next up previous
Next: C: Processor in Memory Up: I: Petaflops Architectures Previous: A: Conventional Distributed Shared

B: Superconducting Design

  1. 200 GHz superconducting C.P.U. with negligible cache and simple architecture, giving 200 Gigaflops performance (this is probably conservative)
  2. Conventional memory subsystem
  3. 5,000 supercomputing C.P.U.'s and the same memory as option A; giving 1 Petaflops performance and 64 Terabytes of memory


Geoffrey Fox, Northeast Parallel Architectures Center at Syracuse University, gcf@npac.syr.edu