Workshops
Workshop on Cloud Computing
Vinod Rebello and Sarita Bruschi
The Workshop on Cloud Computing (WCC) is an international forum for discussing recent developments and hot topics related to the cloud computing continuum. The workshop aims to attract researchers, industry professionals, and students from the fields of artificial intelligence, big data, systems architecture, service-oriented architecture, virtualization, security and privacy, and, in particular, high performance computing, to share cutting-edge advances in the theory and practice of exploiting cloud computing platforms. The workshop aims to foster the exchange of ideas, highlight emerging research directions, and help shape the future of cloud computing.
A European Software Suite for Modular HPC systems from the EUPEX project
Sai Narasimhamurthy, Pélagie Alves and Jean-Robert Bacou
This workshop presents the software ecosystem developed within the EUPEX project, a European initiative focused on building a modular supercomputing platform based on European technologies, including processors from the European Processor Initiative (EPI). The EUPEX software suite is designed to support both application developers and system operators, enabling efficient execution of scientific and industrial workloads on systems based on Modular Supercomputing Architecture (MSA).
17th Workshop on Applications for Multicore Architectures
Claude Tadonki
Since the advent of the multi-core concept, significant advances have been made on many of the related aspects. Multi-core has become a natural element in the HPC ecosystem, and its pervasiveness within the landscape of common computing devices has made it a standard. Therefore, hardware and software concerns related to multi-core are good targets for computer science investigations, with a high potential for a genuine contribution. Beside the plethora of applications for which more powerful solutions are still expected, efficient implementation techniques for many-core chip processors are of keen interest. WAMCA is aiming at providing an opportunity to address all aforementioned technical challenges and more, including reports on specific case studies. This workshop is an opportunity for application designers and computer architects to discuss new techniques and emerging applications as well as their implications on current and next-generation many-core architectures.
Tutorials
Parallel Scalability Suite: Profiling and Visualizing the Scalability of Parallel Applications
Samuel Xavier-de-Souza, Elisa Gabriela Lucena and Pedro Rici
PaScal Suite integrates two tools, the PaScal Analyzer and the PaScal Viewer. It simplifies the execution, measurement, and comparison of several executions of a parallel program, allowing the analysis of scalability trends in configuration environments with different amounts of processing elements and different workloads with visual elements that help the user to understand the program’s behavior and recognize scalability bottlenecks that may require in-depth optimization analysis. The toolset can be used to help the development of parallel programs that run on a single shared-memory computational node. Future versions will support distributed programs running on many nodes.
Unlocking malleability in HPC applications
Alberto Cascajo and Javier Fernandez Muñoz
This demonstration showcases the concept of malleability in High Performance Computing (HPC) using FlexMPI. Malleability refers to the ability of a parallel application to dynamically adapt the number of processes it uses during execution, allowing it to respond to changes in resource availability in real time. In this demo, we illustrate how FlexMPI enables an application to expand or shrink its computational resources without stopping execution. This capability improves overall system efficiency by better utilizing available resources and reducing idle time in shared environments such as HPC clusters.