With the Supercomputing Conference 2014 (SC14) on the horizon, Robert Roe reviews the front runners for the prestigious 2014 Gordon Bell Prize – to be presented at the conference in New Orleans this November.
The Association for Computing Machinery’s (ACM) awards committee has four months left to choose a winner for the prestigious 2014 Gordon Bell Prize. The winner will be presented with the award at the Supercomputing Conference 2014 (SC14) in New Orleans in November.
Five technical papers have been shortlisted and are still in contention for one of the highest honours in high performance computing (HPC). The eventual winner of this prize will have demonstrated an outstanding achievement in HPC that helps solve critical science and engineering problems.
Along with the accolades, the winner of the prize will receive $10,000 financial support, provided by Gordon Bell, a pioneer in high-performance and parallel computing.
With an emphasis on HPC applications in science, engineering, and large-scale data analytics; the Gordon Bell Prize tracks the overall progress in parallel computing. It is an annual award given to an individual or team who has demonstrated an outstanding achievement in one of three areas: peak performance, scalability and time-to-solution, or a special achievement. Submitted papers must follow a structure to elucidate what the innovations were, the performance levels achieved on one or more real-world applications, and what the implications of the approach are for the broader HPC community. Solving an important scientific or engineering problem in HPC is important to demonstrate and justify, but scientific outcomes alone are not sufficient for this prize.
‘The committee had the difficult task of deciding the award’s finalists—five this year—from which the single winner will be selected,’ says chair of ACM’s Gordon Bell prize committee, Adolfy Hoisie and Pacific Northwest National Laboratory’s (PNNL) Director of Advanced Computing, Mathematics, and Data Division. ‘We had a very good set of submissions representing a spectrum of award-relevant areas such as new or specialised architectures, advances in algorithms and applications leading to high performance, or indicating significantly increased performance on large-scale systems through a combination of increased system and application performance.’
This year’s finalists are:
‘Real-time Scalable Cortical Computing at 46 Giga-Synaptic OPS/Watt with ~100× Speedup in Time-to-Solution and ~100,000× Reduction in Energy-to-Solution,’ with research led by Dharmendra S. Modha, IBM Fellow and IBM Chief Scientist – Brain-inspired Computing, and team including members from IBM and Cornell Tech – which was covered in SCW this week;
‘24.77 Pflops on a Gravitational Tree-Code to Simulate the Milky Way Galaxy with 18600 GPUs,’ with their research led by Simon Portegies Zwart and Jeroen Bédorf of the Netherland’s Leiden Observatory and team;
‘Anton 2: Raising the Bar for Performance and Programmability in a Special-Purpose Molecular Dynamics Supercomputer,’ with lead researcher David E. Shaw, of DE Shaw Research, and team;
‘Petascale High Order Dynamic Rupture Earthquake Simulations on Heterogeneous Supercomputers,’ a collaborative research project co-led by Michael Bader (TUM, Germany), Christian Pelties (LMU, Germany) and Alexander Heinecke (Intel, United States); and
‘Physics-based urban earthquake simulation enhanced by 10.7 BlnDOF x 30 K time-step unstructured FE non-linear seismic wave simulation,’ with research led by the University of Tokyo’s Tsuyoshi Ichimura.
The authors of ‘Real-time Scalable Cortical Computing at 46 Giga-Synaptic OPS/Watt with ~100× Speedup in Time-to-Solution and ~100,000× Reduction in Energy-to-Solution’ developed a parallel, event-driven kernel for neurosynaptic computation, called TrueNorth, that targets a broad range of cognitive applications. This kernel is highly efficient with respect to computation, memory, and communication. This entry also demonstrates TrueNorth as a co-designed silicon expression of the kernel. More about the paper can be found here.
‘24.77 Pflops on a Gravitational Tree-Code to Simulate the Milky Way Galaxy with 18600 GPUs,’ looks at the long-term evolution of the Milky Way Galaxy, which is simulated in this submission using 51 billion particles. The simulation achieves impressive performance on the Swiss Piz Daint supercomputer using the N-body gravitational tree-code Bonsai. Read more about the paper here.
The paper ‘Anton 2: Raising the Bar for Performance and Programmability in a Special-Purpose Molecular Dynamics Supercomputer’ introduces a second-generation special-purpose supercomputer for molecular dynamics simulations, Anton 2. The authors’ results indicate significant gains in performance, programmability, and capacity compared to its predecessor, Anton 1, with simulations running up to 180 times faster than on any general-purpose hardware. More information about the submission can be found here.
In ‘Petascale High Order Dynamic Rupture Earthquake Simulations on Heterogeneous Supercomputers,’ the authors present an end-to-end optimisation of the Arbitrary high-order DERivative Discontinuous Galerkin (ADER-DG) software SeisSol. The optimizations target the Intel Xeon Phi coprocessor platforms, achieving impressive earthquake model complexity of complex seismic wave propagation phenomena. More information about the paper can be found on the SC14 website as well as in SCW’s previous coverage ‘What makes SuperMUC so super?’
And finally, the science in the paper ‘Physics-based urban earthquake simulation enhanced by 10.7 BlnDOF x 30 K time-step unstructured FE non-linear seismic wave simulation’ works to improve the reliability of urban earthquake response analyses, using an unstructured 3D finite-element-based wave amplification simulation code, GAMERA running on the K computer. More about the paper can be found here.
One of these papers will be announced the winner of the 2014 Gordon Bell Prize with the runner-up receiving Honourable Mention.
The Gordon Bell awards committee is selected by ACM and comprised of past Gordon Bell winners, as well as leaders in the field.
Last year’s Gordon Bell Prize went to an international team of experts from Germany, Switzerland and the United States: Nikolaus Adams, Costas Bekas, Adam Bertsch, Alessandro Curioni, Scott Futral, Panagiotis Hadjidoukas, Babak Hejazialhosseini, Petros Koumoutsakos, Diego Rossinelli, and Steffen Schmidt for ‘11 PFLOP/s Simulations of Cloud Cavitation Collapse’, which is published in the Proceedings of SC13 and available to read from the ACM Digital Library.