- Set up time significantly reduces from weeks or months to minutes.
- Increased agility and reliability to more efficiently manage platform
- Improved configuration to increase the scale, to enable creation hundreds
of execute nodes at once, without any errors.
- Increased cost savings by eliminating cluster ownership/maintenance costs
of building out a 10,000 core cluster infrastructure.
Cycle Computing's Recipe for Success
Cycle Computing has delivered its proven, secure and flexible high performance
computing (HPC) and data software solution since 2005. The company’s
technology helps clients maximize existing infrastructure and speed
computations on desktops and servers on-demand in the cloud. With its
CycleServer HPC management software and CycleCloud fully supported and secured
HPC clusters, Cycle clients experience faster time-to-market, decreased
operating costs, and unprecedented service and support. Cycle uses Amazon EC2
resources to power its unique high-performance cloud computing platform,
providing highly scalable, reliable and secure infrastructure for Cycle's
"Amazon's nearly limitless scale means no job is too big, while our
CycleServer and CycleCloud solutions offer seamless management and robust
security," said Jason Stowe, CEO Cycle Computing. "However, it would be nearly
impossible for us to manage infrastructure as the scale our customers require
Cycle deployed Chef to automate the provisioning and configuration of
thousands of Amazon EC2 servers, ensuring maximum infrastructure consistency
and reducing deployment times from months to minutes. With Chef, the
Cycle team can deploy infrastructure as code, easily repeating configurations
across hundreds or thousands of Amazon EC2 instances in minutes and delivering
compute power to customers on-demand.
"Chef enables us to deploy infrastructure at unprecedented scale with maximum
consistency and minimal management," Stowe continued. "We use a few simple
lines of code to configure thousands of servers simultaneously, making us
highly responsive to customer needs and giving us the ability to pursue
When Schrodinger, a worldwide leader in computational chemistry research,
needed to virtually screen 21 million molecule conformations against one
possible cancer target, it turned to Cycle because the project was too intense
for its available physical infrastructure. To meet Schrodinger's needs, Cycle
Computing used Chef to provision and configure a 50,000 core utility
supercomputer in Amazon EC2 in less than two hours.
Using Chef to automate server configuration, Cycle scaled out Schrodinger's
cloud supercomputer across seven different geographic regions, maintaining
full availability throughout. Then, Cycle deployed its CycleServer software on
top of the supercomputer to intelligently provision compute tasks to each
region based on real-time bandwidth measurements, ensuring no region was over
or under utilized.
"The Schrodinger project was our largest to date by far, but is nowhere close
to the limits we'll be able to achieve with Amazon and Chef," Stowe
added. "By automating what would take months to do by hand, we've eliminated
management time and human resources as barriers to scale, which opens up
nearly infinite growth potential."