The system was delivered in late September, 2002. It achieved Linpack performance of 665.1 Gflops on 288 processors in October 2002, making it the 85th fastest computer in the world according to the TOP500 list.
In April 2003, the Linpack benchmarks were run again on 288 processors. Instead of MPICH 1.2.4, we used LAM 6.5.9 as the MPI implementation. In addition, the somewhat newer ATLAS 3.5.0 distribution was used for the level 3 BLAS, and the Intel 7.1 compiler suite was used to compile HPL (while gcc was used for ATLAS). This improved Linpack performance to 757.1 Gflop/s, which resulted in the cluster moving to the 88th fastest computer in the world according to the 21st TOP500 list of June 2003.
The Space Simulator Cluster is dedicated to performing computational astrophysics simulations in the Theoretical Astrophysics group (T-6) at Los Alamos National Laboratory. It is a follow-on to the Loki and Avalon clusters.
[2] M. S. Warren, C. L. Fryer and M. P. Goda. The Space Simulator: Modeling the Universe from Supernovae to Cosmology. In Proceedings of the ACM/IEEE SC2003 Conference, ACM Press, 2003. (PDF)
Michael S. Warren, mswarren@lanl.gov
M. Patrick Goda, pgoda@lanl.gov
Last modified: October 23, 2003