Periodic Reporting for period 2 - HPC-LEAP (High Performance Computing in Life Sciences, Engineering And Physics)
Período documentado: 2017-04-01 hasta 2019-03-31
Numerical simulation and modelling using advanced computing technologies has evolved into a key research methodology in both academia and industry. The need to solve problems of ever-growing complexity intensifies the quest to attain capable exascale computing. HPC-LEAP responded to the exascale challenges implementing an interdisciplinary strategy for educating the next generation of scientists to address these challenges. It brought together world-leading experts to train young scientists in Europe in mathematical and computational concepts. The mentoring of fellows from multiple institutions in Europe led to a double degree agreed among seven institutions in four EU countries. Six additional academic and four non-academic partners complemented the training offered to the fellows.
The main objectives of the programme were to:
- Provide a rigorous research programme, which is interdisciplinary and at the same time has the required depth, by engaging world-leaders in computational science domains in a collaborative environment.
- Contribute to developing a community of scientists in Europe that uses simulation to bridge experimentation and theory, by designing innovative HPC-driven research projects and training courses.
- Advance the computational capabilities of the different communities by accommodating future HPC architectures requiring higher levels of parallelism and educate scientists to understand the challenges involved in the co-design approach and in managing big data associated with HPC.
- Pioneer innovative HPC-related industries by integrating non-academic partners in the research projects, effectively training young scientists in innovation practices.
The 15 fellows were foreseen to work on interdisciplinary research projects under the close mentorship of two advisors and with the participation of scientists from within the consortium. Computational techniques and algorithms were shared in different application areas, as appropriate. This activity led to the development of original and important scientific results, that have already been published in high-impact scientific journals and presented at several international meetings. All graduating fellows have secured postdoctoral research positions at universities and research institutions in Europe greatly strengthening European research. Through outreach activities the project highlighted to the general public the importance of research and in particular the methodology of computational science in addressing some of the world’s more complex problems. It also highlighted the importance of collaboration across Europe where complementary expertise can be utilized to achieve scientific breakthroughs and generate new knowledge for the benefit of European societies.
The main objectives of the programme were to:
- Provide a rigorous research programme, which is interdisciplinary and at the same time has the required depth, by engaging world-leaders in computational science domains in a collaborative environment.
- Contribute to developing a community of scientists in Europe that uses simulation to bridge experimentation and theory, by designing innovative HPC-driven research projects and training courses.
- Advance the computational capabilities of the different communities by accommodating future HPC architectures requiring higher levels of parallelism and educate scientists to understand the challenges involved in the co-design approach and in managing big data associated with HPC.
- Pioneer innovative HPC-related industries by integrating non-academic partners in the research projects, effectively training young scientists in innovation practices.
The 15 fellows were foreseen to work on interdisciplinary research projects under the close mentorship of two advisors and with the participation of scientists from within the consortium. Computational techniques and algorithms were shared in different application areas, as appropriate. This activity led to the development of original and important scientific results, that have already been published in high-impact scientific journals and presented at several international meetings. All graduating fellows have secured postdoctoral research positions at universities and research institutions in Europe greatly strengthening European research. Through outreach activities the project highlighted to the general public the importance of research and in particular the methodology of computational science in addressing some of the world’s more complex problems. It also highlighted the importance of collaboration across Europe where complementary expertise can be utilized to achieve scientific breakthroughs and generate new knowledge for the benefit of European societies.
The project formally began in April 2015. By October 2015, the fifteen fellowship positions were filled by highly-qualified candidates, the EJD framework was in place and each Fellow formulated a detailed career development plan to ensure the smooth and timely implementation of the programme. Around the same time, the Fellows started receiving their formal training.
To date, HPC-LEAP organised four core three-week workshops offering a well-balanced mixture of general knowledge on HPC architectures and algorithmic design. Moreover, three elective, weeklong workshops took place. Further training was provided depending on the specific needs of the fellows and following a consultation with their academic supervisors. The fellows have also broadened their research experience, by liaising with leading scientists through secondments to partner academic institutions and industrial partners, by receiving further training and having access to state-of-the-art technologies and methodologies.
The projects carried out by the fellows used cutting-edge HPC algorithms and infrastructure to address scientific problems from the Life Sciences, Engineering and Physics thus delivering the objectives of the project. The fellows developed a clear understanding of how to efficiently program a variety of computer architectures and what features to exploit for best performance in research in the thematic areas of the project. Forty eight scientific publications resulted from the research of the fellows and thirty talks were delivered at international meetings.
The fellows also received training in transferable skills and in particular presenting their results. All of the fellows presented their work in conferences and other international meetings and participated in numerous outreach activities advocating HPC and advertising the activities of HPC-LEAP to the general public. This includes representing HPC-LEAP at the European Researchers' Night in 2016-2018, as well as participating in Univ. Open Days.
