World's largest single-memory computer is unveiled
Hewlett Packard Enterprise (HPE) has revealed "The Machine" – a new computing architecture with 160 terabytes of memory.
Hewlett Packard Enterprise (HPE) has introduced the world's largest single-memory computer. Known simply as "The Machine", it is the largest R&D program in the history of the company, and is aimed at delivering a new paradigm called Memory-Driven Computing – an architecture custom-built for the big data era.
"The secrets to the next great scientific breakthrough, industry-changing innovation or life-altering technology hide in plain sight behind the mountains of data we create every day," explained Meg Whitman, CEO of HPE. "To realise this promise, we can't rely on the technologies of the past. We need a computer built for the big data era."
The prototype unveiled this week features a staggering 160 terabytes (TB) of memory, enough to simultaneously work with the data held in every book in the Library of Congress five times over – or approximately 160 million books. It has never been possible to hold and manipulate whole data sets of this size within a single-memory system, and this is just a glimpse of the immense potential of Memory-Driven Computing.
Based on the current prototype, HPE expects the architecture could easily scale to an exabyte-scale single-memory system and, beyond that, to a nearly-limitless pool of memory – 4,096 yottabytes. For context, that is 250,000 times the entire digital universe today.
With such a vast amount of memory, it will be possible to simultaneously work with every digital health record of every person on earth; every piece of data from Facebook; every trip of Google's autonomous vehicles and every data set from space exploration, all at the same time – getting to answers and uncovering new opportunities at unprecedented speeds.
"We believe Memory-Driven Computing is the solution to move the technology industry forward in a way that can enable advancements across all aspects of society," said Mark Potter, CTO at HPE and director, Hewlett Packard Labs. "The architecture we have unveiled can be applied to every computing category from intelligent edge devices to supercomputers."
Memory-Driven Computing puts memory, not the processor, at the centre of the computing architecture. By eliminating the inefficiencies of how memory, storage and processors interact in traditional systems today, Memory-Driven Computing reduces the time needed to process complex problems from days to hours, hours to minutes, minutes to seconds, to deliver real-time intelligence.
The current prototype Machine has its memory spread across 40 physical nodes, each interconnected using a high-performance fabric protocol, with an optimised Linux-based operating system (OS) running on ThunderX2. Photonics/optical communication links, including the new X1 photonics module, are online and operational. Software programming tools are designed to take full advantage of the abundant persistent memory.
"We think that this is a game-changer," said Kirk Bresniker, Chief Architect at HPE. "This will be the overarching arc for the next 10, 20, 30 years."