Cycle Computing which specializes in technical and high-performance cloud computing, and Western Digital's HGST unit ran the largest Fortune 500 production workload and went from zero to 50,000 cores in 23 minutes.
The cloud computing run, executed over the weekend and code-named Gojira, utilized various regions on Amazon Web Services (AWS) and maxed out at 70,980 cores. In 60 minutes, the companies built a 729 TeraFLOPS cluster, or the equivalent of the No. 63 supercomputer on the June Top500 list. The workload ran over 8 hours.
Jason Stowe, CEO of Cycle Computing, said the HGST workload is an example of how enterprises are increasingly using technical computing and high-performance clusters to run analytics workloads and simulations. Cycle Computing historically has had life sciences and insurance customers, but has been adding manufacturers such as HGST and aerospace companies.
Cycle Computing creates containers for cluster computing so customers can make workloads portable. That technology enables supercomputing on cloud infrastructure. Stowe explained that technical computing resources used to sit under research departments, but now fall under the CIO and line of business executives. "Now that technical computing has been centralized under IT, the workloads are run where it makes the most sense," said Stowe.
Here's a look at the cloud run last weekend by the numbers: