EDBT 2026 Demo / reviewers in the wild / expert
John A. Gunnels
dblp:31/1305
· DBLP profile ↗
32ranked-venue papers
2as first author
0since 2021 · last 2019
0000-0001-5110-190XORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Systems, architecture and hardware · 26 · 1 first-authorTheory of computation · 5 · 1 first-authorArtificial intelligence and machine learning · 1Security and privacy · 1 · 1 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Computer architecture, parallel and distributed computing, and storage systems
14 papers |
High-performance computing · 76% Parallel and multicore computing · 17% Performance modeling and evaluation · 3% | |
| Artificial intelligence
2 papers |
Efficient and distributed learning · 52% Optimization for machine learning · 42% Speech recognition and synthesis · 6% | |
| Interdisciplinary, comprehensive, and emerging computing
5 papers |
Bioinformatics and computational biology · 38% Computational science and engineering · 37% Medical and health informatics · 25% |
Topics — the 30 heaviest of 42, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
High-performance computing
scientific computing systems |
0.5 | 5 | 2015 | Massively parallel models of the human circulatory system · SC 2015 Beyond homogeneous decomposition: scaling long-range forces on Massively Parallel Systems · SC 2009 Gordon Bell finalists I - Large-scale electronic structure calculations of high-Z metals on the BlueGene/L platform · SC 2006 |
High-performance computing
application porting |
0.4 | 1 | 2019 | Preparation and optimization of a diverse workload for a large-scale heterogeneous system · SC 2019 |
Parallel and multicore computing
programming models |
0.4 | 1 | 2019 | Preparation and optimization of a diverse workload for a large-scale heterogeneous system · SC 2019 |
High-performance computing
performance optimization at scale |
0.3 | 4 | 2012 | Toward real-time modeling of human heart ventricles at cellular resolution: simulation of drug-induced arrhythmias · SC 2012 Gordon Bell finalists I - Large-scale electronic structure calculations of high-Z metals on the BlueGene/L platform · SC 2006 Gordon Bell finalists I - Large scale drop impact analysis of mobile phone using ADVC on Blue Gene/L · SC 2006 |
Parallel and multicore computing › parallel computing › parallel machine learning
data-parallel training |
0.3 | 1 | 2017 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · IEEE Trans. Parallel Distributed Syst. 2017 |
High-performance computing
supercomputing |
0.2 | 3 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 An overview of the BlueGene/L Supercomputer · SC 2002 Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
High-performance computing › scientific computing systems › computational fluid dynamics
blood flow simulation |
0.2 | 1 | 2015 | Massively parallel models of the human circulatory system · SC 2015 |
High-performance computing › scientific computing systems
computational fluid dynamics |
0.2 | 1 | 2015 | Massively parallel models of the human circulatory system · SC 2015 |
High-performance computing › scientific computing systems › computational fluid dynamics
lattice boltzmann method |
0.2 | 1 | 2015 | Massively parallel models of the human circulatory system · SC 2015 |
Machine learning › Efficient and distributed learning › distributed training
data parallel training |
0.2 | 1 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 |
Machine learning › Efficient and distributed learning
distributed training |
0.2 | 1 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 |
Machine learning › Optimization for machine learning › second-order optimization
hessian-free optimization |
0.2 | 1 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 |
Machine learning › Optimization for machine learning
second-order optimization |
0.2 | 1 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 |
High-performance computing › supercomputer architecture
blue gene/q |
0.2 | 1 | 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · SC 2014 |
High-performance computing › scientific computing systems
molecular dynamics simulation |
0.2 | 2 | 2009 | Beyond homogeneous decomposition: scaling long-range forces on Massively Parallel Systems · SC 2009 Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
High-performance computing › large-scale simulation
petascale simulation |
0.1 | 1 | 2012 | Toward real-time modeling of human heart ventricles at cellular resolution: simulation of drug-induced arrhythmias · SC 2012 |
Performance modeling and evaluation
benchmarking |
0.1 | 2 | 2019 | Preparation and optimization of a diverse workload for a large-scale heterogeneous system · SC 2019 Unlocking the Performance of the BlueGene/L Supercomputer · SC 2004 |
High-performance computing › supercomputing
bluegene/l |
0.1 | 3 | 2007 | Unlocking the Performance of the BlueGene/L Supercomputer · SC 2004 An overview of the BlueGene/L Supercomputer · SC 2002 Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
Parallel and multicore computing › parallelization strategies
parallel decomposition |
0.1 | 1 | 2009 | Beyond homogeneous decomposition: scaling long-range forces on Massively Parallel Systems · SC 2009 |
Machine learning › Efficient and distributed learning › distributed training
distributed DNN training |
0.1 | 1 | 2017 | Parallel Deep Neural Network Training for Big Data on Blue Gene/Q · IEEE Trans. Parallel Distributed Syst. 2017 |
Distributed systems
fault tolerance |
0.1 | 1 | 2007 | Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
