While improving raw performance is of primary interest to most users of high-performance computers, energy consumption also is a critical concern. Some microprocessors allow volta...
Dynamic voltage scaling and sleep state control have been shown to be extremely effective in reducing energy consumption in CMOS circuits. Though plenty of research papers have st...
Razvan Racu, Arne Hamann, Rolf Ernst, Bren Mochock...
In this paper we describe Maestro, a dataflow computation framework for Ibis, our Java-based grid middleware. The novelty of Maestro is that it is a self-organizing peer-to-peer s...
Abstract. In this paper we report on our experiences with hybrid parallelism in PARDISO, a high-performance sparse linear solver. We start with the OpenMP-parallel numerical factor...
High-performance computing clusters running longlived tasks currently cannot have kernel software updates applied to them without causing system downtime. These clusters miss oppo...