Keynote 1: Green Clouds and Black Swans: Low-Power Hyperscale Computing
Tuesday, November 27th, 11:00 - 11:30am
 Partha Ranganathan
Corporate Fellow
HP Labs
Parthasarathy (Partha) Ranganathan is a corporate fellow at Hewlett Packard Labs where he currently leads a research program on future data-centric data centers. His prior work includes key research contributions around energy-aware user interfaces, heterogeneous multi-core processors, enterprise power management and benchmarking, and disaggregated low-power server architectures. His work has had broad impact on both academia and industry, including several commercial products such as the recent Project Moonshot announcement from HP. He holds more than 35 patents, and has published extensively, including several award-winning papers. He has been recognized as one of the world's top young innovators by MIT Technology Review, and is an IEEE Fellow. He also teaches regularly (including, most recently, at Stanford) and is a contributor to several popular computer architecture textbooks. Dr. Ranganathan received his B.Tech degree from the Indian Institute of Technology, Madras and his M.S. and Ph.D. from Rice University.
Abstract: Green Clouds and Black Swans: Low-Power Hyperscale Computing
The amount of digital information we generate is increasing at an incredible rate, and new applications are essential to utilize, manage, and analyze it. Solutions must be tremendously scalable to deal with the rapid data explosion. Current technology would require far more servers, storage, network connections, facilities, and power than we can possibly afford. Instead, we need new solutions that allow for scale-out to dramatic levels within current constraints. Emerging technologies, including low-power system-on-chip processors, non-volatile memories, and optical communications for large-scale cloud computing, offer additional opportunities for new system designs.
About HP:
HP creates new possibilities for technology to have a meaningful impact on people, businesses, governments and society. The world’s largest technology company, HP brings together a portfolio that spans printing, personal computing, software, services and IT infrastructure at the convergence of the cloud and connectivity, creating seamless, secure, context-aware experiences for a connected world. More information about HP (NYSE: HPQ) is available at www.hp.com. |
|
|
Keynote 2: How Flash Storage Is Revolutionizing Enterprise IT
Tuesday, November 27th, 11:30am - Noon
 Gary Smerdon
Sr. VP & GM
LSI
Gary Smerdon is senior vice president and general manager of the Accelerated Solutions Division (ASD) of LSI Corporation. In this role, he oversees all marketing, engineering and manufacturing of the company’s server-based application acceleration solutions combining PCIe flash technology with intelligent caching and management software. ASD products accelerate application performance, reduce total cost of ownership, and deliver robust, interoperability to the enterprise server and storage markets.
Previously, Gary led LSI’s Corporate Strategy Office, which is responsible for developing and driving the company’s overall corporate vision and strategy. He was also vice president of Business Development & Strategy for LSI’s Semiconductor Solutions Group.
Prior to joining LSI in 2007, Gary was chief marketing officer at Tarari, which was acquired by LSI. He also was president and CEO of Greenfield Networks, where he was responsible for raising $35M in funding and leading the company from a pre-product, pre-customer start-up to an early-stage revenue company. Prior to that, Gary was vice president of Marketing at Marvell, responsible for the communications product group as well as all corporate marketing activities. He joined Marvell through the acquisition of Galileo Technology, where he was vice president of marketing and co-general manager for the Ethernet Switching Business Unit. He also spent time at AMD where he led the worldwide marketing activities for the company’s Network Products Division.
Gary currently or previously served as a Board Member or Observer for Greenfield Networks (acquired by Cisco), 3Leaf Systems (Huawei), SandForce (LSI) and Teranetics (PLX).
Abstract: How Flash Storage is Revolutionizing Enterprise IT
The amount of data is currently growing 30 to 50% annually, driven by such factors as pervasive mobile computing, social networks, increased use of video and imaging, and the emergence of the Internet of Things. And there is no end in sight. At the same time, IT budgets are growing only 5 to 7% annually. The result is that information is growing faster than the investments in IT infrastructure required to store, move, analyze, and manage it, leaving a widening “data deluge gap.”