High-performance computing
parallel i/o |
0.1 | 1 | 2007 | Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
High-performance computing
scientific computing |
0.1 | 1 | 2007 | Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instability · SC 2007 |
High-performance computing
finite element method |
0.1 | 1 | 2006 | Gordon Bell finalists I - Large scale drop impact analysis of mobile phone using ADVC on Blue Gene/L · SC 2006 |
High-performance computing
structural analysis |
0.1 | 1 | 2006 | Gordon Bell finalists I - Large scale drop impact analysis of mobile phone using ADVC on Blue Gene/L · SC 2006 |
Integrated circuit design › digital circuit design › arithmetic circuit design
floating-point unit |
0.0 | 1 | 2004 | Unlocking the Performance of the BlueGene/L Supercomputer · SC 2004 |
High-performance computing
supercomputer architecture |
0.0 | 1 | 2004 | Unlocking the Performance of the BlueGene/L Supercomputer · SC 2004 |
Integrated circuit design
system-on-chip |
0.0 | 1 | 2002 | An overview of the BlueGene/L Supercomputer · SC 2002 |
Computational science and engineering › computational physics
plasma physics simulation |
0.0 | 1 | 2009 | Beyond homogeneous decomposition: scaling long-range forces on Massively Parallel Systems · SC 2009 |
GPUs and heterogeneous computing › heterogeneous supercomputing
accelerator-based supercomputing |
0.0 | 1 | 2009 | Petascale computing with accelerators · PPoPP 2009 |
Methods — techniques the papers use, named apart from their topics
hessian-free optimization · 1.0data parallelism · 1.0second-order optimization · 0.6multiscale coupling · 0.4load balancing · 0.4parallel scaling · 0.3cellular-resolution simulation · 0.3heterogeneous decomposition · 0.2memory bandwidth optimization · 0.1long-range force computation · 0.1host-accelerator scheduling · 0.1qbox · 0.1hardware performance counters · 0.1
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2019 | Preparation and optimization of a diverse workload for a large-scale heterogeneous systemabstractProductivity from day one on supercomputers that leverage new technologies requires significant preparation. An institution that procures a novel system architecture often lacks sufficient institutional knowledge and skills to prepare for it. Thus, the "Center of Excellence" (CoE) concept has emerged to prepare for systems such as Summit and Sierra, currently the top two systems in the Top 500. This paper documents CoE experiences that prepared a workload of diverse applications and math libraries for a heterogeneous system. We describe our approach to this preparation, including our management and execution strategies, and detail our experiences with and reasons for using different programming approaches. Our early science and performance results show that the project enabled significant early seismic science with up to a l4X throughput increase over Cori. In addition to our successes, we discuss our challenges and failures so others may benefit from our experience. Ian Karlin, Yoonho Park, Bronis R. de Supinski, Bert Still, D. A. Beckingsale, Robert Blake, Tong Chen 0001, Guojing Cong, Carlos H. A. Costa, Johann Dahm, Giacomo Domeniconi, Thomas Epperly, Aaron Fisher, Sara Kokkila Schumacher, Steve H. Langer, Hai Le, Naoya Maruyama, Xinyu Que, David F. Richards, Björn Sjögreen, Jonathan Wong, Carol S. Woodward, Ulrike Meier Yang, Bob Anderson, David Appelhans, Levi Barnes, Peter D. Barnes Jr., Sorin Bastea, David Böhme, Jamie A. Bramwell, James M. Brase, José R. Brunheroto, Barry Chen, Charway R. Cooper, Tony Degroot, Robert D. Falgout, Todd Gamblin, David J. Gardner, James N. Glosli, John A. Gunnels, Max P. Katz, Tzanio V. Kolev, I-Feng W. Kuo, Matthew P. LeGendre, Pei-Hung Lin, Shelby Lockhart, Kathleen McCandless, Claudia Misale, Jaime H. Moreno, Rob Neely, Jarom Nelson, Rao Nimmakayala, Kathryn M. O'Brien, Kevin O'Brien, Ramesh Pankajakshan, Roger A. Pearce, Slaven Peles, Phil Regier, Steven C. Rennich, Martin Schulz 0001, Howard Scott, James C. Sexton, Kathleen Shoga, Shiv Sundram, Guillaume Thomas-Collignon, Brian Van Essen, Alexey Voronin, Bob Walkup, Chris Ward, Hui-Fang Wen, Daniel A. White, Christopher Young, Cyril Zeller, Edward Zywicz |
SC | 43 |
| 2017 | Massively parallel first-principles simulation of electron dynamics in materials
Erik W. Draeger, Xavier Andrade, John A. Gunnels, Abhinav Bhatele, André Schleife, Alfredo A. Correa |
J. Parallel Distributed Comput. | 3 |
| 2017 | Parallel Deep Neural Network Training for Big Data on Blue Gene/QabstractDeep Neural Networks (DNNs) have recently been shown to significantly outperform existing machine learning techniques in several pattern recognition tasks. DNNs are the state-of-the-art models used in image recognition, object detection, classification and tracking, and speech and language processing applications. The biggest drawback to DNNs has been the enormous cost in computation and time taken to train the parameters of the networks-often a tenfold increase relative to conventional technologies. Such training time costs can be mitigated by the application of parallel computing algorithms and architectures. However, these algorithms often run into difficulties because of the cost of inter-processor communication bottlenecks. In this paper, we describe how to enable Parallel Deep Neural Network Training on the IBM Blue Gene/Q (BG/Q) computer system. Specifically, we explore DNN training using the data-parallel Hessian-free 2nd order optimization algorithm. Such an algorithm is particularly well-suited to parallelization across a large set of loosely coupled processors. BG/Q, with its excellent inter-processor communication characteristics, is an ideal match for this type of algorithm. The paper discusses how issues regarding programming model and data-dependent imbalances are addressed. Results on large-scale speech tasks show that the performance on BG/Q scales linearly up to 4,096 processes with no loss in accuracy. This allows us to train neural networks using billions of training examples in a few hours. I-Hsin Chung, Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, John A. Gunnels, Vernon Austel, Upendra V. Chaudhari, Brian Kingsbury |
