High Performance Computing Services

Exploit Cloud Elasticity, Scalability for HPC-Driven Business Results

Flux7 helps businesses take advantage of the cost efficiency, productivity and compute power of the cloud to quickly and reliably run complex High Performance Computing workloads. Whether in Life Sciences, Oil and Gas, Manufacturing, Semiconductor or another industry, cloud HPC speeds time to market and, in turn, lets you hit your targets without stress and unneeded long-term capital investment. 

 

Many organizations have seen their on-premises compute clusters age poorly while cloud providers continuously add faster compute, new services, and features that make execution in the cloud faster and easier. Driving innovation on-demand, HPC cloud solutions provide enterprises with nearly limitless capacity with a scalable, elastic infrastructure that can address even the most compute-intensive models.  

 

With major cloud providers constantly adding new compute, storage and networking options, companies have greater flexibility than ever for their workloads.

The cloud computing experts at Flux7 help companies take advantage of cloud-based HPC to:

 

Speed Time to Results

Available on-demand, Cloud-based HPC eliminates the need for scientists and researchers to wait their turn in line for internal resources to be free. And, with a vast and growing number of features and functionality, research teams can run a wide variety of workloads in the cloud, accelerating their time to completion.


Increase ROI

Speed time to market by minimizing lengthy procurement cycles.  Avoid costly set-up and maintenance with cloud-based HPC. Optimize your investments with cloud providers that regularly add new instance types and functionality, such as the ability to test Machine Learning workloads.  Pay only for what you use and save even more with spare compute power like Spot instances.  Take advantage of Spot Market pricing for interruptible workloads and maximize your dollar per compute cycle.


Grow Productivity

Shorten the time to create a winning design or product by increasing researcher’s productivity. Cloud-based HPC avoids scientist downtime as they wait for available resources, while providing scalability and elasticity that accelerates time to workload completion. And, by being able to match infrastructure configurations to the application, scientists aren’t constrained by the settings of on-site HPC systems.


Expand Insights

Unleash the potential of AI and ML to optimize your compute. Analyze terabytes of data with big data technologies that can unearth trends and insights about how to target your jobs that would be impossible with simple human analysis. Avoid in-house ML and AI tooling challenges and the need to keep up with the latest GPUs and/or specialized processors with the constant availability of market-leading technology in the cloud.


HPCwire Press Release: Flux7 Launches HPC Cloud Consulting Practice

AUSTIN, Texas, Oct. 3, 2019

Flux7, an IT services provider helping organizations innovate and achieve agility at the speed of the market, today announced a new consulting practice dedicated to helping organizations take advantage of cloud-based High Performance Computing (HPC) to accelerate innovation. Derek Magill, solution architect at Flux7 who brings more than 20 years’ experience in HPC, leads the newly formed practice.

 

Flux7 Labs Spot Virtual Meetup

At Flux7 Labs, as part of our consulting, we found ourselves solving the same problems in cost and performance optimization for our clients. We have productized some of these learnings into our product VyScale. A major feature of VyScale is its management of spot instances. We have been working closely with users of spot instances and Amazon to come up with strategies to use spot instances. As part of that, today, we hosted a Hangout on spot instances. The idea was to get people out from working in silos and offering a platform to share knowledge and ideas. 

 

 

Digital Transformation Boosts Manufacturing Agility, Competitiveness

Few industries face the level of global competition that manufacturing does. To compete and realize the promise of Industry 4.0, manufacturers are increasingly embracing digital transformation. Evolving the business — from the manufacturing floor to the sales office — requires a holistic effort that requires a smart IT roadmap strategy and effective execution. In today’s blog, we’re taking a look at the digital transformation journey of several manufacturers and how it has benefited their productivity, efficiency and ultimately their strategic market positLearnion. 

