Exascale
Exascale. The next big thing. A computing system capable of a quintillion calculations per second. And Altair is at the forefront, exploring the next level of high-performance computing(HPC). With the advent of the exascale era, every day we’re pioneering tools that scale, running on next-generation systems and supporting increasingly complex HPC requirements in areas like machine learning, deep learning, and multiphysics.
Research and Innovation - Faster Than Ever
The power of exascale will scale up discovery and speed innovation. Exascale computing will enable new insight in areas including weather prediction, climate modeling, drug discovery, precision medicine, aeronautics, and space science.
HPC - Only as Powerful as the Software That Runs It
Powerful computing hardware requires powerful software tools, and with exascale it’s more critical than ever to manage workloads efficiently.Altair® PBS Professional®orchestrates it all with automated job scheduling, management, monitoring, and reporting.
Argonne’s Aurora Supercomputer Making History
The "Aurora" exascale computer, with workload management by PBS Professional, is slated to go online at Argonne National Laboratory in 2022. It will be the fastest system in the U.S., capable of performing a quintillion calculations per second.
Altair RapidMiner delivers breadth and depth across the analytics lifecycle.
The Next Big Thing
We’ve partnered with Argonne National Laboratory in support of exploring exascale with the HPE-designed Aurora system. And that’s just the start. With the advent of the exascale era, we’re pioneering tools that scale, getting them ready to run on next-generation systems and support increasingly complex HPC requirements in areas like machine learning, deep learning, and multiphysics. Supercomputers are critical to the future and we’re helping shape the U.S. exascale ecosystem as a member of the Department of Energy’s Exascale Computing Project (ECP) Industry Council. We are honored to collaborate, more realistically simulating the processes in precision medicine, additive manufacturing, biofuels, and much more.
The Road to Exascale
Getting to exascale demands speed and scale to handle millions of operations. It requires extreme resilience and continuous fault recovery. Running an exascale-class system takes significant power, so power management is critical. So is a good user experience. We’ve considered all this and more on our road to exascale and beyond, which includes:
- Altair® Accelerator™ Plus for 6-10x greater throughput
- PMIx for fast launch of huge MPI jobs
- Active-active PBS Professional server
- Green Provisioning™
- Hybrid cloud bursting, ARM64, GPUs, and SSDs
- Dual-licensed PBS Professional with extensive plugin framework
- Altair® Control™ for monitoring, analytics, and simulation
- Security focus
Going Big
Altair® PBS Professional® runs big — 50,000 nodes in one cluster, 10,000,000 jobs in a queue, and 1,000 concurrent active users. It runs fast — 10,000,000 jobs per hour end-to-end throughput and 10-second end-to-end run for a single 4,000+ node job. Some of the biggest computing systems in the world use PBS Professional for efficient workload management, including those leading the race to exascale. Exascale will have widespread implications in industries from manufacturing to personalized medicine, allowing users to stay at the forefront of innovation.