IEEE Trans. Parallel Distributed Syst. | 5 |
| 2016 | Massively Parallel First-Principles Simulation of Electron Dynamics in MaterialsabstractWe present a highly scalable, parallel implementation of first-principles electron dynamics coupled with molecular dynamics (MD). By using optimized kernels, network topology aware communication, and by fully distributing all terms in the time-dependent Kohn-Sham equation, we demonstrate unprecedented time to solution for disordered aluminum systems of 2,000 atoms (22,000 electrons) and 5,400 atoms (59,400 electrons), with wall clock time as low as 7.5 seconds per MD time step. Despite a significant amount of non-local communication required in every iteration, we achieved excellent strong scaling and sustained performance on the Sequoia Blue Gene/Q supercomputer at LLNL. We obtained up to 59% of the theoretical sustained peak performance on 16,384 nodes and performance of 8.75 Petaflop/s (43% of theoretical peak) on the full 98,304 node machine (1,572,864 cores). Scalable explicit electron dynamics allows for the study of phenomena beyond the reach of standard first principles MD, in particular, materials subject to strong or rapid perturbations, such as pulsed electromagnetic radiation, particle irradiation, or strong electric currents. Erik W. Draeger, Xavier Andrade, John A. Gunnels, Abhinav Bhatele, André Schleife, Alfredo A. Correa |
IPDPS | 3 |
| 2016 | An Early Performance Study of Large-Scale POWER8 SMP SystemsabstractIn this paper we evaluate the performance of a large-scale POWER8 symmetric multiprocessor (SMP) system with eight processors. We focus our attention on cache and memory subsystems, analyzing the characteristics that have a direct impact on high-performance computing and analytics applications. We provide insight into the relevant characteristics of the POWER8 processor using a set of micro-benchmarks. We also analyze the POWER8 SMP at the system level using the well-known roofline model. Using the knowledge gained from these micro-benchmarks, we optimize three applications and use them to assess the capabilities of the POWER8 system. The results show that the POWER8 - based SMP system is capable of delivering high performance for a wide range of applications and kernels. Daniele Buono, Fabio Checconi, Jee W. Choi, Xinyu Que, Fabrizio Petrini, John A. Gunnels, Jeffrey Stuecheli |
IPDPS | 7 |
| 2016 | The BLIS Framework: Experiments in PortabilityabstractBLIS is a new software framework for instantiating high-performance BLAS-like dense linear algebra libraries. We demonstrate how BLIS acts as a productivity multiplier by using it to implement the level-3 BLAS on a variety of current architectures. The systems for which we demonstrate the framework include state-of-the-art general-purpose, low-power, and many-core architectures. We show, with very little effort, how the BLIS framework yields sequential and parallel implementations that are competitive with the performance of ATLAS, OpenBLAS (an effort to maintain and extend the GotoBLAS), and commercial vendor implementations such as AMD’s ACML, IBM’s ESSL, and Intel’s MKL libraries. Although most of this article focuses on single-core implementation, we also provide compelling results that suggest the framework’s leverage extends to the multithreaded domain. Field G. Van Zee, Tyler M. Smith, Bryan Marker, Tze Meng Low, Robert A. van de Geijn, Francisco D. Igual, Mikhail Smelyanskiy, Xianyi Zhang, Michael Kistler, Vernon Austel, John A. Gunnels, Lee Killough |
ACM Trans. Math. Softw. | 11 |
| 2015 | Scalable Community Detection with the Louvain AlgorithmabstractIn this paper we present and evaluate a parallel community detection algorithm derived from the state-of-the-art Louvain modularity maximization method. Our algorithm adopts a novel graph mapping and data representation, and relies on can efficient communication runtime, specifically designed for fine-grained applications executed on large-scale supercomputers. We have been able to parallelize graphs with up to 138 billion edges on 8, 192 Blue Gene/Q nodes and 1, 024 P7-IH nodes. Leveraging the convergence properties of our algorithm and the efficient implementation, we can analyze communities of large scale graphs in just a few seconds. To the best of our knowledge, this is the first parallel implementation of the Louvain algorithm that scales to these large data and processor configurations. Xinyu Que, Fabio Checconi, Fabrizio Petrini, John A. Gunnels |
IPDPS | 4 |
