Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Tuesday, March 8
 

1:00pm

Pre-Summit Badge Pick Up
Tuesday March 8, 2016 1:00pm - 6:00pm
Concourse
 
Wednesday, March 9
 

8:00am

Expo Hall Open
Wednesday March 9, 2016 8:00am - 10:00am
Grand Ballroom

8:00am

Breakfast
Wednesday March 9, 2016 8:00am - 10:00am
Grand Ballroom

8:00am

Registration
Wednesday March 9, 2016 8:00am - 7:00pm
Concourse

8:00am

Hackathon BEGINS
Wednesday March 9, 2016 8:00am - Thursday March 10, 2016 10:00am
Exec Ballrooms 210A&E

10:00am

Opening Keynote: Welcome/Intro - Jason Taylor, Facebook
Speakers
JT

Jason Taylor

President and Chairman of the Open Compute Project, and VP of Infrastructure, Facebook


Wednesday March 9, 2016 10:00am - 10:20am
Hall 1

10:00am

10:20am

Platinum Sponsored Keynote: Jason Waxman, Intel
Speakers
JW

Jason Waxman

Corporate Vice President, Data Center Group GM Cloud Platforms Group,, Intel Corporation
Corporate Vice President, Data Center Group, GM Cloud Platforms Group


Wednesday March 9, 2016 10:20am - 10:35am
Hall 1

10:35am

Keynote: Peter J. Winzer, Bell Labs
Speakers
PW

Peter Winzer

Ph.D and Head of the Optical Transmissions Systems and Networks Research Department


Wednesday March 9, 2016 10:35am - 10:45am
Hall 1

10:45am

Fireside Chat w/Peter J. Winzer
Moderators
avatar for Katharine Schmidtke

Katharine Schmidtke

Sourcing Manager, Optical Technology Strategy, Facebook
Katharine is responsible for Optical Technology Strategy at Facebook.  She has more than 20 years experience in the Opto-Electronics industry, including positions at Finisar, JDSU, and New Focus. She has a Ph.D. in non-linear optics from Southampton University in the UK and completed post-doctoral research at Stanford University.

Wednesday March 9, 2016 10:45am - 10:55am
Hall 1

10:55am

Keynote: Mark Russinovich, Microsoft
Speakers
avatar for Mark Russinovich

Mark Russinovich

CTO, Microsoft Azure
Mark Russinovich is Chief Technology Officer of Microsoft Azure, Microsoft’s cloud computing platform. Mark earned a Ph.D. in computer engineering from Carnegie Mellon University and joined Microsoft when it acquired Winternals Software, which he co-founded in 1996. He is also author of the popular Sysinternals Windows administration and diagnostic tools, and coauthor of the Microsoft Press Windows Internals book... Read More →


Wednesday March 9, 2016 10:55am - 11:15am
Hall 1

11:15am

Panel: Telco Discussion with Rachael King, Wall Street Journal
Moderators
RK

Rachael King

Wall Street Journal

Speakers
KD

Ken Duell, AT&T

Assistant VP of New Technology Product Development & Engineering
ME

Mahmoud El-Assir, Verizon

SVP & CIO - Global Technology Services
KL

Kangwon Lee, SK Telecom

Senior Vice President of R&D at SK Telecom Head of Network IT Convergence Lab
DB

Daniel Brower, Deutsche Telekom

Vice President, Engineering Services


Wednesday March 9, 2016 11:15am - 11:45am
Hall 1

11:45am

12:30pm

Lunch
Wednesday March 9, 2016 12:30pm - 2:00pm
Grand Ballroom

12:30pm

Expo Hall Open
Wednesday March 9, 2016 12:30pm - 8:00pm
Grand Ballroom

1:15pm

Expo Hall Stage Talk: Facebook
Speakers
avatar for Kevin Lee

Kevin Lee

Technical Program Manager, Facebook
Kevin Lee is a Technical Program Manager at Facebook working on AI hardware and Facebook's 1S server compute platform. | | Kevin graduated from the University of Waterloo with a Bachelor's degree in Mechanical Engineering. Prior to moving into Technical Program Management, he worked as a Hardware Validation Engineer on a variety of Data Center and server/storage hardware products at Facebook.


Wednesday March 9, 2016 1:15pm - 1:30pm
Expo Hall - Grand Ballroom

2:00pm

Expo Hall Stage Talk: Sony Optical Archive Inc.
Speakers
HS

Horst Schellong

Solutions Architect, Sony Optical Archive Inc.


Wednesday March 9, 2016 2:00pm - 2:15pm
Expo Hall - Grand Ballroom

2:00pm

Executive Track - Intel: Designing the Next Gen Data Center Storage w/NVM Express
Intel and Facebook collaborate to design NVMe storage solution designed to OCP spec and available for broader community contribution and adoption.

Speakers
DA

Dr. Alex Choi

SK Telecom CTO
avatar for Chris Petersen

Chris Petersen

Software Engineer, Facebook
UQ

Uzair Qureshi

Cloud Storage Technologist, Intel Corporation


Wednesday March 9, 2016 2:00pm - 2:25pm
Lower Level: LL20D

2:20pm

Expo Hall Stage Talk: StackVelocity
Speakers
avatar for Doug Taylor

Doug Taylor

Senior Director Open Compute Project Strategy, Strategic OEM Engagements, StackVelocity
Doug Taylor is the Senior Director responsible for StackVelocity’s Open Compute Project Strategy and Strategic OEM Engagements.  StackVelocity is a Platinum level Open Compute Solution Provider offering end-to-end global services for workload-optimized hardware solutions at the platform and data center level. StackVelocity’s rack-level integrated solutions are designed for customers with specific requirements for open source... Read More →


Wednesday March 9, 2016 2:20pm - 2:35pm
Expo Hall - Grand Ballroom

2:30pm

Executive Track - Facebook: Optical interconnects for Datacenters and beyond.
Facebook is hosting a discussion with Microsoft, Google, and Equinix to discuss standardization efforts in data center optics and inter-datacenter (WAN) transport solutions to help the industry move faster on networking. Panelists will discuss areas including WAN architecture, 100G optical interconnects, and single-mode fiber.

Speakers
avatar for Katharine Schmidtke

Katharine Schmidtke

Sourcing Manager, Optical Technology Strategy, Facebook
Katharine is responsible for Optical Technology Strategy at Facebook.  She has more than 20 years experience in the Opto-Electronics industry, including positions at Finisar, JDSU, and New Focus. She has a Ph.D. in non-linear optics from Southampton University in the UK and completed post-doctoral research at Stanford University.


Wednesday March 9, 2016 2:30pm - 2:55pm
Lower Level: LL21A/B

2:40pm

3:00pm

Expo Hall Stage Talk - SanDisk: The Consequences of Infinite Storage Bandwidth
Overall increases in CPU and DRAM processing power are falling behind the massive acceleration in available storage and network bandwidth.  Storage management services are emerging as a serious bottleneck.  What does this imply for the datacenter of the future?  How will it affect the physical network and storage topologies?  And how will storage software need to change to meet these new realities?

Speakers
avatar for Fritz Kruger

Fritz Kruger

SanDisk
Fritz Kruger is a SanDisk Fellow and is the Chief Hardware Architect for SanDisk's Systems and Software Solutions division, where he is driving disruptive innovation to fuel the all-flash-datacenter.  Mr. Kruger has a wide range of engineering experience, from fields as diverse as audio, video, graphics, gaming, supercomputing, databases, and storage; and he holds over 45 patents.  Prior to joining SanDisk in 2012, he was responsible... Read More →


Wednesday March 9, 2016 3:00pm - 3:15pm
Expo Hall - Grand Ballroom

3:00pm

Executive Track - Schneider Electric: Hacking the Conventional Data Center Power Infrastructure
Open Compute has had a revolutionary impact on data center design, offering many simplicity and cost saving benefits. To become more mainstream, we believe critical questions need to be answered about the implications of OCP on the upstream power infrastructure. Can data centers still achieve Tier 3 redundancy? How do I support traditional and OCP loads in the same data center? This presentation will address these and other questions, and propose a series of simplified architectures to support OCP. We will discuss redundancy, availability, and flexibility implications, as well as present a cost analysis. Schneider Electric embraces the spirit of OCP by openly sharing this analysis and making these simplified reference designs freely available.

Speakers

Wednesday March 9, 2016 3:00pm - 3:25pm
Lower Level: LL21A/B

3:00pm

Executive Track: Sony Optical Archive Inc.
Speakers
HS

Horst Schellong

Solutions Architect, Sony Optical Archive Inc.


