Natural Language Processing at Clemson University – 1.1 Million vCPUs & EC2 Spot Instances
September 28, 2017
A group of researchers from Clemson University achieved a remarkable milestone while studying topic modeling, an important component of machine learning associated with natural language processing, breaking the record for creating the largest high-performance cluster by using more than 1,100,000 vCPUs on Amazon EC2 Spot Instances running in a single AWS region, accessed via CloudyCluster.
Cloud vs. Datacenter Costs for High Performance Computing (HPC): A Real World Example
June 19, 2017
In this collaborative guest blog post, Boyd Wilson and Amy Cannon together with Sara Jeanes discuss costs and benefits of running HPC jobs in the cloud vs running them on premesis.
5 Things to Consider When Deploying High Performance Computing (HPC) to the Cloud
June 14, 2017
In this collaborative guest blog post, Boyd Wilson and Amy Cannon together with Sara Jeanes continue the HPC in the Cloud BoF session discussion at the Internet2 Global Summit.
CloudyCluster 1.3 Released
The new CloudyCluster 1.3.1 release includes Multi-Factor Authentication, new software including many Machine Learning Codes, support for EFS based Home Directories and initial support for CCQHub.
CloudyCluster 1.2.1 Released
January 6, 2017
The new CloudyCluster 1.2.1 release includes some bug fixes, new CCQ functionality, improved performance with Dojo and Chrome, R-Studio software and support for the new 20GB AWS Network type.
EMC crying two SAN breakup tears
November 18, 2016
Dell's new 2 TIERS project uses both CloudyCluster and OrangeFS: "Dell EMC is working on fixing the increasing split between primary storage data on flash and capacity data storage on object arrays by logically combining them underneath a 2 TIERS software abstraction layer. "
Automating Cloud HPC Resource Management with CloudyCluster
July 26, 2016
In this guest blog post, Boyd Wilson discusses how CloudyCluster is designed to utilize and automate cloud resources for HPC consumption.
CloudyCluster 1.1 on RHEL Released with Enhanced Features
February 2, 2016
Omnibond today released CloudyCluster 1.1 with expanded functionality including application support for WRF and CESM, Globus integration, and CCQ certificate based sign-on.
Anderson, SC—Omnibond today announced that CloudyCluster 1.1 on RedHat Enterprise Linux is available in Amazon Web Services Marketplace (AWS Marketplace). CloudyCluster 1.1 brings several new features, with application support for Community Earth System Model (CESM) and the Weather Research and Forecasting Model (WRF), Globus integration, support for Torque 6 as well as automatic use of placement groups and enhanced networking for faster computing.
CloudyCluster and Globus demonstrate Cloudy HPC with Globus Data Management Capabilities
November 18, 2015
CloudyCluster works to meet growing cloud HPC needs by using Globus file transfer and sharing capabilities.
Austin, TX—Supercomputing 2015—Today Omnibond and Globus announce the integration of Globus with CloudyCluster, adding functionality to enable spinning up a fully-functional Globus endpoint on demand for streamlined research data management.
The convenience and speed of HPC on Amazon Web Services (AWS) using CloudyCluster is now combined with the “fire-and-forget” high-performance file transfer capabilities of the Globus service. Omnibond and Globus are working together to enable CloudyCluster to automatically create and configure Globus endpoints on demand. Users can spin up HPC clusters using the simple CloudyCluster interface and run resource-intensive computations in the AWS cloud, with a simple tool for uploading and sharing data. The integration makes CloudyCluster instances part of the growing Globus ecosystem, enabling data transfer to and from thousands of Globus endpoints at research computing centers and national supercomputing facilities.
Read the full article.
CloudyCluster on Red Hat Enterprise Linux will be available in the AWS Marketplace
October 6, 2015
Self-service HPC with CloudyCluster, built on the power and dependability of Red Hat Enterprise Linux and provided through the simplicity of the AWS Marketplace. CloudyCluster presents a familiar HPC environment for researchers with the elastic capabilities of AWS Cloud.
Las Vegas, NV – re:Invent —Today Omnibond announced the release of CloudyCluster running on Red Hat Enterprise Linux in the AWS Marketplace, establishing a new level of HPC research and discovery available to everyone.
Read the full article.
CloudyCluster Offers Mobile Cloud-Based HPC
July 15, 2015
CloudyCluster is Omnibond’s innovative solution for creating and managing HPC and Big Data Clusters in a customer's Amazon Web Services (AWS) account. It provides a simple, web-based interface for mobile, tablet and desktop devices to create and manage scalable HPC and Big Data Clusters in AWS. This brings on-demand HPC to a new level of flexibility and portability.
Read the full article.