Hybrid computing: CPU+GPU co-processing and its application to tomographic reconstruction

Agulleiro, J.I.; Heras‐Vázquez, Francisco Javier Las; Garzón, Eduardo Garzón; Fernández, Julio F.

doi:10.1016/j.ultramic.2012.02.003

Cited by 32 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ppcgm calls the routine axmebe to calculate the matrix-vector multiplication y = Au. axmebe does not use the full vectors u and y and the full matrix A, but performs an elementwise matrix-vector multiplication of the form: y el = A el u el (2) for all finite elements el of the FEM. While the size of the full vectors grows proportionally to the number of elements and may grow to some hundreds of thousands, the size of the element vectors remains constant.…”

Section: Sequential Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An execution time and energy model for an energy-aware execution of a conjugate gradient method with CPU/GPU collaboration

Lang

Rünger

2014

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Section: Sequential Methodsmentioning

confidence: 99%

“…A CPU/GPU collaboration scheme for an tomographic reconstruction application is presented in [2]. It uses a task pool for distributing the workload and achieves a speed-up of 1.4. .…”

Section: Cpu/gpu Collaborationmentioning

confidence: 99%

An execution time and energy model for an energy-aware execution of a conjugate gradient method with CPU/GPU collaboration

Lang

Rünger

2014

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…On the other hand, ultra-fast acquisition setups allow for scanning times in the order of hundred seconds, see e.g. [4]. Whilst so far tomographic images were mostly used in a static context, as an auxiliar tool for the assessment of inner microstructure also in view of FE analyses, in the current trend X-ray monitoring is being deemed from a dynamic standpoint, as embedded in the four dimensional space-time.…”

Section: Materials Characterization By Bulk Measurementsmentioning

confidence: 99%

X-ray Microtomography under Loading and 3D-Volume Digital Image Correlation. A Review

Fedele

Ciani

Fiori

2014

Fundamenta Informaticae

View full text Add to dashboard Cite

In this review paper the synergistic combination of X-ray microtomography, in situ mechanical tests on material samples and full-field kinematic measurements by 3D-Volume Digital Image Correlation is discussed. First, basic features are outlined, concerning X-ray microtomography by either laboratory sources or synchrotron radiation. The main equations for 3D-Volume Digital Image Correlation are then presented, and different provisions regularizing the ill-posed problem of motion estimation are outlined. Thereafter, a survey of the state of the art is provided, with reference to a variety of biological and engineering materials. Limitations and perspectives of the proposed methodology in diverse applications are highlighted. The rapid growth of this research topic is emphasized, due to the truly multi-disciplinary vocation, the synergy between algorithmic and technological solutions, a fusion of experiments and numerical methods.

show abstract

“…, preprocessing, alignment, classification, and averaging of subtomograms) are several orders of magnitude greater for SPT than for SPA. However, Moore’s Law (Schaller 1997) has finally caught up with this field, and it is now practical to compute hundreds of tomographic reconstructions and average tens of thousands of subtomograms making use of algorithms that previously would have been untenable (Agulleiro et al 2012). …”

Section: Introduction: the Need For Single Particle Tomographymentioning

confidence: 99%

The advent of structural biology in situ by single particle cryo-electron tomography

Galaz-Montoya

Ludtke

2017

Biophys Rep

View full text Add to dashboard Cite

Single particle tomography (SPT), also known as subtomogram averaging, is a powerful technique uniquely poised to address questions in structural biology that are not amenable to more traditional approaches like X-ray crystallography, nuclear magnetic resonance, and conventional cryoEM single particle analysis. Owing to its potential for in situ structural biology at subnanometer resolution, SPT has been gaining enormous momentum in the last five years and is becoming a prominent, widely used technique. This method can be applied to unambiguously determine the structures of macromolecular complexes that exhibit compositional and conformational heterogeneity, both in vitro and in situ. Here we review the development of SPT, highlighting its applications and identifying areas of ongoing development.

show abstract

Hybrid computing: CPU+GPU co-processing and its application to tomographic reconstruction

Cited by 32 publications

References 24 publications

An execution time and energy model for an energy-aware execution of a conjugate gradient method with CPU/GPU collaboration

An execution time and energy model for an energy-aware execution of a conjugate gradient method with CPU/GPU collaboration

X-ray Microtomography under Loading and 3D-Volume Digital Image Correlation. A Review

The advent of structural biology in situ by single particle cryo-electron tomography

Contact Info

Product

Resources

About