Abstract
Base stations have been built from ASICs, DSP processors, or FPGAs. This paper studies the feasibility of building wireless base stations from commercial graphics processing units (GPUs). GPUs are attractive because they are widely used massively parallel devices that can be programmed in a high level language. Base station workloads are highly parallel, making GPUs a potential candidate for a cost effective programmable solution. In this work, we develop parallel implementations of key kernels to evaluate the merits of using GPUs as the baseband signal processor. We also study the mapping method of key kernels onto a multi-GPU system to minimize the number of required GPUs and the overall subframe processing latency. Our results show that the baseband subsystem in an LTE base station, which supports ≤150 Mbps peak data rate, can be built with up to four NVIDIA GTX 680 GPUs and commercial motherboards. We also show that the digital processing subsystem for a 75 Mbps LTE base station can be built using two NVIDIA GTX 680 GPUs with power consumption of 188 W.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
(2006). Intel solutions for the next generation multi-radio basestation. Intel application note. http://intel.com/design/intarch/applnots/307450.htm.
(2006). The vanu anywave base station subsystem. http://www.vanu.com/documents/technology/vanu-anywave-2006-05.pdf.
(2007). Long Term Evolution (LTE). Motorola White Paper. http://www.motorolasolutions.com/web/Business/Solutions/Industry%20Solutions/Service%20Providers/Wireless%20Operators/LTE/_Document/Static%20Files/6833_MotDoc_New.pdf.
(2007). Overview of the 3GPP long term evolution physical layer. Freescale semiconductor white paper. http://www.element14.com/community/servlet/JiveServlet/previewBody/13380-102-1-42319/3GPPEVOLUTIONWP.pdf.
(2009). Alcatel-Lucent 9926 digital 2U eNodeB baseband unit. Alcatel-lucent product brief.
(2009). LTE emerges as early leader in 4G technologies. White Paper. http://www.ti.com/general/docs/lit/getliterature.tsp?baseLiteratureNumber=spry124&;fileType=pdf.
(2010a). Accipiter systems 4G (LTE/WiMAX) base transceiver station AMC. Product Brief. http://www.accipitersystems.com/Files/Admin/wexford%20product%20brief%20final_4G_Proprietary_Removed_6_28_10.pdf.
(2010b). Freescale modular AdvancedMC platform for broadband/LTE base stations. http://cache.freescale.com/files/32bit/doc/fact_sheet/LTEWIMAXFS.pdf.
(2011). Gigabyte GA-X79-UD7. http://www.gigabyte.us/products/product-page.aspx?pid=4047#sp.
(2011). LTE baseband targeted design platform. Xilinx product brief. http://www.origin.xilinx.com/publications/prod_mktg/LTE-Baseband-SellSheet.pdf.
(2012). Designing basestation channel cards with FPGAs. ALtera product brief. http://www.altera.com/literature/po/wireless-channel-card.pdf.
(2012). NVIDIA GeForce GTX 680: The fastest, most efficient GPU ever built. White Paper. http://www.geforce.com/Active/en_US/en_US/pdf/GeForce-GTX-680-Whitepaper-FINAL.pdf.
(2013). CUFFT User Guide. http://docs.nvidia.com/cuda/cufft/index.html.
Coleri, S, Ergen, M, Puri, A, Bahai, A (2002). Channel estimation techniques based on pilot arrangement in OFDM systems. IEEE Transactions on Broadcasting, 48 (3), 223–229.
Gardner, JS (2012). CEVA EXPOSES DSP SIX PACK-XC4000 family uses coprocessors to buff up the baseband. http://www.linleygroup.com/mpr/article.php?url=mpr/h/2012/10864/10864.pdf.
Huang, S, Xiao, S, Feng, W (2009). On the energy efficiency of graphics processing units for scientific computing. In: IEEE international symposium on parallel distributed processing (IPDPS’09) (pp. 1–8).
Larsson, E (2009). MIMO detection methods: how they work [lecture notes]. IEEE Signal Processing Magazine, 26 (3), 91–95.
Lee, S, Ahn, C, Choi, S (2011). Implementation of Software-based 2X2 MIMO LTE base station system using GPU. In: SDR-WInnComm.
Micikevicius, P (2012). Multi-GPU programming. In: GPU technology conference.
Proakis, JG, & Salehi, M. (2008). Digital Communications, 5th edn. New York: McGraw-Hill.
Wu, M, Sun, Y, Wang, G, Cavallaro, J (2011). Implementation of a high throughput 3GPP turbo decoder on GPU. Journal of Signal Processing Systems, 65 (2), 171–183. doi:10.1007/s11265-011-0617-7.
Zheng, Q, Chen, Y, Dreslinski, R, Chakrabarti, C, Anastasopoulos, A, Mahlke, S, Mudge, T (2013a). Architecting an LTE base station with graphics processing units. In: 2013 IEEE workshop on signal processing systems (SiPS) (pp. 219–224).
Zheng, Q, Chen, Y, Dreslinski, R, Chakrabarti, C, Anastasopoulos, A, Mahlke, S, Mudge, T (2013b). Parallelization techniques for implementing trellis algorithms on graphics processors. In: 2013 IEEE international symposium on circuits and systems (ISCAS) (pp. 1220–1223).
Zheng, Q, Chen, Y, Dreslinski, R, Chakrabarti, C, Anastasopoulos, A, Mahlke, S, Mudge, T (2013c). WiBench: An open source kernel suite for benchmarking wireless systems. In: 2013 IEEE international symposium on workload characterization (IISWC) (pp. 123–132).
Acknowledgments
We wish to thank Nilmini Abeyratne and Yuan Lin for their generous help and useful feedback on the paper. This work is supported by the National Science Foundation grant NSF-CNS-0910851 and ARM Ltd.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zheng, Q., Chen, Y., Lee, H. et al. Using Graphics Processing Units in an LTE Base Station. J Sign Process Syst 78, 35–47 (2015). https://doi.org/10.1007/s11265-014-0932-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-014-0932-x