High Performance Computing (HPC) Systems
TACC operates many of the most powerful and capable high performance computing systems in the world, which are used by thousands of scientists and engineers each year to perform research in all domains of science, including the humanities, digital media, and the arts. At nearly 10 petaflops, Stampede is operational and available to the national open science community (as of January 7, 2013). Stampede is one of the world's most comprehensive systems for the open science community as part of the National Science Foundation's (NSF) XSEDE (formerly NSF TeraGrid) program. After five years of stellar performance and contributions to open science, Ranger retired on February 4, 2013. At 579.4 teraflops, Ranger was the most powerful and capable HPC system in the NSF TeraGrid when it was deployed in February 2008. Additionally, Lonestar 4, which went online in February 2011, clocks in at more than 302 teraflops and offers nearly 200 million computing hours per year to researchers. Our newest system, Wrangler, will debut in January of 2015.
Dell PowerEdge C8220 Cluster with Intel Xeon Phi coprocessors
Stampede is one of the largest computing systems in the world for open science research. As an NSF HPC acquisition, this system provides unprecedented computational capabilities to the national research community enabling breakthrough science that has never before been possible. The scale of Stampede delivers opportunities in computational science and technology research, from highly parallel algorithms to high-throughput computing, from scalable visualization to next generation programming languages.
Dell Linux Cluster
Lonestar is a powerful, multi-use cyberinfrastructure HPC and remote visualization resource. The system contains 22,656 cores within 1,888 Dell PowerEdgeM610 compute blades (nodes), 16 PowerEdge R610 compute-I/Oserver-nodes, and 2 PowerEdge M610 (3.3GHz) login nodes. Each compute node has 24GB of memory, and the login/development nodes have 16GB. The system storage includes a 1000TB parallel (SCRATCH) Lustre file system, and 276TB of local compute-node disk space (146GB/node).
Wrangler is scheduled to be in production by January 5, 2015. It will be the most powerful data analysis system allocated in XSEDE, with 10PB replicated, secure, high performance data storage (at TACC and Indiana University). It will consist of 3,000 embedded processing cores for data analysis; 120 Intel Haswell based servers for data access and embedded analytics; and a large scale flash storage tier for analytics, with bandwidth of 1TB/s and 275M IOPS. The system will provide flexible support for a wide range of software stacks, including Hadoop and relational data, and integration with Globus Online services for rapid and reliable data transfer and sharing. Its fully scalable design will allow for growth in both the number of users and data applications.