Texas A&M University is partnering with IBM to create on scientific research that will be supported by a large computational sciences infrastructure -- the initial focus will be on agriculture, geosciences and engineering.
The collaboration will harness big data analytics and HPC systems to research on improving extraction of energy resources, facilitating the smart energy grid, accelerating materials development, improving disease identification and tracking in animals, and developing a better understanding of global food supplies.
The A&M system will consist of a research computing cloud that will be made up of IBM hardware and software. Blue Gene/Q will serve as the foundation of the computing infrastructure, with a Blue Gene/Q system consisting of two racks, with more than 2,000 compute nodes, providing 418 teraflops (TF) of sustained performance. A total of 75 PowerLinux 7R2 servers with POWER7+ microprocessors will be connected by 10GbE into a system optimised for big data analytics and high performance computing.
This complex includes IBM BigInsights and Platform Symphony software, IBM Platform LSF scheduler, and IBM General Parallel File System. The system will also contain an estimated 900 IBM System x dense hyperscale compute nodes as part of an IBM NeXtScale system. Some of the nodes will be managed by Platform Cluster Manager Advanced Edition (PCM-AE) as a University-wide HPC cloud while the others will be managed by Platform Cluster Manager Standard Edition (PCM-SE) and serve as a general purpose compute infrastructure for the geosciences and open source analytics initiatives.
Texas A&M Engineering Experiment Station (TEES) partners with academic institutions, governmental agencies, industries, and communities to help improve the quality of life, promote economic development, and enhance the educational systems of Texas.
In support of the long-term research effort, IBM will supply technical computing technologies, which will be cloud-enabled. IBM will work with researchers at the A&M System to assess new computing technologies to advance data-driven science discovery and innovation over the next few years.