The session began with a welcome and introduction by Mateo Valero (BSC), one of the main drivers of this cooperation and a leading name in the field of HPC. This intervention was later complemented by Fabrizio Gagliardi (BSC). Afterward, Elsa Carvalho (INESC TEC) presented the work done in terms of communication by the RISC2 team, an important segment for all the news and achievements to reach all the partners and countries involved.

Carlos J. Barrios Hernandez then presented the work done within the HPC Observatory, a relevant source of information that European and Latin American research organizations can address with HPC and/or AI issues.

The session closed with an important and pertinent debate on how to strengthen cooperation in HPC between the European Union and Latin America, in which all participants contributed and gave their opinion, committing to efforts so that the work developed within the framework of RISC2 is continued.

What our partners had to say about the meeting?

Rafael Mayo Garcia, CIEMAT:

“The policy event organized by RISC2 in Brussels was of utmost importance for the development of HPC and digital capabilities for a shared infrastructure between EU and LAC. Even more, it has had crucial contributions to international entities such as CYTED, the Ibero-American Programme for the Development of Science and Technology. On the CIEMAT side, it has been a new step beyond for building and participating in a HPC shared ecosystem.”

Esteban Meneses, CeNAT:

“In Costa Rica, CeNAT plays a critical role in fostering technological change. To achieve that goal, it is fundamental to synchronize our efforts with other key players, particularly government institutions. The event policy in Brussels was a great opportunity to get closer to our science and technology ministry and start a dialogue on the importance of HPC, data science, and artificial intelligence for bringing about the societal changes we aim for.”

Esteban Mocskos, UBA:

“The Policy Event recently held in Brussels and organized by the RISC2 project had several remarkable points. The gathering of experts in HPC research and management in Latin America and Europe served to plan the next steps in the joint endeavor to deepen the collaboration in this field. The advance in management policies, application optimization, and user engagement are fundamental topics treated during the main sessions and also during the point-to-point talks in every corner of the meeting room.
I can say that this meeting will also spawn different paths in these collaboration efforts that we’ll surely see their results during the following years with a positive impact on both sides of this fruitful relationship: Latin America and Europe.”

Sergio Nesmachnow, Universidad de la República:

“The National Supercomputing Center (Uruguay) and Universidad de la República have led the development of HPC strategies and technologies and their application to relevant problems in Uruguay. Specific meetings such as the policy event organized by RISC2 in Brussels are key to present and disseminate the current developments and achievements to relevant political and technological leaders in our country, so that they gain knowledge about the usefulness of HPC technologies and infrastructure to foster the development of national scientific research in capital areas such as sustainability, energy, and social development. It was very important to present the network of collaborators in Latin America and Europe and to show the involvement of institutional and government agencies.

Within the contacts and talks during the organization of the meeting, we introduced the projecto to national authorities, including the National Director of Science and Technology, Ministry of Education and Culture, and the President of the National Agency for Research and Innovation, as well as the Uruguayan Agency for International Cooperation and academic authorities from all institutions involved in the National Supercomputing Center initiative. We hope the established contacts can result in productive joint efforts to foster the development of HPC and related scientific areas in our country and the region.”

Carla Osthoff, LNCC:

“In Brazil, LNCC is critical in providing High Performance Computing Resources for the Research Community and training Human Resources and fostering new technologies. The policy event organized by RISC2 in Brussels was fundamental to synchronizing LNCC efforts with other government institutions and international  entities. On the LNCC side, it has been a new step beyond building and participating in an HPC-shared ecosystem.

Specific meetings such as the policy event organized by RISC2 in Brussels  were very important to present the network of collaborators in Latin America and Europe and to show the involvement of institutional and government agencies.

As a result of joint activities in research and development in the areas of information and communication technologies (ICT), artificial intelligence, applied mathematics, and computational modelling, with emphasis on the areas of scientific computing and data science, a Memorandum of Understanding (MoU) have been signed between LNCC and Inria/France. As a  result of new joint activities, LNCC and INESC TEC/Portugal are starting  collaboration through INESC TEC International Visiting Researcher Programme 2023.”