| 2015 | Massively parallel models of the human circulatory systemabstractThe potential impact of blood flow simulations on the diagnosis and treatment of patients suffering from vascular disease is tremendous. Empowering models of the full arterial tree can provide insight into diseases such as arterial hypertension and enables the study of the influence of local factors on global hemodynamics. We present a new, highly scalable implementation of the lattice Boltzmann method which addresses key challenges such as multiscale coupling, limited memory capacity and bandwidth, and robust load balancing in complex geometries. We demonstrate the strong scaling of a three-dimensional, high-resolution simulation of hemodynamics in the systemic arterial tree on 1,572,864 cores of Blue Gene/Q. Faster calculation of flow in full arterial networks enables unprecedented risk stratification on a perpatient basis. In pursuit of this goal, we have introduced computational advances that significantly reduce time-to-solution for biofluidic simulations. Amanda Randles, Erik W. Draeger, Tomas Oppelstrup, Liam Krauss, John A. Gunnels |
SC | 5 |
| 2014 | Parallel deep neural network training for LVCSR tasks using blue gene/QabstractWhile Deep Neural Networks (DNNs) have achieved tremendous success for LVCSR tasks, training these networks is slow. To date, the most common approach to train DNNs is via stochastic gradient descent (SGD), serially on a single GPU machine. Serial training, coupled with the large number of training parameters and speech data set sizes, makes DNN training very slow for LVCSR tasks. While 2nd order, data-parallel methods have also been explored, these methods are not always faster on CPU clusters due to the large communication cost between processors. In this work, we explore using a specialized hardware/software approach, utilizing a Blue Gene/Q (BG/Q) system, which has thousands of processors and excellent interprocessor communication. We explore using the 2nd order Hessian-free (HF) algorithm for DNN training with BG/Q, for both cross-entropy and sequence training of DNNs. Results on three LVCSR tasks indicate that using HF with BG/Q offers up to an 11x speedup, as well as an improved word error rate (WER), compared to SGD on a GPU. Tara N. Sainath, I-Hsin Chung, Bhuvana Ramabhadran, Michael Picheny, John A. Gunnels, Brian Kingsbury, George Saon, Vernon Austel, Upendra V. Chaudhari |
INTERSPEECH | 5 |
| 2014 | Parallel Deep Neural Network Training for Big Data on Blue Gene/QabstractDeep Neural Networks (DNNs) have recently been shown to significantly outperform existing machine learning techniques in several pattern recognition tasks. DNNs are the state-of-the-art models used in image recognition, object detection, classification and tracking, and speech and language processing applications. The biggest drawback to DNNs has been the enormous cost in computation and time taken to train the parameters of the networks - often a tenfold increase relative to conventional technologies. Such training time costs can be mitigated by the application of parallel computing algorithms and architectures. However, these algorithms often run into difficulties because of the cost of inter-processor communication bottlenecks. In this paper, we describe how to enable Parallel Deep Neural Network Training on the IBM Blue Gene/Q (BG/Q) computer system. Specifically, we explore DNN training using the data parallel Hessian-free 2nd order optimization algorithm. Such an algorithm is particularly well-suited to parallelization across a large set of loosely coupled processors. BG/Q, with its excellent inter-processor communication characteristics, is an ideal match for this type of algorithm. The paper discusses how issues regarding programming model and data-dependent imbalances are addressed. Results on large-scale speech tasks show that the performance on BG/Q scales linearly up to 4096 processes with no loss in accuracy. This allows us to train neural networks using billions of training examples in a few hours. I-Hsin Chung, Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, John A. Gunnels, Vernon Austel, Upendra V. Chaudhari, Brian Kingsbury |
SC | 5 |
| 2013 | Deriving dense linear algebra librariesabstractAbstract Starting in the late 1960s computer scientists including Dijkstra and Hoare advocated goal-oriented programming and the formal derivation of algorithms. The chief impediment to realizing this for loop-based programs was that a priori determination of loop-invariants, a prerequisite for developing loops, was a task too complex for any but the simplest of operations. Around 2000, these techniques were for the first time successfully applied to the domain of high-performance dense linear algebra libraries. This has led to a multitude of papers (mostly published in the ACM Transactions for Mathematical Software), a system for the mechanical derivation of algorithms, and a high-performance linear algebra library, , that includes more than a thousand variants of algorithms for more than a hundred linear algebra operations. To our knowledge, this success story has unfolded with limited awareness on the part the formal methods community. This paper reports on ten years of experience and is meant to raise that awareness. Paolo Bientinesi, John A. Gunnels, Margaret E. Myers, Enrique S. Quintana-Ortí, Tyler Rhodes, Robert A. van de Geijn, Field G. Van Zee |
Formal Aspects Comput. | 2 |
