First-Hand:The Supercomputer Class Evolution: A Personal Perspective
By C. Gordon Bell
Since my first visit to Lawrence Livermore National Laboratory in 1961, seeing the LARC, the elegance of the CDC 6600, and just observing computer evolution have been high points of my life as an engineer in the computing industry. Throughout their early evolution, supercomputer architecture “trickled down” for use with other computers. In the mid 1990s the flow reversed when large computers became scalable and constructed from clusters of microprocessor-based computers that Livermore’s Eugene Brooks wrote about in 1989. Unlike the two paths of Bell’s Law that account for the birth, evolution, and death of other computer classes e.g. minicomputers, supercomputers have doubled in performance every year for the last 50 years.
While computer performance is the first order term to track their high performance, many other factors, e.g. FORTRAN, LINPACK, government funding policy, and application pull have contributed to the extraordinary progress in supercomputing. I hope to trace the trajectory and contributors to this exciting class.
The Supercomputer Class Evolution: A Personal Perspective (Video of talk given at Lawrence Livermore National Laboratory, 24 April 2013.