Wednesday March 9, 2016 3:00pm - 3:25pm
Lower Level: LL20D

3:30pm

Executive Track: Microsoft
Speakers
avatar for Kushagra Vaid

Kushagra Vaid

General Manager – Server Engineering Cloud+Enterprise Division, Microsoft
Kushagra Vaid is the General Manager for Server Engineering in Microsoft’s Cloud & Enterprise division, and is responsible for driving R&D, engineering and operations for server infrastructure deployed across all of Microsoft’s global cloud scale services. The engineering effort includes the Open Cloud Server (OCS) specification that was contributed by Microsoft to the Open Compute Project (OCP) in January 2014. Prior to... Read More →


Wednesday March 9, 2016 3:30pm - 3:55pm
Lower Level: LL21A/B

3:30pm

Executive Track: StackVelocity
Speakers
avatar for Doug Taylor

Doug Taylor

Senior Director Open Compute Project Strategy, Strategic OEM Engagements, StackVelocity
Doug Taylor is the Senior Director responsible for StackVelocity’s Open Compute Project Strategy and Strategic OEM Engagements.  StackVelocity is a Platinum level Open Compute Solution Provider offering end-to-end global services for workload-optimized hardware solutions at the platform and data center level. StackVelocity’s rack-level integrated solutions are designed for customers with specific requirements for open source... Read More →


Wednesday March 9, 2016 3:30pm - 3:55pm
Lower Level: LL20D

3:40pm

Expo Hall Stage Talk - Schneider Electric: The Experience of Deploying OCP- Embrace Internet Giants Data Center Design
The data center for Internet Web Giants have very unique requirement, such as super energy efficiency, cost effective, quick deployment, & etc... . Considering the super lager scale and different business requirements than the traditional enterprise data center, the IG users require unique product as well the new product engineering support & consult from the professional data center vendors. Schneider Electric will present our view on the Internet Data Center and how we co-engineering & co-innovate with the IG customers to accelerate the data center infrastructures evolution.

Speakers

Wednesday March 9, 2016 3:40pm - 3:55pm
Expo Hall - Grand Ballroom

4:00pm

4:00pm

Executive Track - SanDisk: Enabling a New Generation of Services & Applications, Never Before Thought Possible..
Today's flash solutions and arrays can address most data center problems – they are low power, high performance, somewhat scalable  and highly reliable but there is one thing that is holds it back – Favorable Economics. It’s simply way too expensive for at scale workloads making flash out of reach.  We’ll explore how to make flash storage within reach.  

Speakers
BA

Brian Allison

Brian Allison is the Director of Data Center Solutions Marketing for SanDisk. Brian has over 20 years of industry experience in building and driving go-to-market approaches to achieve substantial business growth through technology transitions or changing market trends from a variety of marketing, sales, product management and partner business development roles in the high-tech industry. Brian spent 5 years at Dell, where he drove solutions... Read More →


Wednesday March 9, 2016 4:00pm - 4:25pm
Lower Level: LL20D

4:00pm

4:20pm

Expo Hall Stage Talk - Microsoft: Growing OCS Ecosystem

To meet increasing customer demands of cloud scale, Microsoft is deploying hundreds of thousands of new servers every year, and the company has spent more than $15B building datacenters around the world. At the center of this virtuous cycle is incredible innovation in software, hardware, and processes to address costs of procuring, deploying, operating, and retiring hardware at this scale.

Since 2014, Microsoft has contributed these designs and open source tools to OCP {e.g., server (OCS); back up power with LES (Local Energy Source), etc.}.  Microsoft continues to work with System Providers and Component Suppliers to address cost, easy of deployment, and continuity of supply challenges.  During the presentation Sanjeev Khanna will talk about how Microsoft is working is broaden the ecosystem and how OCP community can take advantage of these innovations and our learnings.


Speakers
avatar for Sanjeev Khanna

Sanjeev Khanna

Senior Director, Microsoft Cloud Infrastructure & Operations, Microsoft
Sanjeev Khanna is versatile leader with 20+ years of broad technology industry experience, successfully building and transforming multi-billion businesses. Strong leadership skills with a balanced combination of strategic, technical, sales & marketing, supply chain & sourcing, finance, and management expertise. Khanna currently holds the position of Senior Director for Microsoft’s Cloud Infrastructure & Operations team, the... Read More →


Wednesday March 9, 2016 4:20pm - 4:35pm
Expo Hall - Grand Ballroom

4:30pm

4:30pm

4:40pm

Expo Hall Stage Talk: Hewlett Packard Enterprise
Speakers
JG

John Gromala

Sr. Director, HPE
Hyperscale Servers & Service Provider Solutions


Wednesday March 9, 2016 4:40pm - 4:55pm
Expo Hall - Grand Ballroom

5:00pm

Executive Track - Intel: The Future of Next Generation Hyperscale Infrastructure for Open Compute An Intel Perspective
Intel Rack Scale Architecture is a logical architecture and is compatible with the hardware designs being contributed and adopted by OCP.

Speakers
MK

Mohan Kumar

Technical Fellow at DCG, Intel


Wednesday March 9, 2016 5:00pm - 5:25pm
Lower Level: LL21A/B

5:30pm

OCP Summit Happy Hour
Wednesday March 9, 2016 5:30pm - 7:00pm
Expo Hall - Grand Ballroom
 
Thursday, March 10
 

8:00am

8:00am

Registration
Thursday March 10, 2016 8:00am - 3:00pm
Concourse

9:00am

Expo Hall Stage Talk: Penguin Computing
Speakers
avatar for Phil Pokorny

Phil Pokorny

Penguin Computing
Philip Pokorny is responsible for all aspects of the Penguin Computing hardware products. After joining the company in February, 2001 as an engineer, he has steadily taken on more responsibilities. He brings a wealth of both customer and engineering experience to the design, development and support of Penguin Computing products. Prior to Penguin Computing, he spent 14 years in various engineering and system administration roles with Cummins, Inc... Read More →


Thursday March 10, 2016 9:00am - 9:15am
Expo Hall - Grand Ballroom

9:00am

Multi-Node Management Specification
Live Stream - http://www.youtube.com/watch?v=NOS4Hira8mY

Presentation the latest Multi-Node Management specification. The aim from this presentation is to get & collect more feedback before we present the spec for voting.

Speakers
avatar for Brian Kelly

Brian Kelly

Sr.Firmware Dev Engineer, Microsoft


Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL21C

9:00am

Open Networking Moves from Data Center Top-of-Rack to Network Core and Network Edge
View live stream at: http://www.youtube.com/watch?v=G5f3AW_avdI


Open Networking in Open Compute has grown from simple hardware only designs for data center Top or Rack (ToR) switching to a complete ecosystem of hardware providers, commercial network operating system providers, open source applications, and open source network operating systems. The benefits realized by Open Networking is much more than a simple reduction in capex spending it is about reduction of vendor lock in with freedom of choice, rapid innovation through fast paced start-ups and community based projects , and expedited delivery of new services to end users. Open Networking is now migrating to the center of network topologies while at the same time the access layer of networks. The open networking benefits realized by data center operators is now being pursued by Telecomm operators and also those providing access layer services to Campus and Enterprise customers. Accton and Edgecore will presenting the next chapter in Open Networking with contributions to OCP including a large scale open networking modular system. This modular open networking system is envisioned as the next generation open architecture platform that will allow for the integration of various networking technologies in a common cost effective open form factor. 

Accton and Edgecore will also be presenting contributions to Open Compute that allow open networking to now reach the access layer of networks though contributions of various access layer devices.  It is envisioned that these access contributions will bring the same open networking benefits realized by data center operators, along with the establishment of a new ecosystem of software solution providers, to the Campus and Enterprise markets.

Speakers
JC

Jeff Catlin

Associate Vice President of Technology, Accton Technology Corporation


Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL21A/B

9:00am

Facebook's 1S Server Platform - Yosemite
Live Stream - http://www.youtube.com/watch?v=HF5ZGBIFcqw

Update on Facebook's 1S server platform with various network options.

Speakers

Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL21D

9:00am

Open CloudServer - Next Gen
Live Stream - http://www.youtube.com/watch?v=aI_1b1Si58Q

Provide an overview of the Open CloudServer system: - Next Generation Blade upgrades - New full-width Blade - Chassis Manager upgrade.

 

Speakers
avatar for Mark Shaw

Mark Shaw

Director of Hardware Engineering, Microsoft
Standardized, scalable hardware for the Cloud! Open CloudServers!


Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL20D

9:00am

Review and approve the OCP Storage Charter Document
Live Stream - http://www.youtube.com/watch?v=UgLVZOFdmHI

Project Discussion

Speakers

Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL21E

9:00am

Transforming Networks to an All-IT based Infrastructure with OCP and Open Networking
Live Stream - http://www.youtube.com/watch?v=exWDwTQFBHE


As the leading telecom operator in Korea, SK Telecom is trying to transform its infrastructure into All-IT based unified infrastructure to prepare for changing environments. One of the key components in such transformation is utilizing commodity hardware and open source to implement telco-grade SDN environment. As an attempt to achieve aforementioned goal, SK Telecom ran a PoC on how OCP certified networking hardware can be utilized for telco-level operating environment.

Specifically, one task was porting an OpenFlow agent on ONL (Open Network Linux) and FB Wedge for SDN use case to interact with SONA, SKT’s SDN Platform based on ONOS project. Another task was porting a new network OS (OpenSwitch) on FB Wedge, to support legacy networking use case. With the PoC, SK Telecom could learn the lessons and details on how to improve legacy network infra and adopt SDN feature, with commodity hardware & customized hardware based on open architecture. Another approach SK Telecom has been taking on customized hardware with open architecture is to build a converged network appliance design for virtualized network services. T-CAP is the latest approach toward such goal, pursuing both flexibility & cost effectiveness. The first hardware model of T-CAP will be displayed during the summit. Open Networking has created new opportunities and new challenges for Data Center designers and implementers. Many customers are used to using monolithic solutions from a single integrator.