| 2012 | Toward real-time modeling of human heart ventricles at cellular resolution: simulation of drug-induced arrhythmiasabstractWe have developed a highly efficient and scalable cardiac electrophysiology simulation capability that supports groundbreaking resolution and detail to elucidate the mechanisms of sudden cardiac death from arrhythmia. We can simulate thousands of heartbeats at a resolution of 0.1 mm, comparable to the size of cardiac cells, thereby enabling scientific inquiry not previously possible. Based on scaling results from the partially deployed Sequoia IBM Blue Gene/Q machine at Lawrence Livermore National Laboratory and planned optimizations, we estimate that by SC12 we will simulate 8 -- 10 heartbeats per minute -- a time-to-solution 400 -- 500 times faster than the state-of-the-art. Performance between 8 and 11 PFlop/s on the full 1,572,864 cores is anticipated, representing 40 -- 55 percent of peak. The power of the model is demonstrated by illuminating the subtle arrhythmogenic mechanisms of anti-arrhythmic drugs that paradoxically increase arrhythmias in some patient populations. Arthur A. Mirin, David F. Richards, James N. Glosli, Erik W. Draeger, Bor Chan, Jean-Luc Fattebert, William D. Krauss, Tomas Oppelstrup, John Jeremy Rice, John A. Gunnels, Viatcheslav Gurev, Changhoan Kim, John Magerlein, Matthias Reumann, Hui-Fang Wen |
SC | 10 |
| 2009 | MPI collective communications on the blue gene/p supercomputer: algorithms and optimizationsabstractThe IBM Blue Gene/P (BG/P) system is a massively parallel supercomputer succeeding BG/L, and it is based on orders of magnitude in system size and significant power consumption efficiency. BG/P comes with many enhancements to the machine design and new architectural features at the hardware and software levels. In this work, we demonstrate techniques to leverage the architectural features of BG/P to deliver high performance MPI collective communication primitives. Ahmad Faraj, Sameer Kumar 0001, Brian E. Smith, Amith R. Mamidala, John A. Gunnels, Philip Heidelberger |
ICS | 5 |
| 2009 | Petascale computing with acceleratorsabstractA trend is developing in high performance computing in which commodity processors are coupled to various types of computational accelerators. Such systems are commonly called hybrid systems. In this paper, we describe our experience developing an implementation of the Linpack benchmark for a petascale hybrid system, the LANL Roadrunner cluster built by IBM for Los Alamos National Laboratory. This system combines traditional x86-64 host processors with IBM PowerXCell™ 8i1 accelerator processors. The implementation of Linpack we developed was the first to achieve a performance result in excess of 1.0 PFLOPS, and made Roadrunner the #1 system on the Top500 list in June 2008. We describe the design and implementation of hybrid Linpack, including the special optimizations we developed for this hybrid architecture. We then present actual results for single node and multi-node executions. From this work, we conclude that it is possible to achieve high performance for certain applications on hybrid architectures when careful attention is given to efficient use of memory bandwidth, scheduling of data movement between the host and accelerator memories, and proper distribution of work between the host and accelerator processors. Michael Kistler, John A. Gunnels, Daniel A. Brokenshire, Brad Benton |
PPoPP | 2 |
| 2009 | Beyond homogeneous decomposition: scaling long-range forces on Massively Parallel SystemsabstractWith supercomputers anticipated to expand from thousands to millions of cores, one of the challenges facing scientists is how to effectively utilize this ever-increasing number. We report here an approach that creates a heterogeneous decomposition by partitioning effort according to the scaling properties of the component algorithms. We demonstrate our strategy by developing a capability to model hot dense plasma. We have performed benchmark calculations ranging from millions to billions of charged particles, including a 2.8 billion particle simulation that achieved 259.9 TFlop/s (26% of peak performance) on the 294,912 cpu JUGENE computer at the Jülich Supercomputing Centre in Germany. With this unprecedented simulation capability we have begun an investigation of plasma fusion physics under conditions where both theory and experiment are lacking--in the strongly-coupled regime as the plasma begins to burn. David F. Richards, James N. Glosli, Bor Chan, Milo R. Dorr, Erik W. Draeger, Jean-Luc Fattebert, William D. Krauss, Thomas E. Spelce, Frederick H. Streitz, Michael P. Surh, John A. Gunnels |
SC | 11 |
| 2008 | Optimization of Fast Fourier Transforms on the Blue Gene/L Supercomputer
Yogish Sabharwal, Saurabh Kumar Garg 0001, Rahul Garg 0001, John A. Gunnels, Ramendra K. Sahoo |
HiPC | 4 |
| 2008 | Optimization of BLAS on the Cell Processor
Vaibhav Saxena, Prashant Agrawal, Yogish Sabharwal, Vijay K. Garg, Vimitha A. Kuruvilla, John A. Gunnels |
HiPC | 6 |
| 2007 | Extending stability beyond CPU millennium: a micron-scale atomistic simulation of Kelvin-Helmholtz instabilityabstractWe report the computational advances that have enabled the first micron-scale simulation of a Kelvin-Helmholtz (KH) instability using molecular dynamics (MD). The advances are in three key areas for massively parallel computation such as on BlueGene/L (BG/L): fault tolerance, application kernel optimization, and highly efficient parallel I/O. In particular, we have developed novel capabilities for handling hardware parity errors and improving the speed of interatomic force calculations, while achieving near optimal I/O speeds on BG/L, allowing us to achieve excellent scalability and improve overall application performance. As a result we have successfully conducted a 2-billion atom KH simulation amounting to 2.8 CPU-millennia of run time, including a single, continuous simulation run in excess of 1.5 CPU-millennia. We have also conducted 9-billion and 62.5-billion atom KH simulations. The current optimized ddcMD code is benchmarked at 115.1 TFlop/s in our scaling study and 103.9 TFlop/s in a sustained science run, with additional improvements ongoing. These improvements enabled us to run the first MD simulations of micron-scale systems developing the KH instability. James N. Glosli, David F. Richards, K. J. Caspersen, R. E. Rudd, John A. Gunnels, Frederick H. Streitz |
