Beyond Super

Discovery Enters the Exascale Era

Contact Us

Start with the right partner.

We've been helping visionaries like you solve the most complex computing problems for over four decades.

The Next Inflection Point

The road to exascale computing started as a speed milestone. But along the way it changed. Today it signals a major inflection point for computing ― and a new era of discovery and innovation.


Driven by explosive data growth, converging workloads, and the imperative for digital transformation, organizations are asking completely new questions. And they need new capabilities to answer them. Exascale computing completely rethinks how technology comes together to answer your biggest questions today ― and your even bigger ones tomorrow.


New Era Begins with an End

Exascale computing* is almost unfathomably fast. The quest to achieve these speeds started because the industry saw the era of Moore’s Law was nearing its end. The law says the number of transistors in a dense integrated circuit doubles about every two years. And it held for decades ― until it didn’t.

We can no longer apply a brute force approach or add hundreds of thousands of virtual servers on the cloud to add the capability today’s workloads require. In effect, the end of Moore’s Law elevated the need for a new, more intelligent and purposeful approach that bring the best of HPC and the cloud together to deliver a step function increase in capability.

*exascale computing means a computing system that can perform at least one exaflops ― or one quintillion (a billion billion) calculations per second. For perspective, it would take 40,000 years for one quintillion gallons of water to spill over Niagara Falls. The Milky Way galaxy is 1 quintillion kilometers wide.

What Makes Exascale an Era

Exascale is more than a speed milestone or a system size. Exascale is new workloads brought on by new questions intersecting with new compute capabilities to create a major technological shift.


To understand this shift, you have to understand some macro trends in research and enterprise. First, uncontrolled data growth is driving organizations of all sizes to data-intensive computing. Second, digital transformation has become a business imperative. And third, the number of HPC and AI workloads is exploding.


In response to these trends, AI, analytics, IoT, simulations, and modeling workloads are all converging into one business-critical workflow – a workflow that must operate at extreme scale and in real-time.


These trends and realities are forcing a complete rethinking of compute, networking, software, and storage architectures. The resulting capabilities will take research and enterprise computing beyond super and into the exascale era.


Read the blog post to understand why exascale computing is a technology inflection point and not just the next high five in the race.


EXASCALE TECHNOLOGY

Technologically, the exascale era is characterized by three aspects: flexible compute architectures; system software stacks that bring together HPC and the cloud; and interconnects that unite performance, intelligence, and interoperability.

The underlying capabilities of our Shasta supercomputing architecture and Slingshot interconnect will remove barriers to new workflow creation – and accelerate exascale transformation.

Shasta Supercomputer

Cray’s new supercomputer, code-named Shasta, is an entirely new design and will underpin the next era of supercomputing. The system is characterized by exascale performance capability, new datacentric workloads, and an explosion of processor and accelerator architectures. Shasta incorporates next-generation Cray system software to enable modularity and extensibility, supports unparalleled flexibility in processing choice, and scales seamlessly.

Learn more about Shasta

Slingshot Interconnect

The Cray-designed Slingshot™ interconnect is the network backbone for the diverse simulation, modeling, AI, and analytics workloads today’s scientific and technological questions require. It offers a host of important new features such as adaptive routing, congestion control, and Ethernet compatibility.

Learn more about Slingshot Technology


The Only Question We Can’t Answer Is What Comes Next

Some people will never be comfortable anywhere other than the leading edge. And to those, we’re pleased to introduce the nation’s next-generation supercomputers. Built for the Argonne and Oak Ridge National Laboratories and the National Energy Research Scientific Computing Center, these systems will enable innovation and discovery for years to come.

By using this site, you agree to Cray's terms of service and privacy policy.