When using Open Networking solutions from multiple providers, a few key questions arise: will it all work? Are there common interfaces I can use to monitoring and control the hardware? How do Data Center designers and implementers ensure that the components they’ve chosen will be interoperable?

Speakers
avatar for Junho Suh

Junho Suh

Manager, SK Telecom
Currently, I am a research engineer at SKT. Before joining SKT, I received a Ph.D. in network systems at Seoul National University in 2015. Prior to SNU, I received BS at KAIST in Electrical Engineering and Computer Science in 2008. While doing BS, I joined WINE lab and carried out the projects regarding the wireless networks such as a vehicular ad-hoc network with 802.11p WAVE protocol and improving the TCP performance in wireless... Read More →


Thursday March 10, 2016 9:00am - 9:30am
Lower Level: LL21F

9:20am

Expo Hall Stage Talk: QCT
A proud contributor to the OCP community, QCT is pleased to describe its Open Compute lineup, featuring the new Open Rack v2 family of products being unveiled here at the 2016 OCP Summit. Come see the Rackgo X Big Sur, which Facebook is crediting with doubling the speed of its neural network training. We will also showcase two new versatile systems based on the latest Cubby chassis and share QCT’s vision on expanding its OCP designs into 19” EIA systems.

Speakers
avatar for Alan Chang

Alan Chang

Product Marketing Manager, QCT
Alan Chang has been the Product Marketing Manager at QCT (Quanta Cloud Technology) for the past 5 years, helping to define QCT’s own brand Server series (QuantaGrid/QuantaPlex) and Rack solutions (Open Rack, OCS Rack). Graduating from the University of California Irvine with a Master’s Degree in Computer Science and over 10 years of experience in the IT industry, he continues to contribute to the industry at QCT with an extended 5... Read More →


Thursday March 10, 2016 9:20am - 9:35am
Expo Hall - Grand Ballroom

9:30am

Towards a Firmware Update Standard
Live Stream - http://www.youtube.com/watch?v=3yGbwUwwjxc

Discuss proposal to streamline system and device FW updates as well as personality management.


Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL21C

9:30am

Ensuring Interoperability and Open APIs for Open Networking Systems
Live Stream - http://www.youtube.com/watch?v=1vGxK2gB2zo

Open Networking has created new opportunities and new challenges for Data Center designers and implementers. Many customers are used to using monolithic solutions from a single integrator. When using Open Networking solutions from multiple providers, a few key questions arise: will it all work? Are there common interfaces I can use to monitoring and control the hardware? How do Data Center designers and implementers ensure that the components they’ve chosen will be interoperable?

This presentation will cover two key projects related to Interoperability, underway in the Networking group:

1. Interoperability Testing: the content will cover
a) a brief history of the project at the University of New Hampshire InterOperability Lab to test and validate combinations of OCP-certified switches, network operating systems and interface modules,
b) outline the test procedures for ensuring basic interoperability of Open Networking components, including proper physical layer operation for cables, pluggable modules, and switches, as well as baseline packet loss expectations, and
c) plans for further expansion of the testing in 2016.

2. Open Optical Monitoring: the content will cover
a) a brief description of the need for a common set of APIs to access information and control pluggable modules deployed in Open Networking solutions,
b) a review of the project to date,
c) a demonstration of available code enabling ‘Open Optical Monitoring’ and d) plans for the project in 2016.

Speakers
avatar for Craig Thompson

Craig Thompson

Director of Strategic Marketing, Finisar
Craig Thompson is currently Director of Strategic Marketing at Finisar Corporation. In his role Craig focuses on long-term product and technology roadmaps for optical communications, and contributes to advanced development activities supporting the roadmaps. Craig has held a number of marketing and product management roles in optical communications, networking and storage in companies such as Intel, Gennum and EMC, spanning 15 years. Craig... Read More →
avatar for David Woolf

David Woolf

University of New Hampshire InterOperability Laboratory (UNH-IOL)
David Woolf currently leads Data Center initiatives at the University of New Hampshire InterOperability Laboratory (UNH-IOL). While at UNH-IOL, David has led development of dozens of industry-reviewed test programs and procedures as part of the team that has grown the UNH-IOL into a world-class center for interoperability and conformance testing. David has been an active participant in a number industry forums and committee’s addressing... Read More →


Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL21A/B

9:30am

OCP Mezzanine NIC 2.0 Update
Live Stream - http://www.youtube.com/watch?v=cqQUovYlP3U

In the past year, the momentum of OCP Mezzanine card keeps building up. There are more NIC vendors released NIC Mezzanine based on OCP Mezz specification. New use case shows up in OCP community and specification got evolved to give answer to it.

This talk plans to cover below topics:

1. OCP Mezzanine NIC 2.0 specification change since last summit
2. Introduction of KR Mezzanine NIC and connector C
3. 3D package for implementation examples, and how to use them
4. System compatibility with OCP Mezz 2.0
5. Q&A for implementation

Speakers
JN

Jia Ning

Hardware Engineer, Facebook


Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL21D

9:30am

SmartNIC: FPGA Innovation in OCS Servers for Microsoft Azure
Live Stream - http://www.youtube.com/watch?v=zBpO6g9A3jI

Microsoft uses field-programmable gate arrays (FPGAs) to improve performance, reduce power consumption, and provide new capabilities in Azure datacenters. We have designed an FPGA board that plugs into Microsoft-designed OCS servers. In this talk we discuss SmartNIC, an application of FPGAs to networking to enhance our NICs with reconfigurable logic for our software defined networking stack, and demonstrate applications of SmartNIC and FPGAs running in Azure.

Speakers
DF

Daniel Firestone

Principal Software Engineering Manager, Microsoft


Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL20D

9:30am

Open Wear
Live Stream - http://www.youtube.com/watch?v=SPiSxPkhfQA

Project Discussion

Speakers

Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL21E

9:30am

ToRC – Applications, Microservices, and VNFs controlled by the Top-of-Rack Switch
Live Stream - http://www.youtube.com/watch?v=eM3iSWkQODU

What happens when you put a micro server into your network switch? Julius Mueller and Marcel Neuhausler from AT&T Foundry take an edge-computing scenario to showcase and demo how a ToRC (Top-of-Rack Controller) and its extended resource-awareness enables a switch to orchestrate an application in a highly cost-effective and autonomous way. ToRC is based on different open source projects (Mesos, Docker, FBOSS, ONL…) running on an OCP switch (FB Wedge) managing OCP compute hardware.

Speakers
avatar for Julius Mueller

Julius Mueller

Member of Technical Staff, AT&T Foundry
Julius Mueller works in the AT&T Foundry in Palo Alto as Member of Technical Staff focused on virtualization of fixed and mobile networks. He holds a PhD degree that he received for his work in the area of Cross Layer Optimization for Next Generation Networks and Future Internet at TU Berlin and Fraunhofer Institute FOKUS.
avatar for Marcel Neuhausler.

Marcel Neuhausler.

Principal Software Engineer, AT&T Foundry
Marcel Neuhausler is a Principal Software Engineer in the AT&T Foundry in Palo Alto focusing on resource-conscious distributed systems. He is still fascinated by the fact that very little has changed in networking since he taught network programming on TCP/IP, Sun RPC/XDR, and DECnet.


Thursday March 10, 2016 9:30am - 10:00am
Lower Level: LL21F

9:40am

Expo Hall Stage Talk - Emerson Network Power: OCP-Compliant Integrated Rack
Speakers
avatar for Eric Wilcox

Eric Wilcox

Vice President of Engineering for the Hyperscale Solutions team, Emerson Network Power
Eric Wilcox is the Vice President of Engineering for the Hyperscale Solutions team at Emerson Network Power.  Hyperscale Solutions leverages Emerson’s industry leading technology, products and engineering to provide unique problem solving capabilities in the data center space. Eric was the Solutions Architect for the first deployment of Facebook’s Rapidly Deployable Data Center in northern Sweden.  Eric has previous work... Read More →


Thursday March 10, 2016 9:40am - 9:55am
Expo Hall - Grand Ballroom

10:00am

Expo Hall Stage Talk: Wiwynn
Speakers
avatar for Min Chao

Min Chao

Executive Director, Wiwynn Co.
Min Chao, Executive Director of NBDD(New Business Development Department) at Wiwynn Corporation, a networking veteran focus on developing telco specifc and other vertical market segments while leveraging channel partner resources to promote OCP solution. Wiwynn's mission statement: Provide best TCO, workload optimized IT solutions for Data Center. Wiwynn's vision: A value partner for customers in Cloud Service Business.



Thursday March 10, 2016 10:00am - 10:15am
Expo Hall - Grand Ballroom

10:00am

OpenBMC Update
Live Stream - http://www.youtube.com/watch?v=KkHfz4GMiGA

OpenBMC was introduced in OCP summit-2015 and this talk is to present various enhancements done during last year. The updates include support for Multi Node Server platform like 'Yosemite', addition of various ssh-based utilities, and RESTful API implementation.

