Now Reading
Azure: Improving High-Performance Computing Environment (HPC)
[vc_row thb_full_width=”true” thb_row_padding=”true” thb_column_padding=”true” css=”.vc_custom_1608290870297{background-color: #ffffff !important;}”][vc_column][vc_row_inner][vc_column_inner][vc_empty_space height=”20px”][thb_postcarousel style=”style3″ navigation=”true” infinite=”” source=”size:6|post_type:post”][vc_empty_space height=”20px”][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row]

Azure: Improving High-Performance Computing Environment (HPC)

Oakwood Team recently had the opportunity to collaborate on an unusual project that involved a leader in elite biotechnology and genetics serving farmers around the world. Their data is vital in helping livestock owners to breed better quality animals and increase efficiency in the production process. This project involved collaborating with the client to find a better way to deliver timely, relevant data to customers through a high performance computing environment.

Genetics is a complex subject that requires a lot of mathematical calculations. These calculations had to be reliable and accurate in order to meet the demands of their customers. This data cannot be produced manually in a reasonable time. Client relies on large computer clusters for computations.

The genetic testing can put a lot on clients’ computer resources. The client had high-performance computing (HPC), which was set up to manage their genetic testing needs. This environment could be improved to help farmers worldwide breed better animals.

The client wanted to improve their computing environment and migrate some of their data into Azure. They needed someone who was experienced in cloud migrations and could meet their complex data needs.

Oakwood was able, through Microsoft specialists, to resolve the problems they faced throughout the project. Oakwood worked closely with Microsoft to modify Lustre and Slurm templates. Microsoft even contributed their own resources to writing custom scripts in this regard.

The Microsoft specialists were more than happy and able to assist with this project. The specialists were thrilled to use their tools in an actual environment. Oakwood team members would break tools like Slurm and then work with Microsoft to fix it. Microsoft was a major supporter of this project.

Oakwoods client has seen remarkable performance improvements and is still working closely with Oakwood to improve the functionality and performance of this complex environment. The new system is more durable and practical than their existing on-premises systems. The client can create and run entire HPC clusters in order to run genetic tests. Their team can achieve two-gigabytes of throughput using Lustre as backend data storage.

Clients now have to do less day-today management of their systems than before.

Azure has allowed the client to free up significant computing resources. The client now has greater backup and redundancy than ever before. This customer is better equipped to meet the needs their customers through their new HPC environment.

Oakwood’s ability to deliver significant improvements is evident to the client. Oakwood intends to continue working on business intelligence as well as data- and reporting functions. Oakwood and the client plan to apply the lessons learned from this project to future high-performance computing clusters or data center deployments.

Since 1981, the Oakwood Team has helped organizations of all sizes across all industries to solve their most challenging technology-related problems. Our longevity has allowed for us to improve and sharpen our delivery approaches to help ensure better business outcomes.

Oakwood Systems Group is a Microsoft Partner and holds 8 Gold Competencies as well as 6 Silver Competencies. Oakwood Systems Group has over 40 years of experience and several Microsoft Partner of the Year awards. They deliver complex technology solutions on time and within budget.

Share this article on social media and email

View Comments (0)

Leave a Reply

Your email address will not be published.