University/lab startup enables small businesses access to big computers
A new University of Chicago startup is delivering supercomputing-as-a-service to small- and medium-sized businesses and helping these firms more readily compete with industry behemoths.
High-performance computing drives innovation and efficiency in the fast-growing industries that are rapidly transforming our lives--smart cities, Internet of Things, self-driving cars, advanced materials, environmental sustainability and personalized medicine.
Using technology developed at Argonne National Laboratory and the University of Chicago, Parallel Works has democratized this powerful computing practice, which is typically limited to the upper echelons of industry due to cost, complexity and resource constraints.
Parallel Works customers can run advanced simulations on large-scale computing resources without requiring specialized skills in parallel programming and computer science.
Klimaat Consulting and Innovation, an engineering consulting firm focused on climate responsive design, uses the Parallel Works platform for detailed urban micro-climate simulations. This helps their clients, including some of the world’s leading architectural firms, make quick, informed urban-design and ecology decisions and create healthier city habitats.
“Our belief is that big computing will be the next wave after big data,” said Parallel Works CEO Mike Wilde. “Most engineering and scientific investigations require a tremendous
amount of computing power. We’re enabling those studies for companies that previously could not afford it, and making it much more productive for those large companies that are already deeply dependent on large-scale computation.”
Wilde is a software architect at Argonne and senior fellow at the University of Chicago’s Computation Institute. The company has received funding from the University of Chicago Innovation Fund and the U.S. Department of Energy; it is housed at the University’s Polsky Center for Entrepreneurship and Innovation.
This funding has enabled Parallel Works to onboard early customers. The company is currently raising a seed round to accelerate sales and continue platform development.
The Parallel Works platform offers scalable computing-as-a-service, adjusting computing power based on demand. A large energy simulation that once took 20 days can now finish in less than an hour, by using 5,000 processing units working in parallel.
Parallel Works is built on the Swift parallel scripting system, which enables scientists and researchers to more easily deploy large and complex simulation studies on supercomputers.
“Supercomputing ensures that a product’s design is the best it can be and that the optimal answer is found fast,” Wilde said. “We’re increasing the value of a manufacturer's most valuable asset, its engineers, by eliminating the often-frustrating challenges of coding and managing computing hardware.”