Speakers
avatar for Tian Fang

Tian Fang

Software Engineer, Facebook
Tian Fang is a software engineer at Facebook, working on the software stack (FBOSS) running on the Facebook network hardware. In the past two years, his focus has been on the OpenBMC project to bring up different Facebook hardware boards. Prior to Facebook, Tian worked at Cisco on various infrastructure projects and at a startup on different routing protocols.
JM

Jubin Mehta

Facebook


Thursday March 10, 2016 10:00am - 10:30am
Lower Level: LL21C

10:00am

Switch Abstraction Interface (SAI)
Live Stream - http://www.youtube.com/watch?v=UPuqCX4PLmw

Switch Abstraction Interface (SAI) has been officially accepted by the Open Compute Project (OCP) as a standardized C interface to program hardware ASICs. SAI came into existence as network operators started seeking ways to adopt a more dynamic, programmable infrastructure. The lack of a common and well understood way to program network switch ASIC’s is a source of reduced agility, increased complexity, poor reliability, and greater cost. SAI helps by being a standardized C API to program ASICs.

SAI allows software to program many different switch chips without undergoing any changes. This helps us to keep the base router platform simple, consistent, and stable. It also reduces the time to market, and enables the adoption of the latest available hardware easily. It breaks the software-hardware coupling and allows us to pick the best fit of software and hardware on a “need by application” or a “need by network” basis. By providing simple, consistent interfaces for applications and protocol stacks that orchestrate and automate cloud services, it helps consume the underlying complex and heterogeneous hardware easily.

This helps in shifting our focus to applications that require integrating our network with our cloud. SAI is, therefore, a big step towards open networking software. Today SAI has 10 contributors, and features that range from basic L3 functionality to more complicated QoS, PFC with RDMA, and buffer management. The SAI demo hosted live at the Microsoft booth will display these features and the power of open networking by integrating 5 different NOS, 5 different switch platforms, 5 different ASICs, over 6 *same* SAI implementations.

Speakers
avatar for Kamala Subramaniam

Kamala Subramaniam

Architect, Microsoft
Kamala Subramaniam is an architect in Azure Networking at Microsoft. She drives the success of the Azure Cloud Switch and the adoption of the Switch Abstraction Interface. She works closely with several operators and vendors in the industry at the OCP to innovate the open networking space.


Thursday March 10, 2016 10:00am - 10:30am
Lower Level: LL21A/B

10:00am

M.2 PCIe Carrier Card
Live Stream - http://www.youtube.com/watch?v=Qrp6G_hbXW8

The talk will cover the details of a M.2 PCIe carrier card specification that will also be submitted. The carrier card fits in a standard full-height PCIe slot and supports up to 4x PCIe M.2 SSDs without the need for a PCIe switch. We will cover the electrical, mechanical, and thermal requirements for the design.

Speakers
avatar for Chris Petersen

Chris Petersen

Software Engineer, Facebook


Thursday March 10, 2016 10:00am - 10:30am
Lower Level: LL21D

10:00am

OCP adoption in 19" EIA architecture
Live Stream - http://www.youtube.com/watch?v=vRhUa3TlDc8

-19" adoptions today
-- Decathlete
-- Roadrunner
--QCT's vision on more 19" architecture
--Leopard
--Yosemite
-- Q&A

Speakers
avatar for Alan Chang

Alan Chang

Product Marketing Manager, QCT
Alan Chang has been the Product Marketing Manager at QCT (Quanta Cloud Technology) for the past 5 years, helping to define QCT’s own brand Server series (QuantaGrid/QuantaPlex) and Rack solutions (Open Rack, OCS Rack). Graduating from the University of California Irvine with a Master’s Degree in Computer Science and over 10 years of experience in the IT industry, he continues to contribute to the industry at QCT with an extended 5... Read More →


Thursday March 10, 2016 10:00am - 10:30am
Lower Level: LL20D

10:00am

NVMe Optional features for Cloud SSD customization
Live Stream - http://www.youtube.com/watch?v=nWCil5jWzjc

SSDs account for a growing share of the costs of large scale application deployments. The NAND in the SSD requires significant management by the flash controller to deal with media requirements. This management layer has significant impact on the usable cost of the SSD, the endurance, the reliability, and the consistency of performance. This has left large datacenters with a few options:
• Leverage commodity SSDs and try to make the workload SSD friendly and deal with sub optimal performance and endurance.
• Write detailed specifications for SSD vendors to respond to with custom cloud SSD products.
• Take on the work of designing an in-house SSD solution that needs to be modified for each NAND generation.

NVMe offers a way to leverage an open standard to enable applications and file system to have more direct control on SSD behavior without the need to design the particular issues for a current generation of NAND or other nonvolatile media. This session will go over the typical operation of a flash controller without application awareness, the optional features available in the NVMe standard that enable applications to direct SSD behavior and the potential benefits of this information to enable more usable capacity, lower cost NAND, and more predictable performance. The particular focus areas in the current and potential standards area are:
• Dataset Management & hinting
• Attribute pools & banding
• Directives - Streams, Garbage collection control
• Limited Retry
• Thin provisioning and variable physical capacity

Speakers

Thursday March 10, 2016 10:00am - 10:30am
Lower Level: LL21E

10:00am

Building an OCP-based Telco CDN Platform
Live Stream - http://www.youtube.com/watch?v=cTo6VWgFCBU

Telco industry have recently embraced the Open Compute Project with the objective of bringing rapid innovation to telco data centers. Facing the growth of internet traffic, especially with the movement towards video content, deployment of Content Delivery Network (CDN) in an operator's network has been the major technical and economic response by telco carriers.

However, there is a subtle difference between building a CDN infrastructure as opposed to a data center, especially for video streaming where bandwidth alone is not enough. There is a need to be able to deliver video steadily and reliably to 100K users simultaneously without so much as a hiccup. At 100G rates and the requirement to deliver packets flawlessly to so many users, managing each individual stream in software is simply not an option. Having the right choice of hardware and software therefore becomes the key to building an efficient Telco CDN appliance. In this presentation, we discuss some of the challenges of CDN, its requirement from underlying infrastructure and how it can be delivered with an OCP based platform.


Thursday March 10, 2016 10:00am - 11:00am
Lower Level: LL21F

10:20am

Expo Hall Stage Talk: Seagate
Speakers
avatar for Jamon Bowen

Jamon Bowen

Jamon Bowen is a Director of Customer Marketing in the Flash Products Division of Seagate. He focuses on the large scale SSD deployments. He is active in the IT community discussing SSD technology and has been a member of the board of directors of SNIA's Solid State Storage Initiative. | | Jamon Bowen has been supporting enterprise SSD deployments since 2004 for very demanding applications. Previously, he was the Director of Web Cloud Marketing... Read More →


Thursday March 10, 2016 10:20am - 10:35am
Expo Hall - Grand Ballroom

10:30am

Out of Band Management for OCP Server PCIe add-on-cards and SSDs
Live Stream - http://www.youtube.com/watch?v=_alt6Vx0n0I

The I2C sideband management feature developed for PCIe add-on-cards (AOC) by the OCP community can be a very useful tool for running datacenters more efficiently and offers potential for advanced server management of SSDs. This session will look at how the development of active monitoring of high performance PCIe SSDs by the BMC in OCP servers resulted in significant operational cost savings and SSD endurance management for large scale PCIe flash deployments.

The Add-on-Card Thermal Interface Spec for Intel Motherboard V3.0 specification defines an I2C/SMBus for the SSDs/PCIe AOCs for the BMC in OCP servers. With this the BMC can make decisions to keep server working under most efficient operating range lowering cost of operation. One such use case is temperature monitoring of these devices by BMC so it can dynamically control fan speed to provide adequate cooling. The SSD/PCIe AOC presents itself as an emulated temperature sensor so BMC can get temperature reading as if it is getting directly from a temperature sensor. SSDs draw power based on the type of workload that is presented to them and this power draw can vary over a surprising large range. Heavy writes (the worst workload) draw the maximum power and make them very hot whereas other workload draws significantly different power. These workloads do not necessarily stress other parts of the server, so in the absence of temperature monitoring of the SSDs and dynamic fan control, the server has to assume the worst thermal profile and run fans at the maximum speed. SSD endurance is limited to a certain number of petabytes written so it is impractical that this worst case workload will be running for more than a small fraction of a SSDs life. Additionally, the temperature of the NAND on an SSD is an important input into the endurance that and SSD can deliver, particularly lower cost NAND options. This combination of operational cost savings and lower cost NAND make this a particularly valuable feature that is provided to the OCP community. This mechanism of out-of-band management can be further extended to monitor other aspect of SSDs/PCIe AOCs. The session will cover the potential to more advanced monitoring such as:
• Power: Power consumption, power state transitions etc.
• SSD life cycle metrics like percentage drive life used, SMART data, Throttling information, FW slot information. Basically some of the monitoring already covered as part of NVMe standard.
• Errors logs and crash logs to provide adequate debugging information of failures.

Speakers

Thursday March 10, 2016 10:30am - 11:00am
Lower Level: LL21C

10:30am

Azure Cloud Switch (ACS)
Azure Cloud Switch (ACS) - Live Stream - http://www.youtube.com/watch?v=5XFm9EteAks

The cloud depends on high-speed, highly available networks to power their services. This makes it critical for network operators to be able to control their own destiny by rapidly adding to their network features they need while keeping out feature changes that increase risk and complexity. ACS came into existence to simplify the way we manage our data center networks. Part of that challenge was to manage the fleet of switches like we manage our servers. To be able to use new switching ASICs from various switch ASIC vendors to reduce time to market. To be able to develop new applications on the switch easily. ACS uses Linux as the base operating system and breaks the software running on the box into different modules. A set of software modules are developed to manage the switch ASICs as well as software routing stack such as BGP. Like any other software modules in Linux, users can use common Linux tools to manage these modules independently.

For example, user can use popular Linux automation tools such as Puppet, Chef and Ansible to manage them. This makes managing this Linux switch box no different than managing all the servers in our data centers in principle. As a result, we integrate this Linux-based box with our network management stack to enable some agile software development practices such as weekly software upgrade and quick bug fix rollout. Azure cloud switch software stack runs on top of Switch Abstraction Interface (SAI), which allows the same software stack to run across different switch platforms. SAI provides a set of unified switch control C APIs across multiple ASICs. Azure cloud switch provides a shared storage for all switch states, which allows users to easily develop new applications to manage the switch states. We developed a switch state service which manages all states within the switch. It provides a consistent view of all switch states to any application that subscribes to them. Above the switch state service, developers can then develop different applications to manage any switch based on the up-to-date view. Below the switch state service, sync agents synchronize the switch states to the hardware throughout SAI.

In summary, this demo presents ACS as a collection of software modules with Linux as the base OS, that runs on top of several switch ASICs, Broadcom, Mellanox, Cavium, Centec, Mediatek, and Barefoot. It allows user to easily integrate switch with existing automation and management software to support agile software development and deployment. The software stack also provides a central place to store all switch states and allow multiple applications orchestrate the switch resource management.

Speakers
avatar for Kamala Subramaniam

Kamala Subramaniam

Architect, Microsoft
Kamala Subramaniam is an architect in Azure Networking at Microsoft. She drives the success of the Azure Cloud Switch and the adoption of the Switch Abstraction Interface. She works closely with several operators and vendors in the industry at the OCP to innovate the open networking space.


Thursday March 10, 2016 10:30am - 11:00am
Lower Level: LL21A/B

10:30am

Big Sur, An OCP GP-GPU Server
Live Stream - http://www.youtube.com/watch?v=Nl1sz2u6BvE

This talk will go in detail about the architecture of the Big Sur GP-GPU server. We detail the server at the block diagram level as well as explaining the flexibility of the PCI-e setup that allows to connect 4 GPUs per CPU or all 8 GPUs connected to one CPU.

Speakers
avatar for Kevin Lee

Kevin Lee

Technical Program Manager, Facebook
Kevin Lee is a Technical Program Manager at Facebook working on AI hardware and Facebook's 1S server compute platform. | | Kevin graduated from the University of Waterloo with a Bachelor's degree in Mechanical Engineering. Prior to moving into Technical Program Management, he worked as a Hardware Validation Engineer on a variety of Data Center and server/storage hardware products at Facebook.
avatar for Marcos Peixoto

Marcos Peixoto

Facebook
Marcos is responsible for infrastructure product partnerships at Facebook.   Marcos has more than 25 years of experience working in the computer industry.  Marcos has worked in sales and mostly product management at companies such as HP, Sun Microsystems and Acer.  He holds a BSEE from Pontificia Universidade Catolica in Rio de Janeiro, Brazil and a MBA from Santa Clara University.


Thursday March 10, 2016 10:30am - 11:00am
Lower Level: LL21D

10:30am

HPE - Cloudline Servers
Live Stream - http://www.youtube.com/watch?v=ICKQU7bZ95I

Speakers
avatar for Dave Peterson

Dave Peterson

Group Manager, Hyperscale Servers, Hewlett Packard Enterprise


Thursday March 10, 2016 10:30am - 11:00am
Lower Level: LL20D

10:30am

Improving Software Defined Storage Ceph Performance While Reducing Costs
Live Stream - http://www.youtube.com/watch?v=G2w26xwJaUY

Seagate is developing innovative technologies through community collaboration. Seagate's advanced work with shingled magnetic recording HDDs (SMR) flash and caching software can satisfy both performance and cost/capacity objectives, at a lower TCO compared to traditional magnetic (CMR) HDD media. Red Hat Ceph Storage provides a unified, private cloud storage system designed for excellent performance, reliability, and scalability. Together, they enhance private cloud object storage by combining the ultra-low latency of flash with the capacity, space,power and cost effectiveness of SMR HDDs. This session will provide benchmark comparisons of Ceph on SMR with cache acceleration vs. on traditional HDDs.

Speakers

Thursday March 10, 2016 10:30am - 11:00am
Lower Level: LL21E

10:40am

Expo Hall Stage Talk: Cavium
Speakers
RC

Rishi Chugh

Director, Product Marketing, Cavium
As Director, Product Marketing, Rishi Chugh is responsible for product marketing in Cavium's Data Center Processor division, as well as leading specific product management and strategic planning activities for Cavium. Mr. Chugh joined Cavium in August 2013. Prior to joining Cavium, Mr. Chugh held Product Marketing role at Broadcom's Data Center switch product line managing the Trident switch product line. Mr. Chugh has over 18 years of industry... Read More →


Thursday March 10, 2016 10:40am - 10:55am
Expo Hall - Grand Ballroom

11:00am

Expo Hall Stage Talk: Applied Micro
Speakers
KS

Kumar Sankaran

Associate Vice President of Software and Platform Engineering, Applied Micro
Kumar Sankaran is the Associate Vice President of Software and Platform Engineering at Applied Micro. He is responsible for the software architecture and development and platform engineering for the X-Gene family of products from Applied Micro. In addition, he handles the software eco-system development and promotion within the ARM64 community. Kumar has a Bachelor of Engineering degree in Electronics Engineering, a Master of Science... Read More →


Thursday March 10, 2016 11:00am - 11:15am
Expo Hall - Grand Ballroom

11:00am

Redfish and OCP topics
Live Stream - http://www.youtube.com/watch?v=cLlLf5S2xSs

Update on the DMTF Redfish Specification, including new work in progress, and a discussion of an OCP conformance checklist project to provide a standardized implementation target for Redfish support on OCP platforms. New work under development to align Redfish with UEFI and other OCP or industry specifications will also be discussed.

Speakers

Thursday March 10, 2016 11:00am - 11:30am
Lower Level: LL21C

11:00am

OCP Adoption – Revolution with 21” racks vs. Transition from 19” racks
Live Stream - http://www.youtube.com/watch?v=AqB2Z2XZ8oc

Wiwynn shall present our intelligent design of a high-density server by OCP certified mother boards in an chassis for EIA 19” rack. When Open Compute Project proves its efficiency in the energy consumption, reliability and cost for data centers, its demand grows time to time. However, Open Compute Project defined Open Rack spec which is different than conventional rack. To accommodate OCP project means a new investment for traditional data centers.

Carmel, a new generation product of EIA 19” 2U high density server accommodating OCP MB combines the advantages of OCP Leopard MB with the application of EIA 19” chassis. Carmel shows not only the efficiency and reliability of OCP MB but also the application flexibility.

For the 2U 4Nodes architecture, there are 4 high performance MB nodes in a 2U system and each MB node could accommodate 1 full-height half-length PCIe add on card and 1 SSD with 9.5mm thickness; for the 2U 2Nodes, each MB node could accommodate 3 pcs full-height half-length PCIe add on cards and 6 pcs hot-swappable SSDs. Furthermore, the system is designed with Tool-less concept to ease all the maintenance of MBs, SSDs, Fan modules and PSUs.

Integration of up to 4 OCP server boards and EIA 19” 2U chassis converged the OCP benefits and existing investment of data centers seamlessly. Through the sophisticated system design, all the components including Server Sleds, PSUs, Fans, Drives are easy to maintain. System configuration and drives maintenance are front serviceable in the cold aisle like OCP achieved its success.

Speakers
avatar for Bill Lin

Bill Lin

Mechanical Associate Director, Wiwynn


Thursday March 10, 2016 11:00am - 11:30am
Lower Level: LL20D

11:00am

Soft-Hardware: The Foundation of Cloud 2.0
Live Stream - http://www.youtube.com/watch?v=bT0tJG0COTo

This presentation will be a continuation the journey / story outlined in Rackspace's presentation from the OCP 2015 Summit in San Jose.

"...software is eating the world." Many people have heard this phrase, first coined by Marc Andreesen, in 2011. It is now a well-understood phenomenon. Less well understood, is why this phenomenon is facing headwinds, brought about by the decline of Moore's Law.

We all want ever-smarter, more-pervasive, and lower cost computing. We want a world with self-driving cars and five-dollar genome sequences, with instant answers to our most complex questions about the health of our bodies and businesses. These things may be born-in or powered-by a cloud, but not one that exists, today. For many scientists, researchers, engineers, analysts, and other creative minds working on these new horizons, today's clouds are not enough... they are not powerful enough, are too costly, and lack critical functions and tools.

This is a big problem with big opportunities. Addressing it will require a significant shift in how systems are designed, affecting hardware, firmware, and operating systems. Solutions of the future will be powered by new processing, memory, and storage elements, with new software interfaces. And these solutions must operate flexibly with the existing operating systems, software, and tools already in use on today's cloud.