The post RISC2’s partners gather in Brussels to reflect on three years of collaboration between EU and Latin America first appeared on RISC2 Project.

Date: May 31, 2023 | 4 p.m. (UTC+1)

The post Webinar: Addressing the challenges of scientific visualization in the exascale age first appeared on RISC2 Project.

Our partners Carlos Barrios Hernandez (from Industrial University of Santander) and Esteban Meneses (from Costa Rica National High Technology Center) participated directly on the “Americas HPC Collaboration” session, on November 16, which aimed to showcase opportunities and experiences between different HPC networks. On this session, Philippe Navaux (from UFRGS and SCALAC) presented the RISC2 project.

It was also during the conference that RISC2 was honoured with the HPCwire Editors’ Choice Award for “Best HPC Collaboration (Academia/Government/Industry)” 2022.

The partners representing RISC2 were Fabrizio Gagliardi (from Barcelona Supercomputing Center), Rui Oliveira (from INESC TEC), Bernd Mohr (from Jülich Supercomputing Centre), Carlos Barrios Hernandez (from Industrial University of Santander), Esteban Meneses (from Costa Rica National High Technology Center), Pedro Alberto (From University of Coimbra), and Philippe Navaux (from UFRGS and SCALAC).

The post RISC2 attended the Supercomputing Conference 2022 first appeared on RISC2 Project.

As the utility and usage of HPC infrastructures increases, more computational and storage power is required to efficiently handle the amount of targeted applications. In fact, many HPC centers are now aiming at exascale supercomputers supporting at least one exaFLOPs (1018 operations per second), which represents a thousandfold increase in processing power over the first petascale computer deployed in 2008 [RD+15]. Although this is a necessary requirement for handling the increasing number of HPC applications, there are several outstanding challenges that still need to be tackled so that this extra computational power can be fully leveraged. 

Management of large infrastructures and heterogeneous workloads: By adding more compute and storage nodes, one is also increasing the complexity of the overall HPC distributed infrastructure and making it harder to monitor and manage. This complexity is increased due to the need of supporting highly heterogeneous applications that translate into different workloads with specific data storage and processing needs [ECS+17]. For example, on the one hand, traditional scientific modeling and simulation tasks require large slices of computational time, are CPU-bound, and rely on iterative approaches (parametric/stochastic modeling). On the other hand, data-driven Big Data applications contemplate shorter computational tasks, that are I/O bound and, in some cases, have real-time response requirements (i.e., latency-oriented). Also, many of the applications leverage AI and machine learning tools that require specific hardware (e.g., GPUs) in order to be efficient.

Support for general-purpose analytics: The increased heterogeneity also demands that HPC infrastructures are now able to support general-purpose AI and BigData applications that were not designed explicitly to run on specialised HPC hardware [KWG+13]. Therefore, developers are not required to significantly change their applications so that they can execute efficiently at HPC clusters.

Avoiding the storage bottleneck: By only increasing the computational power and improving the management of HPC infrastructures it may still not be possible to fully harmed the capabilities of these infrastructures. In fact, Big Data and AI applications are data-driven and require efficient data storage and retrieval from HPC clusters. With an increasing number of applications and heterogeneous workloads, the storage systems supporting HPC may easily become a bottleneck [YDI+16, ECS+17]. Indeed, as pointed out by several studies, the storage access time is one of the major bottlenecks limiting the efficiency of current and next-generation HPC infrastructures. 

In order to address these challenges, RISC2 partners are exploring: New monitoring and debugging tools that can aid in the analysis of complex AI and Big Data workloads in order to pinpoint potential performance and efficiency bottlenecks, while helping system administrators and developers on troubleshooting these [ENO+21].

