HP Labs: Thinking Differently about the Future of IT
I recently gave the keynote address at the Nth Symposium conference and explained why I have one of the coolest jobs on Earth. As Director of HP Labs, I am helping HP rethink what computing means. At its core, computing architecture has not changed in more than 60 years. We still have the CPU, main memory, and some sort of IO—typically storage and networking. But we’re now faced with a changing IT environment and computing must evolve with it.
These days, enterprises commonly handle petabytes—or more—of data and increasing amounts of unstructured data. Tomorrow it will be exabytes. The sheer amount of computing horsepower required to handle all that data is enormous, taking a financial, logistical and environmental toll on organizations.
If you looked at the existing public cloud as a country, it would be the fifth largest consumer of electricity in the world. For context, reducing public cloud electricity consumption in half would be enough to power the United Kingdom. This current path is unsustainable, as we are barely scratching the surface of the deluge of data that’s projected to come at us in the coming years. This reality requires transformative thinking that addresses energy consumption and other IT challenges.
At HP, we are working to develop the next generation of computing architecture and have identified specific areas ripe for change. We are finding ways to think differently, and to create innovative, end-to-end solutions from mobile devices, to data centers to storage and networking. Let’s take a look at some examples:
- Energy-efficient processing: HP’s Moonshot servers, developed in HP Labs and released earlier this year, are dramatically changing the cost and power curves. We’ve moved a significant portion of HP.com to Project Moonshot servers and can now run one of the busiest websites on the planet with the equivalent of 12, 60-watt light bulbs. But that’s just the start. By moving from general purpose processors to task-specific, system-on-chip ecosystems we can simultaneously achieve quantum leaps in compute performance and power-efficiency.
- Network connectivity: We are working on new photonic interconnects that will eventually supplant the traditional copper cables currently in use. We expect to greatly reduce the energy-per-bit needed to process data by moving from copper-based systems to photonics-enabled systems.
- Universal memory: We are reaching the point of diminishing returns when it comes to traditional storage hierarchy and need to explore new options to be able to manipulate the vast data sets of the future. The traditional memory hierarchy – working memory and mass storage – must be replaced with a single, universal memory. We believe that HP’s memristor technology is the best candidate to deliver the necessary, speed, endurance, cost and scale.
This powerful new, energy-efficient computing architecture will give us a place to put data, ways to move and process data, allow us to easily access data and then extract value from the data. This will empower you, our customers—not just data scientists—to extract meaning from massive data sets almost instantaneously.
But that’s just one piece of the puzzle. As I said earlier, HP is uniquely positioned to provide end-to-end technology solutions. An improved computing architecture, in conjunction with advanced data analytics from our HAVEn platform, will allow anyone to sit down at a computer, ask a question and receive an answer in real time.
HP has a long history of innovation and has placed a renewed focus on research and development under Meg Whitman’s guidance. These are just some examples of how HP is leading the development of new technologies that will change the way we interact with the world. I’m excited for the future.