file.pdf (1.69 MB)
Dimorphic Computing (CMU-CS-06-123)
journal contributionposted on 2006-04-01, 00:00 authored by H. Andres Lagar-Cavilla, Niraj Tolia, Rajesh Balan, Eyal de Lara, M. Satyanarananan, David O'Hallaron
Dimorphic computing is a new model of computing that switches between thick and thin client modes of execution in a completely automated and transparent manner. It accomplishes this without imposing any language or structural requirements on applications. This model greatly improves the performance of applications that alternate between phases of compute- or data-intensive processing and intense user interaction. For such applications, the thin client mode allows efficient use of remote resources such as compute servers or large datasets. The thick client mode enables crisp interactive performance by eliminating the harmful effects of Internet latency and jitter, and by exploiting local graphical hardware acceleration. We demonstrate the feasibility and value of dimorphic computing through AgentISR, a prototype that exploits virtual machine technology. Experiments with AgentISR confirm that the performance of a number of widely-used scientific and graphic arts applications can be significantly improved without requiring any modification.