SC | 5 |
| 2007 | An experimental comparison of cache-oblivious and cache-conscious programsabstractCache-oblivious algorithms have been advanced as a way of circumventing some of the difficulties of optimizing applications to take advantage of the memory hierarchy of modern microprocessors. These algorithms are based on the divide-and-conquer paradigm -- each division step creates sub-problems of smaller size, and when the working set of a sub-problem fits in some level of the memory hierarchy, the computations in that sub-problem can be executed without suffering capacity misses at that level. In this way, divide-and-conquer algorithms adapt automatically to all levels of the memory hierarchy; in fact, for problems like matrix multiplication, matrix transpose, and FFT, these recursive algorithms are optimal to within constant factors for some theoretical models of the memory hierarchy. Kamen Yotov, Tom Roeder, Keshav Pingali, John A. Gunnels, Fred G. Gustavson |
SPAA | 4 |
| 2006 | Gordon Bell finalists I - Large scale drop impact analysis of mobile phone using ADVC on Blue Gene/LabstractExisting commercial finite element analysis (FEA) codes do not exhibit the performance necessary for large scale analysis on parallel computer systems. In this paper, we demonstrate the performance characteristics of a commercial parallel structural analysis code, ADVC, on Blue Gene/L (BG/L). The numerical algorithm of ADVC is described, tuned, and optimized on BG/L, and then a large scale drop impact analysis of a mobile phone is performed. The model of the mobile phone is a nearly-full assembly that includes inner structures. The size of the model we have analyzed has 47 million nodal points and 142 million DOFs. This does not seem exceptionally large, but the dynamic impact analysis of a product model, with the contact condition on the entire surface of the outer case under this size, cannot be handled by other CAE systems. Our analysis is an unprecedented attempt in the electronics industry. It took only half a day, 12.1 hours, for the analysis of about 2.4 milliseconds. The floating point operation performance obtained has been 538 GFLOPS on 4096 node of BG/L. Hiroshi Akiba, Tomonobu Ohyama, Yoshinoir Shibata, Kiyoshi Yuyama, Yoshikazu Katai, Ryuichi Takeuchi, Takeshi Hoshino, Shinobu Yoshimura, Hirohisa Noguchi, Manish Gupta 0002, John A. Gunnels, Vernon Austel, Yogish Sabharwal, Rahul Garg 0001, Shoji Kato, Takashi Kawakami, Satoru Todokoro, Junko Ikeda |
SC | 11 |
| 2006 | Gordon Bell finalists I - Large-scale electronic structure calculations of high-Z metals on the BlueGene/L platformabstractFirst-principles simulations of high-Z metallic systems using the Qbox code on the BlueGene/L supercomputer demonstrate unprecedented performance and scaling for a quantum simulation code. Specifically designed to take advantage of massively-parallel systems like BlueGene/L, Qbox demonstrates excellent parallel efficiency and peak performance. A sustained peak performance of 207.3 TFlop/s was measured on 65,536 nodes, corresponding to 56.5% of the theoretical full machine peak using all 128k CPUs. François Gygi, Erik W. Draeger, Martin Schulz 0001, Bronis R. de Supinski, John A. Gunnels, Vernon Austel, James C. Sexton, Franz Franchetti, Stefan Kral, Christoph W. Ueberhuber, Juergen Lorenz |
SC | 5 |
| 2005 | Early Experience with Scientific Applications on the Blue Gene/L Supercomputer
Gheorghe Almási 0001, Gyan Bhanot, Dong Chen 0005, Maria Eleftheriou, Blake G. Fitch, Alan Gara, Robert S. Germain, John A. Gunnels, Manish Gupta 0002, Philip Heidelberger, Michael Pitman, Aleksandr Rayshubskiy, James C. Sexton, Frank Suits, Pavlos Vranas, Robert Walkup, T. J. Christopher Ward, Yuriy Zhestkov, Alessandro Curioni, Wanda Andreoni, Charles Archer, José E. Moreira, Richard Loft, Henry M. Tufo, Theron Voran, Katherine Riley |
Euro-Par | 8 |
| 2005 | Large-Scale First-Principles Molecular Dynamics simulations on the BlueGene/L Platform using the Qbox codeabstractWe demonstrate that the Qbox code supports unprecedented large-scale First-Principles Molecular Dynamics (FPMD) applications on the BlueGene/L supercomputer. Qbox is an FPMD implementation specifically designed for large-scale parallel platforms such as BlueGene/L. Strong scaling tests for a Materials Science application show an 86% scaling efficiency between 1024 and 32,768 CPUs. Measurements of performance by means of hardware counters show that 36% of the peak FPU performance can be attained. François Gygi, Robert K. Yates, Juergen Lorenz, Erik W. Draeger, Franz Franchetti, Christoph W. Ueberhuber, Bronis R. de Supinski, Stefan Kral, John A. Gunnels, James C. Sexton |
SC | 9 |
| 2005 | A fully portable high performance minimal storage hybrid format cholesky algorithmabstractWe consider the efficient implementation of the Cholesky solution of symmetric positive-definite dense linear systems of equations using packed storage. We take the same starting point as that of LINPACK and LAPACK, with the upper (or lower) triangular part of the matrix stored by columns. Following LINPACK and LAPACK, we overwrite the given matrix by its Cholesky factor. We consider the use of a hybrid format in which blocks of the matrices are held contiguously and compare this to the present LAPACK code. Code based on this format has the storage advantages of the present code but substantially outperforms it. Furthermore, it compares favorably to using conventional full format (LAPACK) and using the recursive format of Andersen et al. [2001]. Bjarne Stig Andersen, John A. Gunnels, Fred G. Gustavson, John K. Reid, Jerzy Wasniewski |
