OEM Solutions

HPE and Stephen Hawking’s COSMOS to Investigate the Early Universe

Humanity has always studied its surroundings to gain understanding. Data could hold the key to understanding the secrets of the early universe. The problem? There is 14 billion years of information to analyze. To further understand the origin and edifice of the universe through analytics and visualization, Stephen Hawking upgrades his shared-memory supercomputer (named COSMOS) at the University of Cambridge. A hundred years ago, Albert Einstein searched for answers in thought experiments. However, theories tested through confrontation with real data—and today's technology - invite us to probe the mysteries of our universe as never before possible. The United Kingdom’s COSMOS advanced computing facility, founded by renowned physicist Stephen Hawking and colleagues, and under the direction of Professor Paul Shellard, leverages Superdome Flex and in-memory computing to transform large data volumes into insights, accelerate innovation, and further understanding the universe. For breakthrough computing power to run real-time analyses and complex simulations, COSMOS relies on another discovery pioneer: Hewlett Packard Enterprise (HPE).


New HPE Superdome Flex enables research team to analyze massive data sets to understand the origins of space and time

HPE and the Faculty of Mathematics at the University of Cambridge announced a collaboration to accelerate discoveries in the mathematical sciences at Discover 2017 Madrid in November.  It includes partnering with Stephen Hawking’s Centre for Theoretical Cosmology (COSMOS) to understand the origins and structure of the universe. Leveraging the HPE Superdome Flex in-memory computing platform, the COSMOS group searches for clues hiding in massive data sets—spanning 14 billion years of information that could unlock the secrets of the early universe and black holes.

 The recent discovery of gravitational waves offers profound insights about black holes and the whole universe. With exciting new data like this, COSMOS needs flexible and powerful computer systems to keep ahead to test mind gobbling theories and innovate. “In-memory computing ingests all of this data and acts on it immediately, trying out new ideas, new algorithms. It accelerates time to solution and equips us with a powerful tool to probe the big questions about the origin of our universe,” said Paul Shellard, Professor of Cosmology, University of Cambridge, and Coordinator of COSMOS.

The new effort, which leverages HPE’s Superdome Flex servers, is a step forward for the COSMOS project, which has existed in one form or another since 1997. Back then, SGI and Intel were both major players, though HPE seems to be tackling the upgrades and improvements on its own so far.


CHALLENGE- Data-driven discovery requires massive computing power

Satellites orbiting the earth. Ground-based instruments pick up traces of ancient radiation. Humans devise ingenious ways to collect clues about the origin of the universe. Transforming those clues into insight takes enormous computational muscle both to analyze sensor data and to simulate cosmic events such as the merger of black holes.


SOLUTION- In-memory computing to drive more insights, faster

The tenth and latest COSMOS high-performance system goes where no computer has gone before. Featuring the new HPE Superdome Flex in-memory platform, the COSMOS group can turn data into actionable insight at unparalleled scale and in real-time.


RESULTS- New research horizons

The cosmology team leverages the COSMOS system to achieve two principal objectives: develop a seamless history of the Big Bang and to understand the gravitational waves of black holes. The team forms theories about the origins of the universe, creates simulations to extremely high precision and makes predictions, and then looks for those projections within a flood of new data. With a sizeable in-memory computing system, the team can analyze the data through visualization and in real-time while the simulation is running.

“High-performance computing has become the third pillar of research, and we look forward to new developments across the mathematical sciences in areas as diverse as ocean modeling, medical imaging and the physics of soft matter,” said Professor Nigel Peake, Head of the Cambridge Department of Applied Mathematics and Theoretical Physics.

At Discover 2017 Madrid, Professor Paul Shellard and Mike Woodacre, HPE Distinguished Technologist, discussed how Stephen Hawking and his colleagues are solving the complexities of our universe through the analytics of great data sizes with in-memory computing. How enterprises of any size can capitalize on the same technology to identify customer behavior in real-time, optimize new service delivery, increase sales and outpace competitors.


HPE Superdome Flex

The HPE Superdome Flex is the world’s most scalable and modular in-memory computing platform. With designed leveraging principles of Memory-Driven Computing, HPE Superdome Flex can scale from 4 to 32 sockets and 768GB to 48TB of shared memory in a single system, delivering unmatched compute power for the most demanding applications. Stephen Hawking chose HPE’s new mission-critical platform to provide in-memory high-performance computing, tackling highly complex, data-intensive problems holistically at an unprecedented scale and with single-system simplicity. HPE Superdome Flex leverages the principles of Memory-Driven Computing, the architecture central to HPE’s vision for the future of computing, featuring a pool of memory accessed by compute resources over a high-speed data interconnect. HPE’s Superdome Flex is unquestionably a beast; the machine can scale from 4-32 sockets and supports 768GB-48TB of memory. The new Superdome Flex system is not limited to COSMOS, but also available to numerous other research departments. For more information, please visit the Superdome Flex page here.

To discover the clues hiding in these large data sets, Stephen Hawking’s COSMOS Research Group is relying on HPE Superdome Flex's ability to transform the flood of data into insights. Watch this video to know more!


Featured articles:


Learn more about HPE’s OEM Program:


0 Kudos
About the Author