Create Business Solutions Faster with Cloud, DevOps, and High Performance Computing

Secure, compliant HPC framework

Personal Peptides sequences, analyzes and compares DNA against large data sets, requiring massive amounts of computing resources in order to return information within a reasonable timeframe. Yet, managing patient DNA patterns requires meeting HIPAA requirements and protecting client information along the supply chain. To help Personal Peptides meet these dual challenges while maintaining competitive advantage through efficient use of computing resources, Flux7 helped the firm blueprint a cloud-based HPC solution that allowed the company to remain agile, with a highly secure infrastructure that provides an additional level of data protection along the document chain.

HPC Cloud Migrations

Intelligently prioritize the order in which HPC workloads should be migrated to the cloud. Seeking to innovate across the organization — from R&D to IT — Flux7 helped this pharmaceutical leader migrate its systems to take advantage of software automation and HPC resources for real-time analytics of its clinical data. A highly-available, secure environment for advanced R&D modeling and analysis, the new HPC environment includes a complete migration of the firm’s diverse data sets and Cloudera Hadoop-based analytics systems to AWS.

Support Research Platforms

Flux7 used the Flux7 Enterprise DevOps Framework as a foundation to create a high performance computing environment for this clinical research firm who explores genomic data from real studies. Flux7 created a single Galaxy cluster for the company, using SLURM for scheduling as it has the ability to distribute workloads and collect results. The cluster allows all the firm’s scientists to use the same cluster that auto scales for jobs, rather than CPU usage or other compute metrics, ensuring scalability that directly addresses their research needs.

Replication for High Availability

For a leading auto manufacturer, Flux7 created cluster replication to provide high availability. Using SSM in HPC clusters ensures cluster replication and system continuity should a storage node fail in the HPC cluster. The firm also benefits from automation of its Elastic File System (EFS) cluster that stores data outputs. And, Flux7 created an on demand, self-service catalog that allows developers to automatically create and destroy dedicated HPC clusters, all without depending on the infrastructure team.

Parallel Compute Across Availability Zones

A leader in autonomous tractor innovation, the world’s largest manufacturer of agricultural equipment needed to perform HPC calculations related to fluid dynamics and element analysis during the equipment design process. Parallel compute needed to spread over hundreds-thousands of cores to support traditional scientific computing workloads. HPC jobs are sent to a number of AWS regions, and bursting is performed to meet dynamic demand.

Containerized Scientific Workflows

A biotechnology firm approached the cloud computing experts at Flux7 to help it enable its genomic analysis with HPC in the cloud. Specifically, it sought support for its Nextflow HPC cluster. A framework for building computation pipelines using Docker containers, NextFlow is where the execution of genomics jobs happen. For this firm, Flux7 built CloudFormation templates for using the NextFlow pipeline engine, automating Nextflow provisioning and use, which in turn automatically pulls and writes to S3 for model data storage.

Save with Spare Compute Resources

Flux7’s AWS Spot strategy solution provides more than 60 percent in reduced costs without the need for human intervention, installations or access to sensitive data. The solution that won an Honorable Mention at AWS re:Invent seamlessly combines the cost savings of spot instances with the reliability of reserved and on-demand instances by using smart placement, instance selection, and AI-based prediction. For media company Yactraq Online, Flux7 optimized price and performance. In processing more than 60-million seconds of video, Flux7 was able to lower the on-demand price by 80%. Yactraq was able to use this spot strategy to continue offering high performance to its customers while being able to lower its prices.

Common Toolset

Slurm, Torque, LSF, LSF AWS cluster, Spot Instances, AWS Snowball, AWS ParallelCluster, AWS Batch

Case Study: Personal Peptides Speeds Genomic Analytics with Optimized AWS Infrastructure

“Flux7 solved a problem in the field of genomics in the process
of building our infrastructure.  As the data is increasingly
becoming available, one of the real business advantages
is solving the problem of how to manage analytics at scale.
When each patient brings such a large amount of data, it is not
long before there is a serious scalability challenge.”

– Dr. Jahan Khalili
Founder of Personal Peptides

Chat with our Technical Specialists

Discover how we help you learn skills for business agility