The Cray MTA and Unstructured Meshes

The Cray MTA, a multithreaded architecture, is a new parallel supercomputer installed at San Diego Supercomputer Center (SDSC). This machine has an architecture quite different from those of other contemporary parallel machines. It has a flat, shared memory without locality and has hardware support for very fine-grained multithreading. The machine and its associated parallelizing compiler promise great ease in scalable parallel computing. We report the results of a study, carried out in July–September 1999, to evaluate the execution of EUL3D, a code that solves the Euler equations on an unstructured mesh, on the 8 processor MTA at SDSC. EUL3D captures the essential features of most unstructured mesh codes used in aerodynamic research and development. Our investigation shows that parallelization of an unstructured code is very straightforward on the MTA. We were able to get an existing parallel code (designed for a shared memory machine), running on the MTA by changing only the compiler directives. Furthermore, a serial version of this code was compiled to run in parallel on the MTA by judicious use of directives to invoke the “full/empty” tag bits of the machine to obtain synchronization. This version achieves nearly 250 Mflop/s per processor with little variation as the number of processors is increased from 1 to 8. We achieved this performance without concerning ourselves with the partitioning or placement of data—issues that would be of paramount importance in other parallel architectures. Our research shows that the fine-grained multithreading possible on the custom built MTA is an interesting alternative to the coarse grained parallelism available on multiprocessors constructed from commodity microcomputers. The recent introduction of commercial microcomputers designed specifically to support multithreading, such as the Intel IXP1200, supports our argument.