In response, companies are increasingly turning to cloud and highly virtualized datacenters to handle unrelenting data growth more effectively and more economically. Traditional storage architectures are being stressed, and storage is often the bottleneck to better application performance and faster response time.
Deploying server-side flash technologies such as PCIe flash accelerator cards in datacenters and cloud environments can provide the lower latency and higher bandwidth required to bridge the data deluge gap without disrupting existing IT infrastructures. When combined with intelligent flash caching software, these solutions hold the key to busting through I/O bottlenecks to accelerate database transactions, reduce total cost of ownership, and help enterprises extract full value from data. About LSI:
LSI Corporation (NYSE: LSI) designs semiconductors and software that accelerate storage and networking in datacenters, mobile networks, and client computing. Our technology is the intelligence critical to enhanced application performance, and is applied in solutions created in collaboration with our partners. More information is available at www.lsi.com. Connect with LSI on Facebook, Twitter, and YouTube. |
|
|
Keynote 3: Cloud Scale Server Futures
Tuesday, November 27th, 1:30 - 2:00pm
 Gregg McKnight
Microsoft
Gregg McKnight is the General Manager of Data Center Advanced Development at Microsoft, where he leads the efforts driving next generation end-to-end solutions for cloud infrastructure. His team’s charter is driving optimization across the data center IT ecosystem for future online and cloud services. With Microsoft since December 2010, he was previously General Manager of the eXtreme Computing Group within Microsoft Research. He led the engineering team working to develop new technologies in next-generation hardware and software. Before joining Microsoft, Gregg was Vice-President for IBM System X and BladeCenter server development. He led the mechanical design, power, and thermal engineering teams as well as the security and energy efficiency organizations. He was Distinguished Engineer and CTO for the IBM System X server group before becoming Vice-President. He holds over 20 patents and has 28 years experience in X86 server development. He has an MSEE from Pennsylvania State University.
Abstract: Cloud Scale Server Futures
Tomorrow's cloud data centers will house servers that integrate more functions into simpler, cheaper, and smaller silicon packages. Their Systems on a Chip (SoC) building blocks will combine DRAM and CPU, integrate network switching, utilize solid state storage, and eliminate today's costly and energy-wasting power distribution systems. This so-called “siliconization” of components will cause significant design improvements. Other major cost-reducing advances will include fuel cells generating power on-site, the elimination of expensive top-of-rack switches, and the simplification of mechanical systems. Cloud computing and energy efficiency concerns will lead to completely different requirements and infrastructures. Server designers must change their entire way of thinking to take full advantage of these new technologies and new approaches
About Microsoft:
Founded in 1975, Microsoft (Nasdaq “MSFT”) is the worldwide leader in software, services and solutions that help people and businesses realize their full potential. For more information, see www.microsoft.com. |
|
|
Keynote 4: How Do We Handle all the Data!
Tuesday, November 27th, 2:00 - 2:30pm
 Andy Walls
Distinguished Engineer and Technical Lead
Systems and Technology Division
IBM
Andy Walls is the Chief Architect for IBM's Flash Systems and Technology. Andy has responsibility for developing leading edge Flash solutions across all of IBM's platforms. He also works closely with IBM Software Group to ensure that these solutions provide differentiation for our applications. In addition, Andy is the chief engineer for IBM's DS8000 hardware platform.
Andy has been with IBM throughout his 31 year career and was appointed as a Distinguished Engineer with IBM in 2006. He has 27 years experience in all areas of storage systems and has filed over 55 patents. He is a regular speaker at industry events on storage and Flash memory and regularly presents to clients, business partners and suppliers on IBM storage systems trends and requirements.
Abstract: How Do We Handle all the Data!
