PSTSWM Description
The Parallel Spectral Transform Shallow Water Model represents an important computational kernel in spectral global atmospheric models. As 99% of the floating-point operations are multiply or add, it runs well on systems optimized for these operations. PSTSWM exhibits little reuse of operands as it sweeps through the field arrays; thus it exercises the memory subsystem as the problem size is scaled and can be used to evaluate the impact of memory contention in SMP nodes.
These experiments examine serial performance, both using one processor and running the serial benchmark on multiple processors simultaneously. Performance is measured for a range of horizontal problems resolutions for 18 vertical levels.