Put together, we call these solutions "Soft-Hardware" – powered by Open Source Hardware & Software movements. The intent of this session is to share Rackspace and its partners are doing to bring this technology to the cloud and to developers and end-users, new and old.

This session will talk about progress, problems, opportunities, and insights that Rackspace has gained on this journey (including updates on the Barreleye server announced during Summit 2015, and what's next). By the end, the audience will have a clearer understanding of how Soft-Hardware will come to life on clouds, how Open Compute and other open source community members can participate in the journey, and ways to profit in the process.

Speakers

Thursday March 10, 2016 11:00am - 11:30am
Lower Level: LL21D

11:00am

Lightning: a flexible NVMe JBOD
Live Stream - http://www.youtube.com/watch?v=W2JiRjfGSFg

The talk will cover the architecture as well as some of the design choices on the Lightning NVMe PCIe JBOD including details on the PCIe topology, connections to the server, and the management solution.

Speakers
avatar for Chris Petersen

Chris Petersen

Software Engineer, Facebook


Thursday March 10, 2016 11:00am - 11:30am
Lower Level: LL21E

11:00am

Low Latency Analytics Platforms for Mobile Edge Computing
Live Stream - http://www.youtube.com/watch?v=SDbY3bNRU4U

We are seeing a convergence of analytics workloads needing HPC type achitectures in both traditional servers and cloud. Analytics workloads are starting to be deployed at the edge of the wireless and wireline networks for a variety of use cases that require ultra low latency. In this presentation as HPC type computing gets deployed into the wireless 4G advanced and 5G networks, we show how some of the analytics workloads that have to be performed close to the edge of the network near users are well serviced using the low latency RapidIO enabled computing being worked on in the OCP. The presentation shows highly dense computing and Top of Rack Switching suitable for modular deployments in either central offices or ruggedized outdoor formats.

Speakers

Thursday March 10, 2016 11:00am - 11:30am
Lower Level: LL21F

11:00am

Hackathon ENDS / Judging Begins
Thursday March 10, 2016 11:00am - 12:00pm
Exec Ballrooms 210A&E

11:20am

Expo Hall Stage Talk - HGST: Storage Building Blocks for Open Compute What’s Hot, What’s Cool. Let’s Build

Traditional monolithic storage doesn’t align with today’s open source scale-out databases and big data frameworks. But creating scalable open-compute clusters with the latest storage building blocks demands expertise in balancing capacity, I/O, throughput, latency and quality of service against budgetary constraints. 

In the early days of open computing, simple concepts like 1:1 core:spindle ratios made it easy to design commodity-based infrastructures.  But in our quest to build vanity free servers, well-intentioned software functions like MySQL/NoSQL sharding and Hadoop replication have compounded server/storage sprawl, driving up space, power and cooling (OpEx).  This unintended consequence has restricted our CapEx budgets for new equipment needed to tackle the next big thing.

With exponential improvements in SSD price/performance and relentless efforts to expand HDD capacities and reliability, 1:1 is no longer the right metric for open compute designs.

This presentation will provide an unbiased view of hot, cool and cold data storage trends, along with benchmarking approaches and new metrics for addressing budget realities.  We will then share construction blueprints for open compute solutions using the latest in SSD, HDD and software technologies that optimize efficiency and fidelity at scale.


Speakers

Thursday March 10, 2016 11:20am - 11:35am
Expo Hall - Grand Ballroom

11:30am

OpenDCRE - Next Generation Data Center Management
Live Stream - http://www.youtube.com/watch?v=83RA1myoWNs

OpenDCRE, the Open Data Center Runtime, is a combination of open-source hardware and software for out-of-band management and monitoring of data centers. OpenDCRE is built on a RESTful API that runs on a Raspberry Pi, or similar footprint, providing rack-level management and sensorfication via power line communications, or via a built-in IPMI bridge. This talk describes the hardware, software and API that comprise OpenDCRE, and demonstrates some of its capabilities.


Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL21C

11:30am

Analytics Platforms for HPC Clusters
Live Stream - http://www.youtube.com/watch?v=WyjqXXOQNPA

We are seeing a convergence of analytics workloads needing HPC type achitectures in both traditional servers and cloud. Analytics workloads are starting to be deployed at the edge of the wireless and wireline networks for a variety of use cases that require ultra low latency. In this presentation as HPC type computing gets deployed into the wireless 4G advanced and 5G networks, we show how some of the analytics workloads that have to be performed close to the edge of the network near users are well serviced using the low latency RapidIO enabled computing being worked on in the OCP. The presentation shows highly dense computing and Top of Rack Switching suitable for modular deployments in either central offices or ruggedized outdoor formats.

Speakers

Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL21F

11:30am

Update on OpenSwitch with OCP Projects
Live Stream http://www.youtube.com/watch?v=sgWCPxt4tCI

In this talk we will show the current status from the OpenSwitch NOS (www.openswitch.net) running on the different OCP networking hardware, and updates on the roadmap and future plans of the project.

Speakers
avatar for Diego Dompe

Diego Dompe

Senior Software Architech, Hewlett Packard Enterprise
Diego Dompe is a Senior Software Architect in Hewlett Packard Enterprise Networking, and an Open Source and Linux expert. He is an specialist on software-hardware interaction and switching silicon. He is also is one of the architects at the OpenSwitch project, where he contributes on a range of topics, from hardware bring-up, to infrastructure and build system, or just hanging on the IRC channel.


Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL21A/B

11:30am

Introduction to Facebook Open Rack V2
Live Stream - http://www.youtube.com/watch?v=NoUVzYlb3sk

This is a entry-level overview of what the features and specifications of the Facebook Open Rack V2. It is intended for individuals that are new to OCP and want to familiarize themselves with what Open Rack V2 is and is not. No new technical information will be presented.

Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL21D

11:30am

Optimized Power Delivery Architecture for Data Center Scale Server Applications
Live Stream - http://www.youtube.com/watch?v=6LXe0RPRCkk

Speakers
avatar for Neilus O'Sullivan

Neilus O'Sullivan

Platforms Power Manager, Google Inc
Leading Platforms Power Development activities at Google.


Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL20D

11:30am

AF-Media High Density All-flash Media Server
Live Stream - http://www.youtube.com/watch?v=indQVJUA5lQ

Abstract AF-Media server is a high density/high efficient all-flash storage server optimized for delivering media contents, developed by SK Telecom. As the leading telecom operator in Korea, SK Telecom was trying to find ways to enhance the service and decrease the TCO of its IPTV service. In order to achieve the goal, SK Telecom cooperated with its two subordinates; SK Hynix, a memory semiconductor of DRAM and Flash chips, and SK Broadband, an internet access and IPTV/CDN service provider. AF-Media was developed as a cooperation project among three companies. AF-Media S16 utilizes the latest Intel Xeon D SoC with 2.5" SATA SSDs and OCP mezzanine network card. The AF-Media features two hot-swappable compute nodes in a 2U form factor to provide an industry leading sixteen hot-swap 2.5" SSD drive bays or two PCIe SSD card slots for largest storage capacity per 1U compute node. Both drives and compute nodes are hot-swappable to facilitate ease of maintenance and minimize down time. To save power and space, the nodes share the same chassis and power supplies. Utilizing AF-Media S16 for its IPTV service, SK Telecom reduced power consumption and density by 80%, while providing better storage and network IO throughput compare to HDD based streaming server system. For this upcoming talk, SK Telecom would like to discuss about the design details, ecosystem, and the support received from OCP projects. As a token of our gratitude, SK Telecom recently upgraded the OCP member ship to Gold level, and expects to continue contributing to OCP for the future.

Speakers
JK

Jungsoo Kim

Manager, SK Telecom


Thursday March 10, 2016 11:30am - 12:00pm
Lower Level: LL21E

11:40am

Expo Hall Stage Talk: Inspur

There are several major rackscale open hardware platforms currently available, including OCP (Facebook Implementation), OCS (Microsoft Implementation), Scorpio Project Designs (Open Datacenter Designs for China), Intel RSA (Rack Scale Architecture).  Datacenter and Cloud designers need to be aware of the differences among them and choose the one which is most suitable for their use case to deploy various types of private cloud, public cloud and hybrid cloud.  We will invite Baidu as case study to speak about their datacenter deployments based on Scorpio Project Designs.


Speakers
DW

Dolly Wu

GM of Datacenter/Cloud USA, INSPUR
Dolly Wu has over 20 years of experience in the high technology industry working with Data Centers, CSPs, Direct End User Customers (in Financial Services, Internet/Cloud, Life Sciences, and Media/Entertainment), VAR/SI, OEMs, Government and Education Customers with focus on Big Data, Cloud Computing, HPC and Storage Market Segments. Currently, Dolly is the GM of Inspur Datacenter/Cloud Division, in charge of opening USA and Canada Markets.


Thursday March 10, 2016 11:40am - 11:55am
Expo Hall - Grand Ballroom

12:00pm

12:00pm

Lunch
Thursday March 10, 2016 12:00pm - 1:00pm
Expo Hall - Grand Ballroom

12:30pm

How app-enabled switches increase innovation for telcos and DC operators

http://www.youtube.com/watch?v=aRnh_e3wpDc

Telco and data centre operators want software-defined capabilities to match their newly open hardware. This talk will demonstrate the state of the art for top-of-rack switches, as well as forthcoming telco-centric open networking such as DSLAMs, GPONs and software-defined LTE base stations, that build a software ecosystem to take advantage of OCP’s open hardware strategy.