Emerging virtualization technologies, such as containers, that enable users to efficiently deploy and execute traditional AI and BigData applications in an HPC environment, without requiring any changes to their source-code [FMP21].  

The Software-Defined Storage paradigm in order to improve the Quality-of-Service (QoS) for HPC’s storage services when supporting hundreds to thousands of data-intensive AI and Big Data applications [DLC+22, MTH+22].  

To sum up, these three research goals, and respective contributions, will enable the next generation of HPC infrastructures and services that can efficiently meet the demands of Big Data and AI workloads. 

References

[DLC+22] Dantas, M., Leitão, D., Cui, P., Macedo, R., Liu, X., Xu, W., Paulo, J., 2022. Accelerating Deep Learning Training Through Transparent Storage Tiering. IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid)  

[ECS+17] Joseph, E., Conway, S., Sorensen, B., Thorp, M., 2017. Trends in the Worldwide HPC Market (Hyperion Presentation). HPC User Forum at HLRS.  

[FMP21] Faria, A., Macedo, R., Paulo, J., 2021. Pods-as-Volumes: Effortlessly Integrating Storage Systems and Middleware into Kubernetes. Workshop on Container Technologies and Container Clouds (WoC’21). 

[KWG+13] Katal, A., Wazid, M. and Goudar, R.H., 2013. Big data: issues, challenges, tools and good practices. International conference on contemporary computing (IC3). 

[NCR+18] Netto, M.A., Calheiros, R.N., Rodrigues, E.R., Cunha, R.L. and Buyya, R., 2018. HPC cloud for scientific and business applications: Taxonomy, vision, and research challenges. ACM Computing Surveys (CSUR). 

[MTH+22] Macedo, R., Tanimura, Y., Haga, J., Chidambaram, V., Pereira, J., Paulo, J., 2022. PAIO: General, Portable I/O Optimizations With Minor Application Modifications. USENIX Conference on File and Storage Technologies (FAST). 

[OG+15] Osseyran, A. and Giles, M. eds., 2015. Industrial applications of high-performance computing: best global practices. 

[RD+15] Reed, D.A. and Dongarra, J., 2015. Exascale computing and big data. Communications of the ACM. 

[ENO+21] Esteves, T., Neves, F., Oliveira, R., Paulo, J., 2021. CaT: Content-aware Tracing and Analysis for Distributed Systems. ACM/IFIP Middleware conference (Middleware). 

[YDI+16] Yildiz, O., Dorier, M., Ibrahim, S., Ross, R. and Antoniu, G., 2016, May. On the root causes of cross-application I/O interference in HPC storage systems. IEEE International Parallel and Distributed Processing Symposium (IPDPS). 

By INESC TEC

The post HPC meets AI and Big Data first appeared on RISC2 Project.

This event, which aimed at preparing students and researchers to introduce HPC tools in their workflows, discussed topics such as Shared-Memory Programming, Distributed-Memory Programming, and High Performance Computing. Rui Oliveira, from INESC TEC, was the Keynote Speaker of this year’s edition of the event.  During his talk, Rui gave a historical perspective of HPC in Europe and Portugal, emphasizing the design and main considerations of the upcoming  Deucalion supercomputer at Minho Advanced Computing Center.

For Esteban Meneses, Costa Rica HPC School General Chair, the event is of strategic importance for the Central American region. As developing countries aim at catching up with European peers in the use of HPC for science and technology, having training resources is fundamental. An in-person event is also a fantastic opportunity for networking and building up truly interdisciplinary research teams.

The post 23 people gathered at the Costa Rica HPC School 2022 to learn more about HPC tools first appeared on RISC2 Project.

“The foreseeable expansion of Eureka to Brazil means new great opportunities to all RISC2 partners”, said Rui Oliveira, member INESC TEC’s Board and director of the Center for Advanced Computing at the University of Minho (MACC).

The post RISC2 partners met at UFRJ during the “Eureka meets the Atlantic” event first appeared on RISC2 Project.