As businesses in a range of industries continue the push into the cloud, questions around how to divide on-premises high-performance computing and cloud resources are becoming more prevalent and complex. Bolstered by a partnership with Amazon Web Services Inc., Intel is using its legacy experience to help customers strategize their cloud transitions.

“Early in the days of cloud computing, there were people who said the the cloud was kind of the opposite of HPC and, therefore, they could never go together. But we think of cloud as a delivery vehicle, a way to get access to computer storage networking, and HPC is what you’re doing,” said Bill Magro (pictured), fellow and chief technologist of high-performance computing at Intel Corp.

Magro spoke with John Furrier (@furrier), host of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, and guest host Justin Warren (@jpwarren), chief analyst at PivotNine Pty Ltd., during the AWS re:Invent conference in Las Vegas, Nevada. They discussed Intel’s work in guiding customers through HPC and cloud integrations and how AWS is supporting this work through its innovative platform. (* Disclosure below.)

Sharing the burden between HPC and cloud

By thinking of HPC as a range of workloads as opposed to an infrastructure system, Intel is able to work with customers to determine which workloads are fit for cloud and which should remain on-prem. Through this holistic integration, Magro and his team position the cloud as a way to deliver HPC capabilities to enterprises.

“If you think of HPC in terms of the characteristics of the workload, it’s something that’s really demanding computationally. … The elastic capability of the cloud augments the supercomputer that you might be using to run your hardest problems,” Magro said.

Where HPC was designed to provide supportive functioning for large-scale computing, cloud computing dovetails with the system by more efficiently processing multiple small variations simultaneously. “We have a lot of … Fortune 500 companies augment their on-premise with cloud as a way to push those workloads … [and] free up on-prem resources, which are much more tailored and expensive, to get more value out of them,” Magro said.

Supplementing an HPC system with cloud ensures resources and human capital are utilized to their full capacity, enabling faster engineering at a lower cost, Magro added.

The greatest challenge for Intel’s customers is determining which workloads are best suited for the cloud and which should remain on-prem. To help them make their decision, Magro and his team take into consideration the privacy and sensitivity of data and technical fit of the workloads.

“The bigger a workload goes … that starts to stress the network and stress the system. That’s where these tailored systems come in. You have to look at where things fall on the spectrum,” Magro said.

Looking ahead, Magro hopes to help more small and medium-sized businesses upgrade their processes by incorporating HPC. With its new C5 Instance release, AWS is making HPC even easier for businesses of all sizes, Magro added.

“We’re seeing improvements in HPC apps … almost up to 5x improvement in going from C4 to C5 Instance on a per-note basis. … [With] every generation of technology what fits in the cloud is growing, and C5 is another important step in that direction,” Magro concluded.

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of AWS re:Invent. (* Disclosure: Intel sponsored this segment of theCUBE. Neither Intel nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE