Cog ex Machina: Cognitive Computing
Computing workloads are rapidly evolving towards non-computational algorithms and petabytes of unstructured and structured data. Today’s challenge is in designing computational systems that are both performance and energy efficient. Our approach, Cognitive Computing, creates a massively-parallel, cognitive architecture that is easy to program, supports adaptive learning, and scales to millions of cores on thousands of multi-core digital processors distributed over a network – and represents a leap beyond previous attempts at building intelligent systems. Cognitive computing, inspired by how the human brain works, has the potential to revolutionize visually-based information analytics, leading to exciting applications in a wide range of domains, including surveillance, location-based services, healthcare safety, fraud detection, sentiment analysis or big data processing and visualization.
CeNSE – Central Nervous System for the Earth
A Central Nervous System for the Earth is positioned to provide a new level of environmental awareness through a network of millions of inexpensive sensors, data storage, and analysis tools to improve the safety, sustainability, and security of people and businesses. Our sensor effort is focused on creating a Moore's Law for sensing. We are applying our nanotechnology expertise to push the boundaries of cost, size, power consumption and integration to create more capable sensor nodes, combining technologies such as chemical/biological and inertial sensing. Our networking effort lays the conceptual groundwork for the communication fabric of a CeNSE-scale sensor network, with an emphasis on the wireless component. Areas of focus include the tools of network information theory, allowing for new architectures, protocols, and codes that go well beyond those deployed in state-of-the art networks today. Finally, our analytics effort applies real-time event visibility to move systems from historical or reactive analysis to proactive, real-time optimization.
Next Generation Datacenters
The explosion of data that enterprises, consumers and sensors continuously generate, store, search, and mine requires new thinking about the way in which the datacenters processing this information have to be designed, managed and programmed. At the same time, emerging technologies around nonvolatile memories and photonics enable new designs. Our end goal is to build a scalable, power- and cost-efficient, automated and programmable datacenter for the "data-centric" society. To achieve this, we have structured a research plan that ties together novel computing platforms, scalable systems and management software, and programming platforms.
Next Generation Scalable Storage
The goal of this research is to design the storage platform for cloud computing. Our approach is to exploit a fundamental tradeoff between the consistency, availability, and network-partition-tolerance of distributed systems. Our system offers various consistency models including some that provide high availability by allowing data updates even when there are network failures. Attributes of our system include scalability, low cost, reliability, and self-repair. The system can cheaply and efficiently scale storage capacity and performance, and a single instance can scale across multiple geographies.
Nonvolatile Memory and Storage
The memristive memory program’s goal is to create low-power, high-speed, ultra-high density, low-cost and nonvolatile universal memory and storage solutions that eventually replace Flash, hard disks, DRAM, and SRAM. Our research path is to continuously invent and improve new memristive materials, device structures, hybrid CMOS/memristor circuits, storage and logic architectures, and information theoretic strategies tailored to specific applications. We develop significant intellectual property and work with external manufacturing partners for development and commercialization of essential components.
Photonics research is focused on replacing the copper-based electrical connections used in today’s IT systems with optical laser communication links. Using light to transmit information can exponentially increase performance, reduce cost, and improve power efficiency over the conventional copper in use today. This project has ambitious goals to develop and commercialize photonic interconnects: develop photonic interconnects enabled by extremely efficient and inexpensive optical sources, modulators, and detectors; create new classes of optical technologies that rely on advanced physics of new materials; and enable new systems, computer processors, and switch architectures through large-scale integrated photonics.
Enterprises are creating and processing information at staggering volumes and accelerating rates. In the next ten years, digital data alone is expected to grow 44 times. By 2020, there will be 4 billion people online creating 50 trillion gigabytes of data. Storage capacity requirements in business are growing 20-40% percent each year. So if an enterprise has 100 terabytes of storage capacity today, then it will require over 370 terabytes within five years.
These mind-boggling quantities of data demand ever-smarter computing architectures, networks, and storage solutions. And that’s because today’s infrastructure is built on old protocols, strained by enterprise requirements to support bandwidth-hungry applications, mobility, security, and manageability. In a world where IT demands and the resources to meet them don’t add up, an intelligent infrastructure can create the backbone of a sustainable society.
An Intelligent Infrastructure is about IT working together in a way that makes sense: a system of smarter, more secure enterprise computing devices, networks, and storage built on scalable architectures. And it’s about creating technology that blends into the way we work and live our lives as individuals and in business.
At HP Labs, we’re developing radical new approaches to how data is collected, processed, and stored to harness the power of information. HP is embedding technology into the world around us to tap into the power of information and make faster, better decisions.
Intelligent Infrastructure Big Bets