ACM Trans. Math. Softw. | 2 |
| 2005 | The science of deriving dense linear algebra algorithmsabstractIn this article we present a systematic approach to the derivation of families of high-performance algorithms for a large set of frequently encountered dense linear algebra operations. As part of the derivation a constructive proof of the correctness of the algorithm is generated. The article is structured so that it can be used as a tutorial for novices. However, the method has been shown to yield new high-performance algorithms for well-studied linear algebra operations and should also be of interest to those who wish to produce best-in-class high-performance codes. Paolo Bientinesi, John A. Gunnels, Margaret E. Myers, Enrique S. Quintana-Ortí, Robert A. van de Geijn |
ACM Trans. Math. Softw. | 2 |
| 2004 | Unlocking the Performance of the BlueGene/L SupercomputerabstractThe BlueGene/L supercomputer is expected to deliver new levels of application performance by providing a combination of good single-node computational performance and high scalability. To achieve good single-node performance, the BlueGene/L design includes a special dual floating-point unit on each processor and the ability to use two processors per node. BlueGene/L also includes both a torus and a tree network to achieve high scalability. We demonstrate how benchmarks and applications can take advantage of these architectural features to get the most out of BlueGene/L. Gheorghe Almási 0001, Siddhartha Chatterjee, Alan Gara, John A. Gunnels, Manish Gupta 0002, Amy Henning, José E. Moreira, Robert Walkup |
SC | 4 |
| 2002 | An overview of the BlueGene/L SupercomputerabstractThis paper gives an overview of the BlueGene/L Supercomputer. This is a jointly funded research partnership between IBM and the Lawrence Livermore National Laboratory as part of the United States Department of Energy ASCI Advanced Architecture Research Program. Application performance and scaling studies have recently been initiated with partners at a number of academic and government institutions,including the San Diego Supercomputer Center and the California Institute of Technology. This massively parallel system of 65,536 nodes is based on a new architecture that exploits system-on-a-chip technology to deliver target peak processing power of 360 teraFLOPS (trillion floating-point operations per second). The machine is scheduled to be operational in the 2004-2005 time frame, at price/performance and power consumption/performance targets unobtainable with conventional architectures. Narasimha R. Adiga, Gheorghe Almási 0001, George S. Almási, Yariv Aridor, Rajkishore Barik, Daniel K. Beece, Ralph Bellofatto, Gyan Bhanot, Randy Bickford, Matthias A. Blumrich, Arthur A. Bright, José R. Brunheroto, Calin Cascaval, José G. Castaños, Waiman Chan, Luis Ceze, Paul Coteus, Siddhartha Chatterjee, Dong Chen 0005, George L.-T. Chiu, Thomas M. Cipolla, Paul Crumley, K. M. Desai, Alina Deutsch, Tamar Domany, Marc Boris Dombrowa, Wilm E. Donath, Maria Eleftheriou, C. Christopher Erway, J. Esch, Blake G. Fitch, Joseph Gagliano, Alan Gara, Rahul Garg 0001, Robert S. Germain, Mark Giampapa, Balaji Gopalsamy, John A. Gunnels, Manish Gupta 0002, Fred G. Gustavson, Shawn Hall, Ruud A. Haring, David F. Heidel, Philip Heidelberger, Lorraine M. Herger, Dirk Hoenicke, R. D. Jackson, T. Jamal-Eddine, Gerard V. Kopcsay, Elie Krevat, Manish P. Kurhekar, Alphonso P. Lanzetta, Derek Lieber, L. K. Liu, M. Lu, Mark P. Mendell, A. Misra, Yosef Moatti, Lawrence S. Mok, José E. Moreira, Ben J. Nathanson, Matthew Newton, Martin Ohmacht, Adam J. Oliner, Vinayaka Pandit, R. B. Pudota, Rick A. Rand, Richard D. Regan, Bradley Rubin, Albert E. Ruehli, Silvius Vasile Rus, Ramendra K. Sahoo, Alda Sanomiya, Eugen Schenfeld, M. Sharma, Edi Shmueli, Sarabjeet Singh, Peilin Song, Vijay Srinivasan, Burkhard D. Steinmacher-Burow, Karin Strauss, Christopher W. Surovic, Richard A. Swetz, Todd Takken, R. Brett Tremaine, Mickey Tsao, Arun R. Umamaheshwaran, P. Verma, Pavlos Vranas, T. J. Christopher Ward, Michael E. Wazlowski, W. Barrett, C. Engel, B. Drehmel, B. Hilgart, D. Hill, F. Kasemkhani, David J. Krolak, Chun-Tao Li 0001, Thomas A. Liebsch, James A. Marcella, A. Muff, A. Okomo, M. Rouse, A. Schram, M. Tubbs, G. Ulsh, Charles D. Wait, J. Wittrup, Myung Bae, Kenneth A. Dockser, Lynn Kissel, Mark K. Seager, Jeffrey S. Vetter, K. Yates |
SC | 38 |
| 2001 | Fault-Tolerant High-Performance Matrix Multiplication: Theory and PracticeabstractWe extend the theory and practice regarding algorithmic fault-tolerant matrix-matrix multiplication, C=AB, in a number of ways. First, we propose low-overhead methods for detecting errors introduced not only in C but also in A and/or B. Second, we show that, theoretically, these methods will detect all errors as long as only one entry, is corrupted. Third we propose a low-overhead roll-back approach to correct errors once detected. Finally, we give a high-performance implementation of matrix-matrix multiplication that incorporates these error detection and correction methods. Empirical results demonstrate that these methods work well in practice while imposing an acceptable level of overhead relative to high-performance implementations without fault-tolerance. John A. Gunnels, Robert A. van de Geijn, Daniel S. Katz, Enrique S. Quintana-Ortí |
DSN | 1 |
| 2001 | FLAME: Formal Linear Algebra Methods EnvironmentabstractSince the advent of high-performance distributed-memory parallel computing, the need for intelligible code has become ever greater. The development and maintenance of libraries for these architectures is simply too complex to be amenable to conventional approaches to implementation. Attempts to employ traditional methodology have led, in our opinion, to the production of an abundance of anfractuous code that is difficult to maintain and almost impossible to upgrade.Having struggled with these issues for more than a decade, we have concluded that a solution is to apply a technique from theoretical computer science, formal derivation, to the development of high-performance linear algebra libraries. We think the resulting approach results in aesthetically pleasing, coherent code that greatly facilitates intelligent modularity and high performance while enhancing confidence in its correctness. Since the technique is language-independent, it lends itself equally well to a wide spectrum of programming languages (and paradigms) ranging from C and Fortran to C++ and Java. In this paper, we illustrate our observations by looking at the Formal Linear Algebra Methods Environment (FLAME), a framework that facilitates the derivation and implementation of linear algebra algorithms on sequential architectures. This environment demonstrates that lessons learned in the distributed-memory world can guide us toward better approaches even in the sequential world.We present performance experiments on the Intel (R) Pentium (R) III processor that demonstrate that high performance can be attained by coding at a high level of abstraction. John A. Gunnels, Fred G. Gustavson, Greg Henry, Robert A. van de Geijn |
ACM Trans. Math. Softw. | 1 |
| 1998 | PLAPACK: High Performance through High-Level AbstractionabstractCoding parallel algorithms is generally regarded as a formidable task. To make this task manageable in the arena of linear algebra algorithms, we have developed the Parallel Linear Algebra Package (PLAPACK), an infrastructure for coding such algorithms at a high level of abstraction. It is often believed that by raising the level of abstraction in this fashion, performance is sacrificed. Throughout, we have maintained that indeed there is a performance penalty, but that by coding at a higher level of abstraction, more sophisticated algorithms can be implemented, which allows high levels of performance to be regained. In this paper, we show this to be the case for the parallel solver package implemented using PLAPACK, which includes Cholesky, LU, and QR factorization based solvers for symmetric positive definite, general, and overdetermined systems of equations, respectively. Contributions of this paper include new parallel algorithms for these factorizations and performance results on a Cray T3E-600. Gregory S. Baker, John A. Gunnels, Greg Morrow, Beatrice Riviere, Robert A. van de Geijn |
ICPP | 2 |
| 1997 | PLAPACK Parallel Linear Algebra Package Design OverviewabstractOver the past twenty years, dense linear algebra libraries have gone through three generations of public domain general purpose packages. In the seventies, the first generation of packages were EISPACK and LINPACK, which implemented a broad spectrum of algorithms for solving dense linear eigenproblems and dense linear systems. In the late eighties, the second generation package called LAPACK was developed. This package attains high performance in a portable fashion while also improving upon the functionality and robustness of LINPACK and EISPACK. Finally, since the early nineties, a third generation package which ports LAPACK to distributed memory networks of computers has been underway as part of the ScaLAPACK project.PLAPACK is a maturing fourth generation package which uses a more application-centric view of vector and matrix distribution, Physically Based Matrix Distribution. It also uses an "MPI-like" programming interface that hides distribution and indexing details in opaque objects, provides a natural layering in the library, and provides a straight-forward application interface. In this paper, we give an overview of the design of PLAPACK. Phillip Alpatov, Gregory S. Baker, H. Carter Edwards, John A. Gunnels, Greg Morrow, James Overfelt, Robert A. van de Geijn |
SC | 4 |
| 1997 | Parallel implementation of BLAS: general techniques for Level 3 BLASabstractIn this paper, we present straightforward techniques for a highly efficient, scalable implementation of common matrix–matrix operations generally known as the Level 3 Basic Linear Algebra Subprograms (BLAS). This work builds on our recent discovery of a parallel matrix–matrix multiplication implementation, which has yielded superior performance, and requires little work space. We show that the techniques used for the matrix–matrix multiplication naturally extend to all important Level 3 BLAS and thus this approach becomes an enabling technology for efficient parallel implementation of these routines and libraries that use BLAS. Representative performance results on the Intel Paragon system are given. © 1997 John Wiley & Sons, Ltd. Almadena Yu. Chtchelkanova, John A. Gunnels, Greg Morrow, James Overfelt, Robert A. van de Geijn |
Concurr. Pract. Exp. | 2 |