Using open source mechanisms optimised for scale-out environments, the speakers will walk through a model central office or data centre, showing how diversity of NOS options and diversity of networking apps can fit together in a highly-automated cluster. Using OpenBMC and FBOSS from Facebook, MAAS, LXD containers, Ubuntu and a range of apps, the speakers will demonstrate dramatically more efficient software-defined approach to infrastructure.

We will use OCP switches to demonstrate running apps on the ToR switch that deploy and manage both server and physical switch infrastructure. Using OpenBMC, PXE, and ONIE, we are able to automate the deployment of scale-out bare metal infrastructure using 100% open source tools.  We will show how the separation of OS and apps enables greater competition for network control plane vendors as well as creating new opportunities for innovation in the SDN, NFV and network intelligence markets.


 


Speakers
avatar for Mark Shuttleworth

Mark Shuttleworth

Founder of Ubuntu, Canonical
Mark leads Canonical products and is founder of Ubuntu, the reference operating system for OpenStack clouds. Mark has charted the course that made Ubuntu the top OS for all public and private cloud platforms, and brings his passion for next-generation platforms and technology to this session.
LW

Luke Williams

Luke Williams is a systems network engineer. He has worked professionally in IT for over 20 years in different roles and has over 8 years of experience in networking architecture and engineering. He has multiple certifications from Cisco, Silver Peak, Juniper as well as Red Hat. He has a Bachelor's Degree in IT Systems Support with a Minor in Networking/Telecommunications from the University of Phoenix. He currently works for Canonical as a... Read More →


Thursday March 10, 2016 12:30pm - 1:00pm
Lower Level: LL21A/B

12:30pm

Touch-safe High Voltage DC Powering of Server Racks using Digital Electricity
Live Stream - http://www.youtube.com/watch?v=TLYmmCho_t0

Digital electricity technology sends electricity in brief packets that contain energy and data. The safe transfer of each packet is verified at the source and destination using a protocol called Packet Energy Transfer or PET. If an exposed conductor is touched, or the wire is short circuited or incorrectly installed, the transmitter will detect the error and stop sending energy within 0.003 seconds. Even when transferring thousands of Watts of power, digital electricity networks can be installed at much lower cost, without conduit or armored cabling, using only technician-grade labor in the same fashion as Ethernet cable. Moreover, the technology has embedded data capabilities for energy management, monitoring and control.

VoltServer has completed dozens of digital electricity installations that include hi-rises, stadiums, conference centers and hospitals. This will be the first presentation addressing data centers. Data will be presented demonstrating an OCP compatible power supply being powered with digital electricity. The only inputs to the supply will be a hybrid copper-fiber cable channeling both high bandwidth data for use by the servers and digital electricity.

Speakers

Thursday March 10, 2016 12:30pm - 1:00pm
Lower Level: LL21D

12:30pm

Use of Alternative Natural Fiber Filled Polypropylene (NFFPP) Plastic in Data Center Equipment Design to Improve Sustainability
Live Stream - http://www.youtube.com/watch?v=w5jStCVUg4s

This alternative plastic material displaces common server plastics such as PC+ABS, with a material that has a lower lifecycle environmental impact. Our efforts have resulted in several variations of a natural-fiber filled polypropylene (NFFPP) plastic that is currently being used in multiple products in our data centers across the world.
Facebook wants to present our experience to the community as a starting point to build upon so that this material and other alternative materials may be further developed to reduce the impact of our equipment on the earth. We will discuss the research that has gone into our lifecycle assessment (LCA) of the material. We will:
- explain our approach to sustainable design and incorporating LCA into our material selection decisions
- show how we are using the material in our data center equipment

- explain some of the special considerations required in designing with the material

- give an overview of the required approach to mold setup and processing

Speakers

Thursday March 10, 2016 12:30pm - 1:00pm
Lower Level: LL20D

12:30pm

Cloud optimized HDD
Live Stream - http://www.youtube.com/watch?v=bt2ZRCtGR4c

Disks form the central element of Cloud-based storage, whose demand far outpaces the considerable rate of innovation in disks. Exponential growth in demand, already in progress for 15+ years, implies that most future disks will be in data centers and thus part of a large collection of disks. We describe the “collection view” of disks and how it and the focus on tail latency, driven by live services, place new and different requirements on disks. Beyond defining key metrics for data-center disks, we explore a range of new physical design options and changes to firmware that could improve these metrics.

Speakers
LY

Lawrence Ying

Engineering Tech Lead, Google Inc
Lawrence is one of the main Uber Engineering Tech Leads of the Google Platforms Storage Team. | He currently leads the HDD Engineering Team and the Storage TCO Team, and overlooks several storage projects at Google.


Thursday March 10, 2016 12:30pm - 1:00pm
Lower Level: LL21E

12:30pm

Open rack enhancements for regulatory approvals and support for telco use cases
Live Stream - http://www.youtube.com/watch?v=XS3rNAjf3No

In order to deploy commercially OCP Open Rack, mandatory regulatory approvals needed (FCC, CE, KCCI..)

Speakers

Thursday March 10, 2016 12:30pm - 1:00pm
Lower Level: LL21F

1:00pm

Expo Hall Stage Talk: AMAX
Speakers
DR

Dr. Rene Meyer

Director of Product Development, AMAX


Thursday March 10, 2016 1:00pm - 1:15pm
Expo Hall - Grand Ballroom

1:00pm

OCP Inspired and OCP Accepted
Live Stream - http://www.youtube.com/watch?v=OgMKSm5v-bU

The OCP Inspired and Accepted Criteria explained.

Speakers
avatar for David Woolf

David Woolf

University of New Hampshire InterOperability Laboratory (UNH-IOL)
David Woolf currently leads Data Center initiatives at the University of New Hampshire InterOperability Laboratory (UNH-IOL). While at UNH-IOL, David has led development of dozens of industry-reviewed test programs and procedures as part of the team that has grown the UNH-IOL into a world-class center for interoperability and conformance testing. David has been an active participant in a number industry forums and committee’s addressing... Read More →


Thursday March 10, 2016 1:00pm - 1:30pm
Lower Level: LL21C

1:00pm

Linux Networking is Awesome
Live Stream - http://www.youtube.com/watch?v=N-8aAWqh004

The Linux kernel has seen some significant improvements in networking over the last several years that make it attractive for building networks with it. Improvements such as: scaling interfaces, vlan aware bridges, VRF, MPLS, and switchdev empower almost all Linux distributions to drive network switches at line rate. When combined with OCP projects like ONIE and APD and OCP hardware like the AS5712 or the MLX1410, one can see how powerful the base Linux kernel has become. We plan on demonstrating this power live.

Speakers
avatar for Scott Emery

Scott Emery

Member of the Technical Staff, Cumulus Networks
avatar for Shrijeet Mukherjee

Shrijeet Mukherjee

VP of Software Engineering, Cumulus Networks
Shrijeet is the VP of Software Engineering at Cumulus Networks. Most recently he was Director of Engineering with the team that delivered the highly successful VIC adaptor line in Cisco's UCS servers. His career has spanned a wide variety of technologies including Team Lead of high performance graphics at SGI, architect of high performance Network Interface Cards at Precision IO and adding virtualization and storage in Cisco with the UCS... Read More →


Thursday March 10, 2016 1:00pm - 1:30pm
Lower Level: LL21A/B

1:00pm

Open Rack Management Backplane Connector and Shared Cooling Zone
Live Stream - http://www.youtube.com/watch?v=RoLdI0hKH6Q

Intel and Quanta recently collaborated on an Open Rack demo to showcase Intel technology and provide a software development vehicle for Intel Rack Scale Architecture (RSA).  The demo rack was shown at OCP summit 2015, and the past two Intel Developer Forum (IDF) events.  Two of the unique features of the demo are the rack management backplane and rack-level cooling.  The existing Open Rack standard does not address rack-level management or cooling.  Now, Intel and Quanta are submitting design guides for the backplane connector and shared cooling module to Open Rack.  In this talk, Intel will share the details presented in the design guides, and lead a discussion on how such features could be standardized for Open Rack.

Speakers
EL

Ethan Long

Sr. Mechanical Engineer, Data Center Group, Intel
Intel Rack Scale Architecture for Open Rack


Thursday March 10, 2016 1:00pm - 1:30pm
Lower Level: LL21D

1:00pm

Open GPON Specification
Live Stream - http://www.youtube.com/watch?v=amfnlezHiSk

Speakers

Thursday March 10, 2016 1:00pm - 1:30pm
Lower Level: LL21F

1:00pm

Hacking the Conventional Data Center Power Infrastructure
Live Stream - http://www.youtube.com/watch?v=bWHwIaowdyQ

Open Compute has had a revolutionary impact on data center design, offering many simplicity and cost saving benefits. To become more mainstream, we believe critical questions need to be answered about the implications of OCP on the upstream power infrastructure.
- Can data centers still achieve Tier 3 redundancy?

-How do I support traditional and OCP loads in the same data center?

