Professor Kenneth Ruud, the Norwegian Chair of PRACE’s
scientific committee, perceives that such tools are now intrinsic, and invaluable, within several frontiers of science. “Nanotechnology, which should form an important part of new medicine, requires the engineering of miniature devices. However,
their development
requires a vast, underlying IT infrastructure. We need to experiment and understand, via modelling, the most promising utilisations of such radical techniques. Additionally,
further simulations
are required to comprehend how such remedies interact with the human body, and could be augmented to meet individuals’ needs.” These, he feels, are beginning to supplant traditional, theoretical
science studies.
Ultimately, they could even supersede controversial practices, such as vivisection. PRACE’s other applications
include climate and
economic modelling, and involvement in the aerospace and automobile industries, alongside the realisation of next-generation entertainments
via cutting-edge
media such as 3D cinema. Convening in Dublin, the PRACE
Council reiterated the importance of these ambitions, and inaugurated an exciting new era in which it hopes to act on its compelling scientific case. “PRACE is now entering a new phase. We’re preparing to develop a sustainable EU infrastructure” comments Rivière. Formerly oriented toward a 2015 horizon, the organisation’s focus now extends beyond, looking forward to 2020. “The council has accepted this new strategic vision, which scrutinises the goals and needs of PRACE in the future” continues the Chair. Especially for complex, long term projects, stability in planning and provision is essential. As Ruud explains, although the organisation has pledged an abiding commitment to HPC (and intends to obtain assurances that will allow researchers to plan some 10 to 20 years ahead), a five year forecast is only prudent, considering the likelihood of dynamic architecture and systems evolution. The next major step after 2020, PRACE anticipates, could be the introduction of ‘exascale’ computing, which would offer a thousandfold improvement on the performance of the first ‘petascale’ unit, which entered service in 2008. The council’s foremost recommendation is the creation of a robust
support structure, which can regulate, yet emancipate access. As the organisation’s Chair shrewdly points
out, measuring HPC
performance in terms of statistics is futile – effectiveness is determined by deployment, and results. “It’s essential for science and industry to increase the number of companies accessing HPC” she says. “We intend to democratise availability,
to boost European
competitiveness across all relevant domains”. To fulfil this, the assembly is seeking an investment of between 800-850 million Euros, which will kickstart the vital interchange of information
www.projectsmagazine.eu.com “PRACE is now
entering a new phase. We’re preparing to
develop a sustainable EU infrastructure”
between clients and computer companies, for their mutual advantage. This element is also important for PRACE’s secondary goal, which indicates that utilisation should be guided by demonstrable research needs, and rationed by users and providers. An optimum environment in which to nurture such an enterprise, it proposes, could be ‘thematic centres’ – facilities which unite various experts, to harness the full potential of HPC.
Most formidable amongst the
challenges facing the multi-national assembly is, perhaps, a lack of qualified human resources – a prerequisite for growth. “Many new areas of science and industry are entering HPC; but there is little precedent, or prior experience in these sectors” observes Ruud. PRACE intends to proactively intervene, by offering training for students, and facilitating the entry of hitherto unsupported disciplines into HPC environments. Rivière
concurs with
Ruud’s assessment, and also identifies the possibility of a detrimental EU ‘brain drain’. Should comparators surge ahead, then “we’ll encounter problems” she admits. “We could lose our talent base, as researchers and engineers with specialist knowledge join rivals overseas. As this phenomenon progresses, competencies and key skills will deplete to the extent that it becomes increasingly hard to replace them.” Software and tool development has
also been highlighted as an area for enhancement. “Developing software which can adapt to scaling – having many computers and processors working on the same problem – is also paramount” says Ruud. “Algorithms used for calculation and analysis,
however, may vary widely between different fields of scientific study, and more compatibility needs to be devised.” Because of the vast amounts of data analysed – particularly in disciplines such as bio-informatics – huge amounts of storage are an inevitable complement to HPC systems. “There needs to be a high performance interface between individual and plural processors, and storage units – as this is becoming something of a bottleneck” contends the academic. Nonetheless, HPC is already making tangible headway within the
EU. A recent project jointly undertaken with the UK Met office granted researchers 145 million core hours, allowing them to advance three years ahead of schedule in their high-resolution climate modelling project. Cenaro, an applied research centre for modelling and numerical simulation, has also been partnered to investigate future jet engines, and assistance was extended to a London-based team examining the effectiveness of organic solar cells, amongst numerous other ongoing investigations. Despite these recent successes, Catherine Rivière issues a cautionary note about complacency – and insists that, to continue to flourish, HPC must follow PRACE’s far-reaching road map. “I think Europe is in a far more significant position than five years ago,” she concludes, “but it must build on the progress it has made”.
★ 97
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132