Abstract
Driven by improved computational throughput, multi- and many-core processors have been increasingly used in medical image processing. As these systems contain a discrete memory node, programmers have to manually manage the data transfer. To improve throughput by overlapping data transfers and task execution, special hardware details have to be known and should be considered with care. Data management could be even more tedious when the data size exceeds the GPU memory. In this work, we present a library that provides a convenient interface for CT reconstruction. Further, it contains a transparent data management, automatic data partitioning in case the GPU memory is insufficient, and overlapping techniques for improved performance. Our evaluations reveal that the library is able to reduce the amount of necessary code lines by ≈ 63% with respect to a comparable manual implementation. Additionally, a speedup of 38.1% for a volume size of 256 (10.7% for a volume size of 512) could be achieved by the library’s overlapping technique.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Eklund A, Dufort P, Forsberg D, et al. Medical image processing on the GPU: past, present and future. Med Image Anal. 2013;17(8):1073–94.
Scherl H, Keck B, Kowarschik M, et al. Fast GPU-based CT reconstruction using the common unified device architecture (CUDA). IEEE Nucl Sci Symp Conf Rec. 2007;6:4464–6.
Rohkohl C, Keck B, Hofmann H, et al. Technical note: rabbitCT - an open platform for benchmarking 3D cone-beam reconstruction algorithms. Med Phys. 2009;36(9):3940–4.
Zinsser T, Keck B. Systematic performance optimization of cone-beam backprojection on the kepler architecture. Proc 12th Fully Three Dim Image Reconstr Radiol Nucl Med. 2013; p. 225–8.
Papenhausen E, Zheng Z, Mueller K. GPU-accelerated back-projection revisited: squeezing performance by careful tuning. ProcWorks High Perform Image Reconstr. 2011;1:1–4.
Wu H, Daniel L, Wolfgang SP. A graph-partition-based scheduling policy for heterogeneous architectures. Proc HIS. 2015.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, H., Berger, M., Maier, A., Lohmann, D. (2016). A Memory Management Library for CT-Reconstruction on GPUs. In: Tolxdorff, T., Deserno, T., Handels, H., Meinzer, HP. (eds) Bildverarbeitung für die Medizin 2016. Informatik aktuell. Springer Vieweg, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-49465-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-662-49465-3_37
Publisher Name: Springer Vieweg, Berlin, Heidelberg
Print ISBN: 978-3-662-49464-6
Online ISBN: 978-3-662-49465-3
eBook Packages: Computer Science and Engineering (German Language)