Orders-of-magnitude performance increases in GPU-accelerated correlation of images from the International Space Station

Lu, Peter J.; Oki, Hidekazu; Frey, Catherine A.; Chamitoff, Gregory; Chiao, Leroy; Fincke, E. Michael; Foale, Cameron; Magnus, S; McArthur, William S.; Tani, Daniel M.; Whitson, Peggy A.; Williams, Jeffrey N.; Meyer, William V.; Sicker, Ronald J.; Au, Brion J.; Christiansen, Mark M.; Schofield, Andrew B.; Weitz, David A.

doi:10.1007/s11554-009-0133-1

Cited by 22 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12). Efficient algorithms designed for GPUs have reported up to 100x speedup over CPU implementations [25,78]. This difference in architecture has a direct consequence, the GPU is much more restrictive than the CPU but it is much more powerful if the solution is carefully designed for it.…”

Section: The Fundamental Difference Between Cpu and Gpu Architecturesmentioning

confidence: 99%

“…The GPU is indeed attractive to any scientist, because it is no more restricted to graphical problems and offers impressive parallel performance at the cost of a desktop computer. It is not a surprise to see GPU-based algorithms achieve considerable amounts of speedup over a classic CPU-based solution [10,30], even by two orders of magnitude [25,78].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Parallel Computing and its Applications in Data-Parallel Problems Using GPU Architectures

Navarro

Hitschfeld

Mateu

2014

Commun. comput. phys.

162

View full text Add to dashboard Cite

Abstract. Parallel computing has become an important subject in the field of computer science and has proven to be critical when researching high performance solutions. The evolution of computer architectures (multi-core and many-core) towards a higher number of cores can only confirm that parallelism is the method of choice for speeding up an algorithm. In the last decade, the graphics processing unit, or GPU, has gained an important place in the field of high performance computing (HPC) because of its low cost and massive parallel processing power. Super-computing has become, for the first time, available to anyone at the price of a desktop computer. In this paper, we survey the concept of parallel computing and especially GPU computing. Achieving efficient parallel algorithms for the GPU is not a trivial task, there are several technical restrictions that must be satisfied in order to achieve the expected performance. Some of these limitations are consequences of the underlying architecture of the GPU and the theoretical models behind it. Our goal is to present a set of theoretical and technical concepts that are often required to understand the GPU and its massive parallelism model. In particular, we show how this new technology can help the field of computational physics, especially when the problem is data-parallel. We present four examples of computational physics problems; n-body, collision detection, Potts model and cellular automata simulations. These examples well represent the kind of problems that are suitable for GPU computing. By understanding the GPU architecture and its massive parallelism programming model, one can overcome many of the technical limitations found along the way, design better GPU-based algorithms for computational physics problems and achieve speedups that can reach up to two orders of magnitude when compared to sequential implementations.

show abstract

Section: The Fundamental Difference Between Cpu and Gpu Architecturesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey on Parallel Computing and its Applications in Data-Parallel Problems Using GPU Architectures

Navarro

Hitschfeld

Mateu

2014

Commun. comput. phys.

162

View full text Add to dashboard Cite

show abstract

“…[57][58][59] However, such methods have gained popularity in the physics and mathematics communities and show great promise for future studies, especially with the emergence of the graphics card as a powerful platform for particle simulations and image processing. [60][61][62] Moreover, there has been a marked increase in the ability to synthesize a stunning array of faceted (nonconvex) particles, 15,26,27,[31][32][33][34][35] as well as a large improvement in the level of control with which such particles can be prepared. 28 This has led to particular interest from the materials science community in these overlap algorithms to perform simulations on nanoparticle and colloid systems.…”

Section: Hard-particle Overlap Algorithmsmentioning

confidence: 99%

Crystal-structure prediction via the Floppy-Box Monte Carlo algorithm: Method and application to hard (non)convex particles

Graaf

Filion

Maréchal

et al. 2012

The Journal of Chemical Physics

View full text Add to dashboard Cite

In this paper, we describe the way to set up the floppy-box Monte Carlo (FBMC) method [L. Filion, M. Marechal, B. van Oorschot, D. Pelt, F. Smallenburg, and M. Dijkstra, Phys. Rev. Lett. 103, 188302 (2009)] to predict crystal-structure candidates for colloidal particles. The algorithm is explained in detail to ensure that it can be straightforwardly implemented on the basis of this text. The handling of hard-particle interactions in the FBMC algorithm is given special attention, as (soft) short-range and semi-long-range interactions can be treated in an analogous way. We also discuss two types of algorithms for checking for overlaps between polyhedra, the method of separating axes and a triangular-tessellation based technique. These can be combined with the FBMC method to enable crystal-structure prediction for systems composed of highly shape-anisotropic particles. Moreover, we present the results for the dense crystal structures predicted using the FBMC method for 159 (non)convex faceted particles, on which the findings in [J. de Graaf, R. van Roij, and M. Dijkstra, Phys. Rev. Lett. 107, 155501 (2011)] were based. Finally, we comment on the process of crystalstructure prediction itself and the choices that can be made in these simulations.

show abstract

“…General purpose CPUs today have multiple compute cores per chip, with an expected increase in the years to come [40]. Moreover, special purpose chips (e.g., GPUs [31,32]) are now combined or even integrated with CPUs to increase performance by orders-of-magnitude (e.g., see [28]). …”

Section: Jungle Computing Systemsmentioning

confidence: 99%

Jungle Computing: Distributed Supercomputing Beyond Clusters, Grids, and Clouds

Seinstra

Maassen

Nieuwpoort

et al. 2011

Computer Communications and Networks

View full text Add to dashboard Cite

In recent years, the application of high-performance and distributed computing in scientific practice has become increasingly wide-spread. Among the most widely available platforms to scientists are clusters, grids, and cloud systems. Such infrastructures currently are undergoing revolutionary change due to the integration of many-core technologies, providing orders-of-magnitude speed improvements for selected compute kernels. With high-performance and distributed computing systems thus becoming more heterogeneous and hierarchical, programming complexity is vastly increased. Further complexities arise because urgent desire for scalability, and issues including data distribution, software heterogeneity, and ad-hoc hardware availability, commonly force scientists into simultaneous use of multiple platforms (e.g. clusters, grids, and clouds used concurrently). A true computing jungle. In this chapter we explore the possibilities of enabling efficient and transparent use of Jungle Computing Systems in every-day scientific practice. To this end, we discuss the fundamental methodologies required for defining programming models that are tailored to the specific needs of scientific researchers. Importantly, we claim that many of these fundamental methodologies already exist today, as integrated in our Ibis high-performance distributed programming system. We also make a case for the urgent need for easy and efficient Jungle Computing in scientific practice, by exploring a set of state-of-the-art application domains. For one of these domains we present results obtained with Ibis on a real-world Jungle Computing System. The chapter concludes by exploring fundamental research questions to be investigated in the years to come.

show abstract

Orders-of-magnitude performance increases in GPU-accelerated correlation of images from the International Space Station

Cited by 22 publications

References 38 publications

A Survey on Parallel Computing and its Applications in Data-Parallel Problems Using GPU Architectures

A Survey on Parallel Computing and its Applications in Data-Parallel Problems Using GPU Architectures

Crystal-structure prediction via the Floppy-Box Monte Carlo algorithm: Method and application to hard (non)convex particles

Jungle Computing: Distributed Supercomputing Beyond Clusters, Grids, and Clouds

Contact Info

Product

Resources

About