Memory and I/O performance bottlenecks in supercomputing simulations are two key challenges that must be addressed on the road to Exascale. The new byte-addressable persistent non-volatile memory technology from Intel, DCPMM, promises to be an exciting opportunity to break with the status quo, with unprecedented levels of capacity at near-DRAM speeds. Here, we explore the potential of DCPMM in the context of two high-performance scientific applications in terms of outright performance, efficiency and usability for both its Memory and App Direct modes. In Memory mode, we show equivalent performance and better efficiency for a CASTEP simulation that is limited by memory capacity on conventional DRAM-only systems without any changes to the application. For IFS, we demonstrate that a distributed object-store over NVRAM reduces the data contention created in weather forecasting data producer-consumer workflows. In addition, we also present the achievable memory bandwidth performance using STREAM.

In this paper, we propose an OpenFlow enabled Internet infrastructure, using virtual path slicing in an end-to-end path, so that any user connected to an OpenFlow network is dynamically allocated a corresponding right of way. This approach allows an interference-free path, from other traffic, between any two endpoints, on multiple autonomous systems, for a given application flow (e.g., WebHD Video Streaming). Additionally, we propose and implement an end-to-end quality of service framework for the Future Internet and extend the virtual path slice engine to support future Internet technologies such as OpenFlow. The proposed framework is evaluated in distinct multiple autonomous scenarios for a city with a population of 1 million inhabitants, emulating xDSL (Digital Subscriber Line), LTE (Long-Term Evolution) and Fibre networking scenarios. The obtained results confirm the suitability of the proposed architecture between multiple autonomous systems, considering both data and control traffic scalability, as well as resilience and failure recovery. Furthermore, challenges and solutions for experimentation in a large-scale testbed are described.