LOS ALAMITOS, Calif., 15 March, 2011 – The global data explosion driven by cloud computing, the growth of mobile systems, faster computing speeds, and the popularity of digital content is creating ripples of change that computing researchers are doing their best to prepare for.
In a groundbreaking article in the January 2011 Outlook issue of Computer magazine, Partha Ranganathan, a principal research scientist at Hewlett Packard Labs and principal investigator for the exascale datacenter project, describes the computing and data systems he foresees existing in the exascale era, in which systems will be able to handle a million trillion operations per second.
"The size of data is going to be very staggering—it's going to be really large data," warns Ranganathan in a video interview with Computing Now Editor in Chief Dejan Milojicic. "It's going to be much faster than anything we're used to."
The article, "From Microprocessors to Nanostores: Rethinking Data-Centric Systems," is one of six on Data Storage Evolution that are featured for a limited time on Computing Now [http://www.computer.org/computingnow], the website where IEEE Computer Society themed publication content is aggregated. The articles can be viewed at http://www.computer.org/portal/web/computingnow/archive/march2011.
Milojicic's wide-ranging video discussion with Ranganathan and Alistair Veitch, director of the Storage and Information Management Platforms Lab, is available at http://www.computer.org/portal/web/computingnow/archive/march2011. Besides being the founding editor of Computing Now, Milojicic is a senior research manager at HP Labs.
Ranganathan was a primary developer of the publicly distributed Rice Simulator for ILP Multiprocessors (RSIM) and is a recipient of the Lodieska Stockbridge Vaughan fellowship and an alumni award from the Indian Institute of Technology, Madras. In 2007, he was named one of the world's top young innovators by Massachusetts Institute of Technology magazine Technology Review.
Ranganathan also elaborates on his ideas on exascale-era systems design in an interview on Computing Now conducted by the late Scott Hamilton, the longtime senior acquisitions editor for Computer magazine.
Ranganathan notes that the first computer to achieve terascale computing (1 trillion operations per second) was demonstrated in the late 1990s. A decade later, the first petascale computer demonstrated a thousand-times-better performance. The first exascale computer is slated to appear before 2020.
In addition to continued advances in performance, computing is experiencing tremendous improvements in power, sustainability, manageability, reliability, and scalability. Power
management, in particular, is now a first-class design consideration.
Recently, system designs have gone beyond optimizing operational energy consumption to examining the total life-cycle energy consumption of systems for improved environmental sustainability. To read more about the expected changes in computing, visit http://www.computer.org/computingnow.