to another computing node via the plurality of network switches. The system can also include a plurality of switch interfaces. Each network switch among the plurality of network switches can include at least one switch interface for each computing node among the plurality of computing nodes. A switch interface corresponding to the computing node can be coupled to a node interface corresponding to the computing node.

Efficiently interconnecting computing nodes to enable use of high-radix network switches

A switching network for effecting point-to-point communication between nodes has a time-varying switching configuration, which causes successive activation and deactivation of multiple channels of the switching network, a first of the channels connecting, when activated, a transmitter node and a first receiver node, and a second of the channels connecting, when activated, the transmitter node and a second receiver node. In a training phase, a method comprises: transmitting from the transmitter node via each channel a known training signal, to cause each receiver node to receive a distorted training signal, using the first distorted training signal and knowledge of the first known training signal to determine respective one or more transmit-side equalizer (EQ) coefficients for each channel, and storing, in memory accessible to the transmitter node, the first transmit-side EQ coefficients, in association with each channel, for use in conducting scheduled communications over the switching network in a communications phase.

Communication in a switching network

A method of fabricating a graded-index polymer optical fibre comprises preparing a cladding composition, the cladding composition comprising either a mixture of a cladding polymer and a dopant or a mixture of a cladding polymer precursor and a dopant; forming cladding from the cladding composition around a core, the core comprising a core polymer; and causing diffusion of the dopant into the core such that the dopant has a continuous concentration gradient, according to which concentration gradient the concentration of the dopant increases with radial distance from a centre of the core. The dopant is a compound having a refractive index which is lower than a refractive index of the core polymer. By distributing the dopant such that the dopant concentration is lowest at the centre of the core, the optical attenuation of the graded-index polymer optical fibre may be reduced. Also provided is a graded-index polymer optical fibre obtainable by the method.

Graded-index polymer optical fibre and the fabrication thereof

A method of fabricating a multi-core polymer optical fibre comprises arranging optical fibre preforms in a stack, the optical fibre preforms each comprising a polymer core and polymer cladding surrounding the polymer core; and drawing and bonding the stack to form the multi-core polymer optical fibre. Any contaminants or impurities which collect on outer surfaces of the preforms may be confined to boundaries between the preforms, which may avoid attenuation of signals passed through the cores while at the same time reducing crosstalk between cores of the final manufactured fibre. Also provided is a multi-core polymer optical fibre obtainable by the method.

Multi-core polymer optical fibre and the fabrication thereof

A system for using free-space optics to interconnect a plurality of computing nodes can include a plurality of optical transceivers that facilitate free-space optical communications among the plurality of computing nodes. The system may ensure a line of sight between the plurality of computing nodes and the optical transceivers to facilitate the free-space optical communications. The line of sight may be preserved by the position or placement of the computing nodes in the system. The position or placement of the computing nodes may be achieved by using different shaped enclosures for holding the computing nodes.

Sloping single point optical aggregation

A system for interconnecting a plurality of computing nodes includes a plurality of optical circuit switches and a plurality of electrical circuit switches. A first network stage comprises a first plurality of circuit switches selected from among the plurality of optical circuit switches and the plurality of electrical circuit switches. Each computing node among the plurality of computing nodes is optically coupled to at least one of the first plurality of circuit switches. A second network stage comprises a second plurality of circuit switches selected from among the plurality of optical circuit switches and the plurality of electrical circuit switches. Each circuit switch among the first plurality of circuit switches is optically coupled to each circuit switch among the second plurality of optical circuit switches.

Efficiently interconnecting a plurality of computing nodes to form a circuit-switched network

A system for using free-space optics to interconnect a plurality of computing nodes can include a plurality of node optical transceivers that are electrically coupled to at least some of the plurality of computing nodes. The system can also include a plurality of router optical transceivers that facilitate free-space optical communications with the plurality of node optical transceivers. Each node optical transceiver among the plurality of node optical transceivers can have a corresponding router optical transceiver that is optically coupled to the node optical transceiver. The system can also include a router that is coupled to the plurality of router optical transceivers. The router can be configured to route the free-space optical communications among the plurality of computing nodes.

Using free-space optics to interconnect a plurality of computing nodes

In various examples there is a communications network comprising a plurality of nodes connected via an interconnection medium to form a receive-from-many communications network. The network has a synchronisation mechanism which synchronizes a signal frequency of the nodes. The network has at least one store holding signal amplitude data of signals previously sent between specified pairs of nodes of the communications network. An amplitude controller uses the stored data to adjust amplitudes of signals communicated between at least one of the pairs of nodes of the communications network.

Amplitude caching in receive from many communications networks

Methods of predicting datacenter performance to improve provisioning are described. In an embodiment, a resource manager element receives a request from a tenant which describes an application that the tenant wants executed by a multi-resource, multi-tenant datacenter. The request that has been received is mapped to a set of different candidate resource combinations within the datacenter, where each candidate resource combination can be used to execute the application in a manner which satisfies a high level constraint specified within the request. This mapping may, for example, be performed using a combination of benchmarking and an analytical model. In some examples, each resource combination may comprise a number of virtual machines and a bandwidth between those machines. Data relating to at least a subset (and in some examples, two or more) of the candidate resource combinations is then presented to the tenant.

Predicting datacenter performance to improve provisioning

Methods of offering network performance guarantees in multi-tenant datacenters are described. In an embodiment, a request for resources received at a datacenter from a tenant comprises a number of virtual machines and a performance requirement, such as a bandwidth requirement, specified by the tenant. A network manager within the datacenter maps the request onto the datacenter topology and allocates virtual machines within the datacenter based on the available slots for virtual machines within the topology and such that the performance requirement is satisfied. Following allocation, stored residual capacity values for elements within the topology are updated according to the new allocation and this updated stored data is used in mapping subsequent requests onto the datacenter. The allocated virtual machines form part of a virtual network within the datacenter which is allocated in response to the request and two virtual network abstractions are described: virtual clusters and virtual oversubscribed clusters.

Offering network performance guarantees in multi-tenant datacenters

Growing community of inventors

Cambridge, United Kingdom

Hitesh Ballani