Performance of Ultra-Scale Applications on Leading Vector and Scalar HPC Platforms
Leonid Oliker, Andrew Canning, Jonathan T. Carter, John M. Shalf, Horst D. Simon, S. Ethier, Parks, David, Shigemune Kitawaki, Yoshinori Tsuda, Tetsuya Sato · Institutional Repositories DataBase (IRDB) · 2005
Abstract The last decade has witnessed a rapid proliferation of superscalar cache-based microprocessors to build high-end capability and capacity computers primarily because of their generality, scalability, and cost effectiveness. However, the constant degradation of superscalar sustained performance, has become a wellknown problem in the scientific computing community. This trend has been widely attributed to the use of superscalar-based commodity components who’s architectural designs offer a balance between memory performance, network capability, and execution rate that is poorly matched to the requirements of large-scale numerical computations. The recent development of massively parallel vector systems offers the potential to increase the performance gap for many important classes of algorithms. In this study we examine four diverse scientific applications with the potential to run at ultrascale, from the areas of plasma physics, material science, astrophysics, and magnetic fusion. We compare performance between the vector-based Earth Simulator (ES) and Cray X1, with leading superscalar-based platforms: the IBM Power3/4 and the SGI Altix. Results demonstrate that the ES vector systems achieve excellent performance on our application suite – the highest of any architecture tested to date. 1.