An Evaluation of the Oak Ridge National Laboratory Cray XT3 Export

@article{citeulike:3577922, abstract = {In 2005, Oak Ridge National Laboratory (ORNL) received delivery of a 5294 processor Cray XT3. The XT3 is Cray's third-generation massively parallel processing system. The ORNL system uses a single-processor node built around the AMD Opteron and uses a custom chip--called SeaStar--for interprocessor communication. The system uses a lightweight operating system called Catamount on its compute nodes. This paper provides a performance evaluation of the Cray XT3, including measurements for micro-benchmark, kernel, and application benchmarks. In particular, we provide performance results for strategic Department of Energy applications areas including climate, biology, astrophysics, combustion, and fusion. Our results, on up to 4096 processors, demonstrate that the Cray XT3 provides competitive processor performance, high interconnect bandwidth, and high parallel efficiency on a diverse application workload, typical in the DOE Office of Science. 10.1177/1094342007085019}, author = {Alam, Sadaf R. and Barrett, Richard F. and Fahey, Mark R. and Kuehn, Jeffery A. and Bronson and Mills, Richard T. and Roth, Philip C. and Vetter, Jeffrey S. and Worley, Patrick H.}, citeulike-article-id = {3577922}, citeulike-linkout-0 = {http://hpc.sagepub.com/cgi/content/abstract/22/1/52}, day = {1}, journal = {International Journal of High Performance Computing Applications}, keywords = {high-performance\_computing, mpi, performance\_analysis}, month = {February}, number = {1}, pages = {52--80}, posted-at = {2008-11-19 11:53:16}, priority = {2}, title = {An Evaluation of the Oak Ridge National Laboratory Cray XT3}, url = {http://hpc.sagepub.com/cgi/content/abstract/22/1/52}, volume = {22}, year = {2008} }

TY - JOUR ID - citeulike:3577922 L3 - citeulike-article-id:3577922 N2 - In 2005, Oak Ridge National Laboratory (ORNL) received delivery of a 5294 processor Cray XT3. The XT3 is Cray's third-generation massively parallel processing system. The ORNL system uses a single-processor node built around the AMD Opteron and uses a custom chip--called SeaStar--for interprocessor communication. The system uses a lightweight operating system called Catamount on its compute nodes. This paper provides a performance evaluation of the Cray XT3, including measurements for micro-benchmark, kernel, and application benchmarks. In particular, we provide performance results for strategic Department of Energy applications areas including climate, biology, astrophysics, combustion, and fusion. Our results, on up to 4096 processors, demonstrate that the Cray XT3 provides competitive processor performance, high interconnect bandwidth, and high parallel efficiency on a diverse application workload, typical in the DOE Office of Science. 10.1177/1094342007085019 IS - 1 JF - International Journal of High Performance Computing Applications EP - 80 TI - An Evaluation of the Oak Ridge National Laboratory Cray XT3 VL - 22 SP - 52 KW - high-performance_computing KW - mpi KW - performance_analysis AU - Alam, Sadaf AU - Barrett, Richard AU - Fahey, Mark AU - Kuehn, Jeffery AU - Bronson AU - Mills, Richard AU - Roth, Philip AU - Vetter, Jeffrey AU - Worley, Patrick PY - 2008/02/01/ UR - http://hpc.sagepub.com/cgi/content/abstract/22/1/52 ER -