HPC Data Analysis May Lead To Research Breakthroughs
It’s all due to a IBM Power7-based supercomputer IBM has donated as part of a $7.6 million IBM Shared University Research award that also includes HPC software, services and life sciences computing expertise. The “BlueBioU” system will be used by Rice researchers and collaborating partners within the Texas Medical Center. The Linux-based system, which features 608 Power7 processors that are capable of simultaneously running 2,432 tasks, is housed at Rice's $16 million state-of-the-art data center. The supercomputer’s energy-efficient features include the ability to create policies and protocols that optimize the balance between energy usage and performance. Power7 microprocessors are an attractive option for computationally demanding and memory-intensive problems in biomedical and life sciences research. The Power7 hardware and software offer real-time analytics capabilities well-suited for mining vast genomic and medical databases. The BlueBioU is capable of handling of 18.8 teraflops, or 18.8 trillion floating point calculations per second. "The productivity and performance benefits of the Power7 platform are well aligned with Rice's future directions for research computing, as well as our ultimate goal of working with the medical center to enhance treatment options and find new cures for patients," said Vivek Sarkar, Rice's E.D. Butcher Professor of Computer Science and professor of electrical and computer engineering, said in a statement. The system will help analyze the genomes of 50 patients with ovarian cancer to discover the mutation profile underlying the disease as well as analyzing 1,000 patients with different cancers over the next year. The data center is connected to the Rice campus and to Texas Medical Center partners through a new $22 million network featuring a multi-gigabit backbone and more than a terabit of aggregate bandwidth. In addition, Rice has a new high-availability storage infrastructure that provides multiple terabytes of data storage in the data center. |
