The ETH Zurich systems group and enterprise computing centerGustavo Alonso; Donald Kossmann; Timothy Roscoe; Nesime Tatbul; Andrew Baumann; Carsten Binnig; Peter M. Fischer; Oriana Riva; Jens Teubner
In: SIGMOD Record, Vol. 37, No. 4, Pages 94-99, Association for Computing Machinery (ACM), 2008.
Computer science is facing a fundamental paradigm shift. Multicore architectures, application virtualization, and cloud computing each present on their own radical departures in the way software is built, deployed, and operated. Taken together, these trends frame a scenario that makes sense from many points of view (usability, scalability, flexibility, development cost) but is also radically different from what we know today. It is fair to say that a coherent answer to the challenges raised by the combination of these trends has yet to emerge from either academia or industry. From an academic perspective, these challenges are particularly difficult because they imply a considerable departure from established procedures. To start with, multicore computers, the virtualization of computing platforms, and the replacement of the one-computer-one-local-copy-ofa-program approach by cloud computing each demand an interdisciplinary approach. In practice, it is likely that traditional disciplines such as operating systems, distributed systems, software engineering, or data management will require major revision as the boundaries between them become blurred.