Advances in VLSI (Very Large Scale Integration) technology have made the raw ingredients for computation plentiful. Large amounts of fast functional units, memory, and bandwidth can be made efficient in terms of chip area, cost, and energy, however, high-performance computers realize only a small fraction of VLSI’s potential. In this talk, Mattan Erez describes the Merrimac streaming supercomputer, which is being developed with an integrated view of the applications, software system, compiler, and architecture. Erez shows how this approach leads to an order of magnitude gain in performance per unit cost, unit power, and unit floor-space for scientific applications compared to common scientific computers designed around clusters of conventional CPUs. This program covers Merrimac's stream architecture, mapping scientific applications to effectively run on the stream architecture, and system issues in the Merrimac supercomputer. From the Series:CSE Colloquia - 2006