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, 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.

Flux7 High Performance Computing Services

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.


Reduce TCO

Avoid lengthy procurement cycles, and costly set-up and maintenance with cloud-based HPC. Eliminate the need for resources to operate and update on-premises systems as cloud providers regularly add new features 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.


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.


Discover how Flux7 helps you learn skills for business agility

Discover how we help you learn skills for business agility

Get a Quote with Flux7 Today

Schedule a live demo with our technical experts

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 assess which HPC workloads can be migrated to the cloud successfully. 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 an automated 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

Get started with Flux7 today!