Advanced Clustering Technologies has been building custom, turn-key high performance computing solutions including HPC clusters for more than 15 years. Follow this blog to get more information on High Performance Computing.
The BeeGFS Rising Bee Award, given to Advanced Clustering Technologies in recognition of our being the fastest growing partner of the year
Advanced Clustering Technologies today received the BeeGFS Rising Bee Award as fastest growing partner for 2018 during a ceremony at the BeeGFS booth at Supercomputing 2018 in Dallas.
BeeGFS (formerly FhGFS) is the leading high-performance parallel cluster file system, delivered by ThinkParQ and developed in cooperation with Fraunhofer HPC.
Advanced Clustering partnered with ThinkParQ in May to integrate the BeeGFS parallel file system into the turn-key HPC solutions being built by the Kansas City-based company, which has been building HPC systems since its founding in 2001.
BeeGFS is available open source and powers the storage of hundreds of scientific and industry customer-sites worldwide. It is ideal for demanding, high-performance, high-throughput workloads for modeling and simulation, product engineering, life sciences, deep learning, predictive analytics, media and financial services.
“With the integration of BeeGFS, we are essentially offering our customers a solution that is 100% scalable and redundant,” said Advanced Clustering President Kyle Sheumaker. “If you need increased capacity, simply add more servers. If a crash occurs, the redundancies kick in, and there’s no downtime.”
BeeGFS won recognition of its own during the SC18 event when it was presented with an HPCwire 2018 Editors’ Choice Award for Best HPC Storage Product or Technology.
The University of Toronto Formula SAE Racing Team is a student‐run club focused on designing, building and competing with an open‐wheeled race car at Formula Student competitions held globally.
In early 2018 the student team partnered with Advanced Clustering Technologies to make use of the company’s on-demand cloud solution, ACTnowHPC. Using Simulia’s Star-CCM+ to run computational fluid dynamics simulations, the team developed numerous iterations of the front wing’s end plates.
Front wings are critical to formula car design because this area has a significant effect on the aerodynamics of a car. Why? Because it precedes the rest of the car and directs the airflow back toward the rest of the vehicle.
ACTnowHPC gave the team access to high end cpus and a high core counts that were not previously available to them. ACTnowHPC runs on bare metal
hardware, not virtualized machines, in order to reduce run times and optimize results. And the results were impressive.
“Our efficiency has spiked massively,” said Jonathan Lee, senior aerodynamics member. “For example, for our front wing design, we have been able to increase our estimated downforce by 25%. That is a very promising start.”
Read more about the ACTnowHPC cloud solution at www.actnowhpc.com. You can sign up for a free trial.
Advanced Clustering Technologies tracks awards made by the National Science Foundation every year because some of the Major Research Instrumentation grants are awarded to customers for the acquisition of high performance computing hardware. This year, the company noted, has been an unusual year for MRI grants for HPC.
“We have seen an increase in allocations for HPC from the NSF, not just in terms of the number of MRI grants but also in terms of the overall amount being awarded to the institutions,” said Wade Sisson, marketing director for Advanced Clustering Technologies. “Nearly $16 million has been awarded to 19 institutions specifically for HPC equipment purchases. Compare that with 2017, when we saw 17 institutions awarded $10.9 million.”
The MRI grant is one way that universities find funding for large-scale HPC systems. Proposals for the grant are due in January and the award decisions usually are announced in August, September and October.
“This year the MRI award announcements came earlier than we’ve seen in recent years,” Sisson said. “Typically ,we see the bulk of these grant award announcements in September and October. Last year the vast majority of awards were announced in October, but for 2018 more than half of the awards were announced in August.”
MRI Grant Proposals for 2019 are due January 22
MRI grants have helped a number of universities acquire campus-wide HPC clusters through the years. The deadline for next year’s program is Jan. 22, 2019. Read the solicitation here.
Advanced Clustering Technologies has been assisting customers in their pursuit of MRI grant funding for more than 17 years.
“For many years our support came primarily from consultations and detailed equipment quotes, but by 2015 we realized that we had heard do’s and don’ts from enough customers that it might be time to write a white paper about the grant writing process.”
White Papers Offer Best Practices for Writing Your Grant Proposal and RFP
Based on interviews with customers who have won MRI grants in the past, Advanced Clustering’s grant writing white paper offers tips for all phases of the grant application process.
“There are commonalities to successful grant applications, and we felt it was important to share those best practice approaches with future grant applicants,” Sisson said.
“Last year we realized that getting the grant funding is only half the battle,” Sisson said. “Many of our customers said the process of writing a Request for Proposal (RFP) is as challenging, if not more so, than winning the grant funding in the first place.”
Most university purchasing departments do not have much experience with the complexities of HPC equipment purchases.
“It’s not like you’re buying a TV,” Sisson said. “You’re buying a system that can include an endless stream of components, and each system is different. We have found that most grant winners are essentially starting from scratch. There often is no template or sense of where to begin.”
The session took place at 10:30 a.m. and was moderated by Thomas Hauser, Director of Research Computing University of Colorado – Boulder. The panel included Jonathan Anderson, Associate Director of Research Computing at the University of Colorado – Boulder; Tim Kaiser, Director of Research and High Performance Computing Colorado School of Mines; and Jim Paugh, Director of Sales at Advanced Clustering Technologies.
The panel offered best practices about how detailed the RFP document for HPC should be, including such topics as:
meeting the hard requirements (budget, power, etc.)
formulating this when you don’t know what you want
allowing for innovative solutions
structuring acceptance testing and payment parameters