To date, HPC-LEAP organised four core three-week workshops offering a well-balanced mixture of general knowledge on HPC architectures and algorithmic design. Moreover, three elective, weeklong workshops took place. Further training was provided depending on the specific needs of the fellows and following a consultation with their academic supervisors. The fellows have also broadened their research experience, by liaising with leading scientists through secondments to partner academic institutions and industrial partners, by receiving further training and having access to state-of-the-art technologies and methodologies.
The projects carried out by the fellows used cutting-edge HPC algorithms and infrastructure to address scientific problems from the Life Sciences, Engineering and Physics thus delivering the objectives of the project. The fellows developed a clear understanding of how to efficiently program a variety of computer architectures and what features to exploit for best performance in research in the thematic areas of the project. Forty eight scientific publications resulted from the research of the fellows and thirty talks were delivered at international meetings.
The fellows also received training in transferable skills and in particular presenting their results. All of the fellows presented their work in conferences and other international meetings and participated in numerous outreach activities advocating HPC and advertising the activities of HPC-LEAP to the general public. This includes representing HPC-LEAP at the European Researchers' Night in 2016-2018, as well as participating in Univ. Open Days.
The research performed by the fellows has impacted progress beyond the state of the art in all research areas. Examples are: i) the development of multi-grid algorithms enabling large scale simulations in lattice QCD as well as the computation of key nucleon observables to unprecedented accuracy, impacting our ability to search for new physics beyond the standard model; ii) the development of hybrid Monte Carlo approaches for turbulent flows enabling the detection of rare events; and iii) the development of a code based on density functional theory in a plane wave basis set that is highly scalable and can be used for large multiscale simulations in the study of biological systems.
In addition to the scientific achievements impacting research progress, the program trained a new generation of researchers in using modelling and HPC to solve complex scientific problems.
More specifically, the programme produced graduates who are:
- Versatile with the mathematical concepts;
- Skilled software developers taking advantage of large-scale computing resources;
- Knowledgeable about the best data analysis techniques;
- Confident in presenting their research findings;
- Flexible researchers, able to work on new projects in other disciplines;
- Excellent in their chosen research discipline;
- Well-equipped to embark on successful careers in both academia and industry.
The fact that the fellows were trained in computational aspects and with a background knowledge in a specific scientific field has given them a direct competitive advantage. This is showcased by the fact that almost all graduating fellows have secured postdoctoral positions in prestigious institutions of their choice in Europe. The fact that they remain in Europe shows that there is indeed need for such trained researchers in Europe and simultaneously shows the benefits for European research from supporting projects like HPC-LEAP. Undoubtedly, this will also positively affect the competitiveness of European science and engineering research capabilities, as well as enhance the ability of EU industry to pioneer HPC developments towards exascale computing.
Taking advantage of the momentum of HPC-LEAP the institutions involved developed academic ties and initiatives that go beyond the project. Capitalizing on HPC-LEAP, this extraordinary consortium of scientists re-engaged and extended the collaboration with a second ITN project, The EJD program SimulaTIon in MUltiscaLe physicAl and biological sysTEms (STIMULATE). STIMULATE extends the HPC-LEAP framework and takes a decisive step towards establishing a joint European doctoral degree among three degree awarding institutions.
In addition to the scientific achievements impacting research progress, the program trained a new generation of researchers in using modelling and HPC to solve complex scientific problems.
More specifically, the programme produced graduates who are:
- Versatile with the mathematical concepts;
- Skilled software developers taking advantage of large-scale computing resources;
- Knowledgeable about the best data analysis techniques;
- Confident in presenting their research findings;
- Flexible researchers, able to work on new projects in other disciplines;
- Excellent in their chosen research discipline;
- Well-equipped to embark on successful careers in both academia and industry.
The fact that the fellows were trained in computational aspects and with a background knowledge in a specific scientific field has given them a direct competitive advantage. This is showcased by the fact that almost all graduating fellows have secured postdoctoral positions in prestigious institutions of their choice in Europe. The fact that they remain in Europe shows that there is indeed need for such trained researchers in Europe and simultaneously shows the benefits for European research from supporting projects like HPC-LEAP. Undoubtedly, this will also positively affect the competitiveness of European science and engineering research capabilities, as well as enhance the ability of EU industry to pioneer HPC developments towards exascale computing.
Taking advantage of the momentum of HPC-LEAP the institutions involved developed academic ties and initiatives that go beyond the project. Capitalizing on HPC-LEAP, this extraordinary consortium of scientists re-engaged and extended the collaboration with a second ITN project, The EJD program SimulaTIon in MUltiscaLe physicAl and biological sysTEms (STIMULATE). STIMULATE extends the HPC-LEAP framework and takes a decisive step towards establishing a joint European doctoral degree among three degree awarding institutions.