Data creation is exponentially growing, processor cores are increasing and new developments in Flash Storage are allowing some relief in the IO bottlenecks. And yet, obstacles persist and some technology scaling limits seem to be arising. So, what is the outlook for servers and IO design in handling all the data? How will shared and direct storage evolve and does clustered storage have the answers. In addition, DRAM and Flash scaling limits will require new innovation. Will Storage Class Memories ever come to the rescue? This industry has been amazingly innovative in the face of obstacles, so what are some possible outcomes this time? |
|
|
Special Keynote: The Next Generation of Datacenter Networks
Tuesday, November 27th, 5:00 - 5:30pm
 Andy Bechtolsheim
Chief Development Officer
Arista Networks
Andy Bechtolsheim is responsible for the overall product development and technical direction of Arista Networks. Previously Andy was a Founder and Chief System Architect at Sun Microsystems, where most recently he was responsible for industry standard server architecture. Andy was also a Founder and President of Granite Systems, a Gigabit Ethernet startup acquired by Cisco Systems in 1996. From 1996 until 2003 Andy served as VP/GM of the Gigabit Systems Business Unit at Cisco that developed the very successful Catalyst 4500 family of switches. Andy was also a Founder and President of Kealia, a next generation server company acquired by Sun in 2004. Andy received an M.S. in Computer Engineering from Carnegie Mellon University in 1976 and was a Ph.D. Student at Stanford University from 1977 until 1982.
Abstract: The Next Generation of Datacenter Networks
Coming soon. About Arista Networks:
Arista Networks was founded to deliver software defined cloud networking solutions for large data center and high-performance computing environments. Arista delivers a portfolio of 1/10/40 and 100 GbE capable products that redefine network architectures, bring extensibility to networking, and dramatically change the price/performance of data center networks. |
|
|
Keynote 5: How Convergence Affects Data Center Fabrics
Wednesday, November 28th, 11:00-11:30am
 Geng Lin
CTO Networking Busines Unit
Dell
Geng Lin is the CTO of Networking Business at Dell, where he has overall responsibility for technology strategy, system architecture, product innovation, and partnership and acquisition of key technologies. Previously, he was the CTO of the IBM Alliance at Cisco Systems, where he was responsible for technology direction, strategy, and solution development of the joint Cisco-IBM solution portfolio worldwide. In his 20 years in the networking industry, he has also served as Vice President of Software Engineering at Netopia (acquired by Motorola), Director of Engineering at Cisco Systems, and Director of Product Strategy at Nortel Networks.
Dr. Lin speaks frequently at conferences and industry tradeshows. He is the contributing author of 4 books and over 40 publications including journal and conference papers, and keynote speeches. He served on the editorial board of two research journals in network and systems software, and the advisory board of two books on cloud computing. He received his B.Sc. and M.Sc. degrees from Peking University and his Ph.D. degree from the University of British Columbia, all in computer science.
Abstract: How Convergence Affects Data Center Fabrics
The Converged Infrastructure (CI) platform has emerged as the new building block for designing large scale data centers. CI imposes new architectural requirements on the data center fabric, both within a platform and between building blocks. However, the networking architectures used in today’s data centers are still mostly derivatives of legacy enterprise-oriented ones. The combination of new application requirements, large data sets, flash memory as a new storage tier, and alternative CPU architectures has revolutionized data centers. With CI redefining the basic architectural elements, it is time to reconsider data center fabrics as well.
About Dell:
Dell listens to customers and delivers innovative technology and services that give them the power to do more. For more information, visit DELL.
Dell PowerEdge 12th generation blade, rack, and tower servers deliver the latest Intel Xeon processor E5-2600 product family performance, extreme memory density, choice of embedded NIC technologies, a wide variety of hot-swappable HDD and SSD choices, PCIe Gen3-enabled expansion slots, and a host of other I/O enhancement options for server virtualization, HPC, VDI, and other compute-intensive applications. |
|
|
Keynote 6: Building Servers for the Cloud
Wednesday, November 28th, 11:30am - Noon
 Kushagra Vaid
General Manager
Server Hardware Engineering
Microsoft
Kushagra Vaid is the General Manager for Hardware Engineering in Microsoft’s Global Foundation Services (GFS) group. He is responsible for driving research and engineering for Microsoft’s server hardware infrastructure. He was previously Director of Server Engineering and led a team of architects and engineers to develop server strategy and hardware platforms for the online services division. With Microsoft since 2007, he started there as Principal Architect. He has previous experience at Intel as a Principal Architect focused on server microprocessors and platforms. He has published papers at research conferences and has been a featured speaker at industry workshops. He holds 25 patents in computer architecture and datacenter design. He has an MS in Computer Science from the State University of New York at Binghamton and a BE in Computer Engineering from the University of Mumbai (India).
Abstract: Building Servers for the Cloud
Cloud computing has expanded rapidly with ever more applications being hosted in public and private clouds. The applications are extremely wide-ranging, including Internet search, Web hosting, email, media streaming, gaming, and social networking. Designing infrastructure for such diverse and varying workloads is challenging with reliability and systems management at scale having to be considered as well as the usual performance, power, and cost. Meanwhile, servers have evolved from simple rack-mounted computers with built-in networking capabilities to complex aggregations of infrastructure resources deployed at datacenter scale. This has fundamentally changed how compute, storage, and networking facilities are designed, deployed, provisioned, and operated. Designing server infrastructure for cloud scale adds new challenges, as evidenced by approaches put forward by cloud service providers. And, of course, technology shifts remain a constant background with major advances occurring in processors, networks, and storage. Designers must find a path that evolves and adapts core infrastructure to meet the scale challenges posed by the massive growth in cloud architectures.
About Microsoft:
Founded in 1975, Microsoft (Nasdaq “MSFT”) is the worldwide leader in software, services and solutions that help people and businesses realize their full potential. For more information, see www.microsoft.com. |
|
|
Keynote 7: Creating High-Performance Cloud Storage
Wednesday, November 28th, Noon - 12:30pm
 Hong Cai
CTO
ZTE USA
Hong Cai is CTO of Cloud Computing for ZTE USA. In this position, he is responsible for helping the R&D team define the roadmap for future cloud computing products and solutions, as well as bridging between the team and North American activities. He is also involved in cloud standards activities and business partnerships. Before joining ZTE USA, he worked on corporate technology evaluation at IBM. He was with IBM for 15 years as a technical leader in both IBM Research and the IBM Software Group. He focused on cloud computing (including cloud resource management, PaaS solutions, commerce-as-a-service, and SaaS multi-tenancy), services computing, and pervasive computing. He has filed many patents, published 50 papers, and co
Abstract: Building Servers for the Cloud
Telecom operators are facing major challenges from slowed revenue growth and fierce competition from OTT (Over The Top) service providers. One way they can meet the challenges is to pursue opportunities in cloud computing, particularly cloud storage. Cloud storage must meet the needs of both consumers and service providers. Consumers want low cost, high availability, and simple access. Service providers want efficient management and operation, support for a wide variety of storage technologies, dynamic and transparent scale out, simple maintenance, and little or no downtime. A complete cloud storage solution involves servers, storage hardware, storage software, and a highly scalable storage platform, all integrated into a single package. Workloads such as archiving, file sharing, and video have varied requirements including latency, IOPS, and cost. Storage utilization can be optimized to improve performance in all cases.
About ZTE USA:
ZTE is a publicly-listed global provider of telecommunications equipment and network solutions with a comprehensive product range covering every telecommunications sector, including wireless, access and bearer, VAS, terminals, and professional services. The company delivers innovative, custom-made products and services to over 500 operators in more than 140 countries, helping them meet the changing needs of their customers while growing revenue. In 2011, ZTE’s revenue increased by 29% to $13.7 billion. ZTE commits 10% of its annual revenue to research and development and has leadership roles in several international bodies focused on telecommunications industry standards..ZTE is committed to corporate social responsibility and is a member of the UN Global Compact. For more information, please visit www.zte.com.cn. |
