Kategórie
General

Services of the POP CoE

The Performance Optimisation and Productivity Centre of Excellence in HPC provides performance optimisation and productivity services for (your?) academic AND industrial code(s) in all domains!

Services of the POP CoE

The Performance Optimisation and Productivity Centre of Excellence in HPC provides performance optimisation and productivity services for (your?) academic AND industrial code(s) in all domains!

The idea that drives the POP CoE (Performance Optimisation and Productivity Centre of Excellence in HPC) is a simple one: to boost productivity of EU research and industry by providing free of charge services that help improve performance of high performance computing (HPC) and parallel software. The aim of POP is to offer our world-class HPC competence to organisations that want to understand software performance issues and to adopt parallel programming best practice.

Main services of the POP CoE are: Performance Audits, Improvement Plans, Proof-of-Concept demos, and Training.

  • Performance Audits are an initial analysis measuring a range of performance metrics to assess quality of performance and identify the issues affecting performance.
  • Improvement Plans undertake further performance evaluations to qualify and quantify solutions and estimate potential improvements.
  • Proof of Concept work uses extracted application kernels to demonstrate actual benefits from tuning and optimisation.
  • Training offers events and materials covering parallel profiling tools, programming models and parallelisation approaches.

Services are free of charge to organisations, SMEs, ISVs, companies in the EU!

 Services of POP CoE are provided for:

  • Code developers. (Assessment of detailed actual behavior, suggestion of most productive directions to refactor code…)
  • Users. (Assessment of achieved performance in specific production conditions, possible improvements modifying environment setup, evidence to interact with code provider...)
  • Infrastructure operators. (Assessment of achieved performance in production conditions, possible improvements from modifying environment setup, information for time computer time allocation processes, training of support staff...)
  • Vendors. (Benchmarking, customer support, system dimensioning/design...)
Central European Working Group in Slovenia 19 May - On May 19, 2025, we met with representatives of National Competence Centres for High-Performance Computing (HPC) from Central European countries. The in-person meeting of the Central European Working Group, held in Slovenia, provided us with an exceptional opportunity to exchange experiences, strengthen regional cooperation, and discuss the shared challenges and opportunities we face within the EuroCC project. We built professional relationships and engaged in constructive discussions with representatives from neighboring countries that, like Slovakia, are running their national HPC competence centres and working on their continuous development. Such meetings play an important role in shaping common approaches, identifying synergies, and sharing best practices in delivering services to users—whether they are research institutions, the public sector, or businesses.
What Is Artificial Intelligence Capable of Today? Watch the Recording of the Webinar "Training Machines to Detect Any Object" 16 May - Dňa 13. mája 2025 sa uskutočnil odborný webinár s názvom Trénovanie strojov na detekciu ľubovoľného objektu, ktorý pripravil RNDr. Andrej Lúčny, PhD. z Fakulty matematiky, fyziky a informatiky Univerzity Komenského v Bratislave. Prednáška bola zameraná na aktuálne výzvy a riešenia v oblasti strojového videnia a umelej inteligencie, pričom sa venovala najmä schopnosti systémov rozpoznávať objekty bez nutnosti ich predchádzajúcej kategorizácie.
HPC and Artificial Intelligence: Joining Forces for the Future of Technology 15 May - V utorok 14. mája 2025 sme sa zúčastnili podujatia PyData Slovakia & Bratislava Meetup #29, ktoré sa uskutočnilo v Bratislave. Stretnutie dátovej a technologickej komunity sa nieslo v duchu aktuálnych trendov v oblasti umelej inteligencie, s dôrazom na pochopenie fungovania veľkých jazykových modelov (Large Language Models – LLMs), ktoré dnes čoraz výraznejšie ovplyvňujú rôzne oblasti nášho života – od komunikácie, cez vzdelávanie až po riadenie procesov vo firmách a verejnej správe. Hlavným rečníkom večera bol Radovan Kavický, prezident a hlavný dátový vedec v GapData Institute, ktorý svojou prednáškou s názvom "Under the Hood of LLM" pútavo predstavil, čo sa skrýva pod povrchom dnešných pokročilých jazykových modelov.