This presentation will address these and other questions, and propose a series of simplified architectures to support OCP. We will discuss redundancy, availability, and flexibility implications, as well as present a cost analysis. Schneider Electric embraces the spirit of OCP by openly sharing this analysis and making these simplified reference designs freely available.

Speakers

Thursday March 10, 2016 1:00pm - 2:00pm
Lower Level: LL21E

1:00pm

Server Management direction for OCP
Live Stream - http://www.youtube.com/watch?v=sg2ESDh99kk

Speakers
avatar for Mark Shaw

Mark Shaw

Director of Hardware Engineering, Microsoft
Standardized, scalable hardware for the Cloud! Open CloudServers!


Thursday March 10, 2016 1:00pm - 2:00pm
Lower Level: LL20D

1:30pm

OCP Certification - Next Steps
Live Stream - http://www.youtube.com/watch?v=iRsv6nISRf8

Discussion on the plans for OCP Certification.

Speakers

Thursday March 10, 2016 1:30pm - 2:00pm
Lower Level: LL21C

1:30pm

Facebook Wedge 100/6 Pack hardware Deep Dive & Hardware Testing
Live Stream - http://www.youtube.com/watch?v=AI0j_4CvrEw

Hardware design deep dive of following FB network projects
1: wedge100 32x100G TOR switch
2: SixPack 128x40G Modular Switch

Speakers
avatar for Hany Morsy

Hany Morsy

Network Engineer, Facebook
Hany Morsy is a network engineer at Facebook on the data center network engineering team. Currently his focus is on the large-scale testing infrastructure for Facebook’s data center switches and topologies.
avatar for Zhiping Yao

Zhiping Yao

Network hardware engineer, Facebook
Zhiping Yao is a network hardware engineer at Facebook, working on Facebook networking hardware such as the Wedge and 6-pack data center switches. Currently his focus is on Wedge 100. Prior to Facebook, Zhiping worked at Brocade on high-speed data center and campus switches.


Thursday March 10, 2016 1:30pm - 2:00pm
Lower Level: LL21A/B

1:30pm

Bloomberg LP B.O.A.R Project
Live Stream - http://www.youtube.com/watch?v=PQZsdjwvE3I

Creating an adaptable Rack that can be used with multiple cooling infrastructure designs and integrated with compute for on-demand modular deployment.

Speakers

Thursday March 10, 2016 1:30pm - 2:00pm
Lower Level: LL21D

1:30pm

XGS-PON 10Gbs Specification Proposal
Live Stream - http://www.youtube.com/watch?v=mYwvn9X_Jbs

Presentation of the XGS-PON Line Card Specification based on the Broadcom SoC chip sets. XGS-PON is the next generation and provides 10Gbps symmetric speed.

Speakers
avatar for Robert Mapes

Robert Mapes

PMTS, AT&T
Robert Mapes is Principle Member Technical Staff, AT&T Access Architecture and Design, where he designs network components and architecture in support of AT&T’s GigaPower FTTx based Wireline Access evolution, and he also helps develop Optical Access Networking/Next Generation PON Standards as a member of FSAN and a delegate to ITU-T SG15/Q2. After obtaining electrical engineering and M.B.A. degrees, his career has spanned over 25 years in... Read More →


Thursday March 10, 2016 1:30pm - 2:00pm
Lower Level: LL21F

2:00pm

Open Discussion of Inspired, Accepted and Certified
Live Stream - http://www.youtube.com/watch?v=Vha2dPxV89g

This session will be an open discussion about OCP Inspried, OCP Accepted and Certificaiton.

Speakers
avatar for David Woolf

David Woolf

University of New Hampshire InterOperability Laboratory (UNH-IOL)
David Woolf currently leads Data Center initiatives at the University of New Hampshire InterOperability Laboratory (UNH-IOL). While at UNH-IOL, David has led development of dozens of industry-reviewed test programs and procedures as part of the team that has grown the UNH-IOL into a world-class center for interoperability and conformance testing. David has been an active participant in a number industry forums and committee’s addressing... Read More →


Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL21C

2:00pm

OCP Solution Provider Program
Live Stream - http://www.youtube.com/watch?v=L6izDH3ahjw

If you are interested in becoming a Solution Provider or if you are already an OCP Solution Provider and you have questions about getting involved in the OCP communtiy please join Steve Helvie, OCP VP of Channel Development for this session.

Speakers

Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL21F

2:00pm

Building a self sustaining automated datacenter: The RuggedPOD project
Live Stream - http://www.youtube.com/watch?v=Bu9Y7cdXLDY

RuggedPOD is an outdoor microdatacenter designed to scale and be ready for automated maintenance. During this talk we will introduce past challenges addressed by the project, and upcoming one's where we are seeking for contributors and experiences engineers ready to change the DC world.


Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL21E

2:00pm

How does FB manage thousands of OCP switches?
Live Stream - http://www.youtube.com/watch?v=fMeECyHaxYw

Facebook has deployed thousands of OCP-accepted Wedge switches into its datacenters over the last year and that number continues to grow. The FBOSS software evolved rapidly throughout that period as we dealt with large-scale outages, different topologies, and other software challenges. At this point, we are able to update the software on thousands of our switches at least weekly, often without dropping a packet. Further, the Facebook 6-pack switch, which we have shared with the OCP community in advance of the OCP summit, is now in production as well. 6-pack is a 128x40 Gb switch designed to operate as the fabric/spine of our datacenter fabric, and it presented several major challenges in the control plane as well as in the management plane for the FBOSS and network management team. In this workshop, we will share our development and operational best practices with the OCP community.

Our FBOSS and network management software engineers will cover how we addressed the challenges of getting FBOSS and our attending operational software/processes to handle thousands of Wedges and how we expanded the same FBOSS and operational software to handle 6-pack. They will cover the network design philosophy of simplicity and scalability and how the hardware and software are crafted to support that.

Speakers
avatar for Jasmeet Bagga

Jasmeet Bagga

Software Engineer, Facebook
Jasmeet Bagga is a software engineer at Facebook, working primarily on network infrastructure projects.  Currently his focus is on FBOSS, Facebook's switching and routing software stack. Prior to Facebook, Jasmeet worked at a start-up building products for network diagnostics and monitoring.


Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL21A/B

2:00pm

OCP adoption in 19" EIA architecture
-19" adoptions today
-- Decathlete
-- Roadrunner
--QCT's vision on more 19" architecture
--Leopard
--Yosemite
-- Q&A

Speakers
avatar for Alan Chang

Alan Chang

Product Marketing Manager, QCT
Alan Chang has been the Product Marketing Manager at QCT (Quanta Cloud Technology) for the past 5 years, helping to define QCT’s own brand Server series (QuantaGrid/QuantaPlex) and Rack solutions (Open Rack, OCS Rack). Graduating from the University of California Irvine with a Master’s Degree in Computer Science and over 10 years of experience in the IT industry, he continues to contribute to the industry at QCT with an extended 5... Read More →


Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL20D

2:00pm

OpenPOWER collaboration and innovation with Open Compute
Live Stream - http://www.youtube.com/watch?v=JEk2zkaB4nc

The OpenPOWER community is teaming with Open Compute to bring industry leadership to system design and innovative price-performance leadership to scale out workloads. Learn about the cross industry progress and opportunity this is driving to address technical and business challenges.

Speakers
CR

Calista Redmond

OpenPOWER Foundation


Thursday March 10, 2016 2:00pm - 2:30pm
Lower Level: LL21D

2:30pm

Enabling Pervasive Network Security Using OCP Switch Hardware and ONL
In this talk, the speaker(s) will present a new architecture for enabling pervasive network security and monitoring capability in a large-scale data center or campus network. Key Architectural Requirements:
* Monitor E-W network traffic in addition to N-W traffic (variable granularity and physical+virtual workloads)
* Optimal utilization of security, monitoring, performance tracking tools
* Scale-out Design
* Economical at Scale In addition to sharing the architectural requirements, speaker(s) will describe an actual deployment of the solution in a large financial services data center. Salient features of the solution include:
* 30+ OCP switch based architecture in a multi-tier design * Open Network Linux (ONL) based switch software -- specialized for working in a controller based architecture
* OCP/ONL-based Switch Economics (compared to a traditional closed, proprietary solution)

Finally, the talk will discuss the applicability of this new, OCP centric design to other large-scale deployments in service provider as well as enterprise environments.

Speakers

Thursday March 10, 2016 2:30pm - 3:00pm
Lower Level: LL21A/B

2:30pm

HatTrick Storage and preview of HatTrick Compute
Designed to be versatile, reliable, and cost effective, HatTrick provides substantial capacity in an extremely efficient footprint. Containing three drive trays with each holding up to 15 3.5” HDDs. More details and potential use cases in the session.

Speakers

Thursday March 10, 2016 2:30pm - 3:00pm
Lower Level: LL21D

2:30pm

A new class device for secure, scalable, long term storage
Sony Optical Archive Inc introduces Everspan, a low cost, highly scalable storage device for the data center. Based on optical storage Everspan provides a new level of reliability and performance while optimizing TCO through lowest power consumption and the elimination of migration.

Speakers
HS

Horst Schellong

Solutions Architect, Sony Optical Archive Inc.


Thursday March 10, 2016 2:30pm - 3:00pm
Lower Level: LL21E