Abbrevation
ROSS
City
PortlandOR
Country
United States
Deadline Paper
Start Date
End Date
Abstract

The complexity of node architectures in supercomputers increases as we<br>cross petaflop milestones on the way towards Exascale&#046; Increasing<br>levels of parallelism in multi&#8211; and many&#8211;core chips and emerging<br>heterogeneity of computational resources coupled with energy and memory<br>constraints force a reevaluation of our approaches towards operating<br>systems and runtime environments&#046;<br>The ROSS workshop, to be held as a full&#8211;day meeting at the HPDC 2015<br>conference in Portland, Oregon, USA, focuses on principles and techniques<br>to design, implement, optimize, or operate runtime and operating systems<br>for supercomputers and massively parallel machines&#046;<br>&#8211; OS and runtime system scalability on many&#8211;node and multi/many&#8211;core systems<br>&#8211; specialized OSs for Supercomputing<br>&#8211; distributed/hybrid/partitioned OSs and runtime systems for Supercomputing<br>&#8211; fault tolerance<br>&#8211; system noise analysis and prevention<br>&#8211; interaction between middleware, runtime system, and the OS<br>&#8211; modeling and performance analysis of runtime systems<br>&#8211; OS and runtime considerations for large&#8211;volume, high&#8211;performance I/O<br>&#8211; parallel job startup<br>&#8211; memory management and emerging memory technologies<br>&#8211; the role of OS and runtime system in minimizing power usage<br>&#8211; real&#8211;time considerations for Supercomputing<br>