Differences

This shows you the differences between two versions of the page.

--- pads:a-pads [2013/01/03 18:11] – gdangelo
+++ pads:a-pads [2013/01/03 18:13] (current) – gdangelo
@@ Line 4: / Line 4: @@
-//Designing, implementing and evaluating a **Parallel And Distributed Simulation (PADS) middleware** capable to work **seamlessly** and **efficiently** among multiple execution architectures (e.g. multi-core smartphones, multi-core desktop CPUs, LAN/WAN clusters, HPCs such as the **IBM Blue Gene** and **public Cloud infrastructures** such as Amazon EC2).//
+//Designing, implementing and evaluating a **Parallel And Distributed Simulation (PADS) middleware** capable to work **seamlessly** and **efficiently** among multiple execution architectures (e.g. multi-core smartphones, multi-core desktop CPUs, LAN/WAN clusters, HPCs such as the **IBM Blue Gene** and public Cloud infrastructures such as **Amazon EC2**).//
 ===== Description =====
@@ Line 15: / Line 15: @@
 A more modern approach, called Parallel Discrete Event Simulation (PDES), relies on multiple interconnected execution units (e.g. CPUs or hosts). In this way, building a so called Parallel And Distributed Simulation (PADS), it is possible to represent very large and complex models using aggregated resources from many execution units and, in some cases, to obtain a speed up with respect to sequential simulation.
-Unfortunately, at the state of the art, there are still many problems that limit the efficiency and the diffusion of PDES. A couple of them are:
+Unfortunately, at the state of the art, there are still many problems that limit the efficiency and the diffusion of PADS. A couple of them are:
-the performance of PDES are strongly affected by the execution environment, the simulation model and the simulation characteristics. Specific features such as the adaptive partitioning of the simulation model and the load-balancing at runtime (of computation and communication) are not available in the simulation middlewares;
+  * the performance of PADS are strongly affected by the execution environment, the simulation model and the simulation characteristics. Specific features such as the adaptive partitioning of the simulation model and the load-balancing at runtime (of computation and communication) are not available in the simulation middlewares;
-moving from an execution architecture, for example a multi-CPU multi-core host, to a public Cloud (e.g. Amazon EC2) is not transparent to the simulation developer. This is a severe limitation for a widespread diffusion of modern public Cloud infrastructures for running simulations.
+  * moving from an execution architecture, for example a multi-CPU multi-core host, to a public Cloud (e.g. Amazon EC2) is not transparent to the simulation developer. **This is a severe limitation for a widespread diffusion of modern public Cloud infrastructures for running simulations.**
 ===== Past and ongoing activity =====
 The A-PADS research project will further extend the work done on the [[pads:artis|ARTÌS]]/[[pads:gaia|GAIA]] [1, 2] middleware. In the past years we have obtained very good performance results using multi-CPU multi-core CPUs and LAN/WAN based clusters. Now we are working on the porting and adaptation of ARTÌS/GAIA+ to the [[http://www.cineca.it/en/content/fermi-bgq|IBM Blue Gene/Q]] system and we plan to extend our work to support some public Cloud infrastructures (e.g. Amazon EC2). More in detail, the support of Cloud infrastructures will require the design, implementation and evaluation of a brand new set of features that are specific to the characteristics and idiosyncrasies of the Cloud (e.g. jitter, fault tolerance, security etc.).
-Related work
+===== Related work =====
 In the [[http://www.cs.unibo.it/~gdangelo/tutorial-hpcs-2011.html|HPCS 2001 tutorial]] [3] we have described why a new approach is necessary for building simulators that are able to fulfill the requirements described above. In [4] the authors, have demonstrated that the Amazon EC2 infrastructure can be used for running distributed simulations with acceptable results in terms of performance and cost. In our vision, the approach introduced in [4] is a good starting point for the development of new specifically tailored mechanisms that will be able to speed up the execution of PADS on public Clouds.