Tera-Scalable Algorithms for Variable-Density Elliptic Hydrodynamics with Spectral Accuracy Session: High End Computing Applications Event Type: Paper Time: 3:30pm - 4:00pm Session Chair: Esmond G Ng Speaker(s): Andrew W. Cook, William H. Cabot, Michael L. Welcome, Peter L. Williams, Brian J. Miller, Bronis R. de Supinski, Robert K. Yates Location: 606-607 Abstract: We describe Miranda, a massively parallel spectral/compact solver for variable-density incompressible flow, including viscosity and species diffusivity effects. Miranda utilizes FFTs and band-diagonal matrix solvers to compute spatial derivatives to at least 10th-order accuracy. We have successfully ported this communication-intensive application to BlueGene/L and have explored both direct block parallel and transpose-based parallelization strategies for its implicit solvers. We have discovered a mapping strategy which results in virtually perfect scaling of the transpose method up to 65,536 processors of the BlueGene/L machine. Sustained global communication rates in Miranda typically run at 85% of the theoretical peak speed of the BlueGene/L torus network, while sustained communication plus computation speeds reach 2.76 TeraFLOPS. This effort represents the first time that a high-order variable-density incompressible flow solver with species diffusion has demonstrated sustained performance in the TeraFLOPS range. This paper can be found in the ACM and IEEE Digital Libaries Click here for ACM Click here for IEEE Chair/Speaker Details: Esmond G Ng (Chair) Lawrence Berkeley National Laboratory Andrew W. Cook LLNL William H. Cabot LLNL Michael L. Welcome LBNL Peter L. Williams LLNL Brian J. Miller LLNL Bronis R. de Supinski LLNL Robert K. Yates LLNL