Moving HPC Workloads to the Cloud

Posted by Gretchen Weaver on Mon, Dec 04, 2017 @ 10:15 AM

Scientists and engineers use High Performance Computing (HPC) in order to solve complex problems. The requirements for success frequently include big compute, high-throughput, and fast networking. For some time, the cloud simply hasn't been an option for these workloads as they were too big to move, the latency was too high, or it was simply too costly. But, now all of that is changing.

The cloud providers are looking to bring HPC workloads into their infrastructures, as was obvious at this year's SC17 in Denver. Both AWS and Google were talking scale and speed to attendees, promoting abilities to scale parallel tasks beyond what is realistic in traditional local infrastructure. But getting the workloads to the cloud services is another story. To learn how to move file-based applications to the cloud non-disruptively, attendees approached Avere.

In the below video, insideHPC editor Rich Brueckner spoke to Bernie Behn, principal engineer at Avere Systems about how to get high-performance workloads from network-attached storage (NAS) environments onto the cloud.

Read More

Topics: HPC, Enterprise Storage, Hybrid Cloud NAS

Spotlight: HPC Data Archiving with Avere & HGST

Posted by Christine Tompkins on Fri, Jun 09, 2017 @ 11:50 AM

Media asset archiving is an essential part of the media & entertainment industry, especially as the volume of data grows. Archives become larger and larger, which means they become more and more difficult to build and manage infrastructure for. At the same time, it is becoming more important to have fast access to that data. For rendering and transcoding applications, performance is an essential component to being competitive in this very fast-moving industry.

Read More

Topics: HPC, Media & Entertainment, Private Object Storage

What is Hybrid Cloud Orchestration?

Posted by Gretchen Weaver on Thu, Apr 27, 2017 @ 04:28 PM

Technology moves quickly and with every new product, process, or development comes new terminology. One of these is "cloud orchestration." While immediate visions of a composer in front of white fluffy puffs in the sky, one immediately knows that isn't quite it. 

Cloud orchestration is often confused with automation. While similar, they aren't the same. Alex Henthorn-Iwane wrote on this topic in Network Computing and did it quite well, so we won't rehash that here in long-form. But basically, while automation focuses on tasks, orchestration takes more into account, extending its reach into the control and coordination of many automated tasks.

Read More

Topics: HPC, Data Center Management, Cloud Compute

Using a Data Access Layer in HPC

Posted by Scott Jeschonek on Fri, Feb 03, 2017 @ 10:55 AM

High-performance computing in the cloud is becoming more and more common, as companies realize its potential to extend their HPC environments without additional significant infrastructure costs. HPC clusters bring hundreds or sometimes even thousands of cores online quickly and efficiently — something perfect for the massive compute farms managed by cloud service providers (CSPs) like Google Cloud Platform and Amazon Web Services. Very large clusters can be created on-demand. You aren’t restricted to one cluster either; you can create any number of clusters on demand, empowering different teams without causing resource contention. 

Photo Credit: iStock Photo

Read More

Topics: HPC, Data Center Management, Technology Community

Overcoming NAS Bottlenecks in HPC

Posted by Gretchen Weaver on Thu, Nov 10, 2016 @ 09:10 AM

As the ability of accessing large computing environments eases with the use of cloud, more and more companies are facing storage challenges in high performance computing (HPC) workloads. As innovation brings larger projects to IT infrastructure, managers are faced with performance, capacity, and budget issues. So how can storage bottlenecks be prevented? 

Read More

Topics: NAS Optimization, HPC, Technology Community

Four Benefits of a Hybrid Cloud Infrastructure for Financial Services

Posted by Gretchen Weaver on Thu, Sep 15, 2016 @ 02:35 PM

Market forces and increased volatility are challenging financial service organizations to make changes that allow for operational efficiencies. How companies go about doing that varies widely, but the once shunned idea of using cloud service providers is becoming more and more attractive. Cloud resources can change the possibilities with nearly unlimited compute resources minutes away from deployment.

Read More

Topics: HPC, Data Center Management, Financial Analysis

IT Infrastucture for Independent Research Organizations

Posted by Gretchen Weaver on Fri, Sep 02, 2016 @ 03:35 PM

Independent Research Institutes play a key role in discovering everything from new vaccines to understanding the natural world better to providing both protection and new resources to better living. Mostly non-profit research organizations, these centers of science are supported primarily through grants. This reliance on grants comes with unique pressures and requires strategic management of resources to deliver on missions within funded timeframes.

These institutions are also reliant on federal policy which directly impacts funding and research initiatives. The Association of Independent Research Institutes (AIRI) works to inform its members of new developments in Congress and across the federal government of issues, policy development, and risk related to biomedical and behavioral research and health care. Beyond policy, the association provides opportunities for learning through its conferences and webinars.

Read More

Topics: HPC, Data Center Management, Life Sciences

One-Click Cloud ComputE Scalability

Posted by Gretchen Weaver on Fri, Aug 26, 2016 @ 09:10 AM

Launching a tiered file system into the cloud is now only a click away. This week, Avere and Cycle Computing jointly announced technology integration that enables high-performance computing (HPC) in popular cloud computing environments. The Avere vFXT Edge filer software can now be launched directly from Cycle Computing’s CycleCloud product, instantly providing users with managed scalable compute nodes.

Read More

Topics: HPC

FinServ IT: Increase Alpha Throughput & Scalability

Posted by Gretchen Weaver on Mon, Aug 15, 2016 @ 03:05 PM

Hedge fund and investment managers seek better returns by analyzing many external datasets impacting the market. These analytics are driving decisions; however, most often the key resources on which the analysis depends are provided by the IT department — computing, networking, and data storage access.

Read More

Topics: HPC, Cloud Compute, Financial Analysis

Eliminating Latency to Colocated Infrastructure

Posted by Gretchen Weaver on Fri, Aug 05, 2016 @ 03:48 PM

If you are in charge of IT, moves to new office locations mean more than packing up some pens and a stapler, gathering your photo frames and favorite poster from the wall and hauling out. Moving servers and storage isn’t easy and allowing for their unique requirements in the new office space can cause more than a few grumbles from office mates and space planners. And even after you find a place to accommodate what you have, do you have room to allow for growth? 

Read More

Topics: HPC, Data Center Management, Rendering & Transcoding