GPU-optimized Direct Fourier Method for On-line Tomography

Shkarin, Roman; Ametova, Evelina; Chilingaryan, S.; Dritschler, T.; Kopmann, A.; Mirone, Alessandro; Shkarin, Andrei; Vogelgesang, Matthias; Tsapko, Sergey

doi:10.3233/fi-2015-1274

Cited by 5 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The later methods are asymptotically faster, but due to the involved interpolation in the Fourier domain are more sensitive to the quality of the available projections. For typical geometries Fourier-based methods are several times faster using the same computing hardware [22] and should be preferred if the computing infrastructure is limited to general-purpose processors only [5]. A recent study suggests to implement back projection as convolution in log-polar coordinates in order to gain high reconstruction speed with interpolation in the image domain [23].…”

Section: Introductionmentioning

confidence: 99%

Reviewing GPU architectures to build efficient back projection for parallel geometries

Chilingaryan

Ametova

Kopmann

et al. 2019

J Real-Time Image Proc

Self Cite

View full text Add to dashboard Cite

Back-Projection is the major algorithm in Computed Tomography to reconstruct images from a set of recorded projections. It is used for both fast analytical methods and high-quality iterative techniques. X-ray imaging facilities rely on Back-Projection to reconstruct internal structures in material samples and living organisms with high spatial and temporal resolution. Fast image reconstruction is also essential to track and control processes under study in real-time. In this article, we present efficient implementations of the Back-Projection algorithm for parallel hardware. We survey a range of parallel architectures presented by the major hardware vendors during the last 10 years. Similarities and differences between these architectures are analyzed and we highlight how specific features can be used to enhance the reconstruction performance. In particular, we build a performance model to find hardware hotspots and propose several optimizations to balance the load between texture engine, computational and special function units, as well as different types of memory maximizing the utilization of all GPU subsystems in parallel. We further show that targeting architecture-specific features allows one to boost the performance 2-7 times compared to the current state-of-the-art algorithms used in standard reconstructions codes. The suggested load-balancing approach is not limited to the back-projection but can be used as a general optimization strategy for implementing parallel algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Reviewing GPU architectures to build efficient back projection for parallel geometries

Chilingaryan

Ametova

Kopmann

et al. 2019

J Real-Time Image Proc

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our approach to compute the backprojection is called bst -as an acronym to backprojection-slice theorem [6] -having the same low complexity of O(N 2 log N ) although easier to implement than his competitors, producing less numerical artifacts and following a more traditional "gridding strategy" similar as [7]. There are several others reconstruction softwares reproducing quasi-real time reconstructions, [8,9,10,11].…”

Section: Introductionmentioning

confidence: 99%

Low-complexity Distributed Tomographic Backprojection for large datasets

Martínez¹,

Filho²,

Miqueles³

2017

Preprint

View full text Add to dashboard Cite

In this manuscript we present a fast gpu implementation for tomographic reconstruction of large datasets using data obtained at the Brazilian synchrotron light source. The algorithm is distributed in a cluster with 4 gpu's through a fast pipeline implemented in c programming language. Our algorithm is theoretically based on a recently discovered low complexity formula, computing the total volume within O(N 3 log N ) floating point operations; much less than traditional algorithms that operates within O(N 4 ) flops over an input data of size O(N 3 ). The results obtained with real data indicate that a reconstruction can be achieved within 1 second provided the data is transferred completely to the memory.

show abstract

“…For single workstations, there are now many high-performance implementations of both classical backprojection methods and iterative methods, often using graphics processing units (GPUs), for both parallel and cone-beam geometries [9–14]. …”

Section: Introductionmentioning

confidence: 99%

A distributed ASTRA toolbox

Palenstijn

Bédorf

Sijbers

et al. 2016

Adv Struct Chem Imag

View full text Add to dashboard Cite

While iterative reconstruction algorithms for tomography have several advantages compared to standard backprojection methods, the adoption of such algorithms in large-scale imaging facilities is still limited, one of the key obstacles being their high computational load. Although GPU-enabled computing clusters are, in principle, powerful enough to carry out iterative reconstructions on large datasets in reasonable time, creating efficient distributed algorithms has so far remained a complex task, requiring low-level programming to deal with memory management and network communication. The ASTRA toolbox is a software toolbox that enables rapid development of GPU accelerated tomography algorithms. It contains GPU implementations of forward and backprojection operations for many scanning geometries, as well as a set of algorithms for iterative reconstruction. These algorithms are currently limited to using GPUs in a single workstation. In this paper, we present an extension of the ASTRA toolbox and its Python interface with implementations of forward projection, backprojection and the SIRT algorithm that can be distributed over multiple GPUs and multiple workstations, as well as the tools to write distributed versions of custom reconstruction algorithms, to make processing larger datasets with ASTRA feasible. As a result, algorithms that are implemented in a high-level conceptual script can run seamlessly on GPU-enabled computing clusters, up to 32 GPUs or more. Our approach is not limited to slice-based reconstruction, facilitating a direct portability of algorithms coded for parallel-beam synchrotron tomography to cone-beam laboratory tomography setups without making changes to the reconstruction algorithm.

show abstract

GPU-optimized Direct Fourier Method for On-line Tomography

Cited by 5 publications

References 20 publications

Reviewing GPU architectures to build efficient back projection for parallel geometries

Reviewing GPU architectures to build efficient back projection for parallel geometries

Low-complexity Distributed Tomographic Backprojection for large datasets

A distributed ASTRA toolbox

Contact Info

Product

Resources

About