Abstract :
Summary form only given. This talk (modestly) attend to address challenges and opportunities ahead of us for making parallel programming as efficient, as productive, as effective as possible, on both Multi-cores and large-scale infrastructures such as Grids and Clouds. We draw on our experience at simplifying the programming of applications that are distributed on local area network (LAN), on cluster of workstations, or GRIDs, and of course, Clouds. We will discuss a specific approach, Network On Ship, to cope seamlessly with both distributed and shared-memory multi-core machines. The point will be illustrated with ProActive an Open Source library for parallel, distributed, and concurrent computing, allowing to showcase interactive and graphical GUI and tools. Benchmarks on platforms such as Grid 5000, together with standardization and collaboration with Chinese partners will also be reported.
Keywords :
distributed shared memory systems; grid computing; parallel programming; workstation clusters; LAN; cloud computing; distributed memory multicore machine; grid computing; large-scale system; local area network; network-on-ship; parallel/distributed programming; shared-memory multicore machine; workstation cluster; Clouds; Concurrent computing; Graphical user interfaces; Large-scale systems; Libraries; Local area networks; Marine vehicles; Parallel programming; Standardization; Workstations;
