TY - JOUR
T1 - Multidimensional DFT IP generator for FPGA platforms
AU - Yu, Chi Li
AU - Irick, Kevin
AU - Chakrabarti, Chaitali
AU - Narayanan, Vijaykrishnan
N1 - Funding Information:
Manuscript received February 21, 2010; revised July 09, 2010; accepted August 24, 2010. Date of publication October 25, 2010; date of current version March 30, 2011. This work is supported in part by the Defense Advanced Research Projects Agency (DARPA) under Grant W911NF-05–1-0248 and in part by the National Science Foundation (NSF) under Grant 0916887 and Grant 0903432. This paper was recommended by Associate Editor B. Shi.
PY - 2011
Y1 - 2011
N2 - Multidimensional (MD) discrete Fourier transform (DFT) is a key kernel algorithm in many signal processing applications. In this paper we describe an MD-DFT intellectual property (IP) generator and a bandwidth-efficient MD DFT IP for high performance implementations of 2-D and 3-D DFT on field-programmable gate array (FPGA) platforms. The proposed architecture is generated automatically and is based on a decomposition algorithm that takes into account FPGA resources and the characteristics of off-chip memory access, namely, the burst access pattern of the synchronous dynamic RAM (SDRAM). The IP generator has been integrated into an in-house FPGA development platform, AlgoFLEX, for easy verification and fast integration. The corresponding 2-D and 3-D DFT architectures have been ported onto the BEE3 board and their performance measured and analyzed. The results shows that the architecture can maintain the maximum memory bandwidth throughout the whole procedure while avoiding matrix transpose operations used in most other MD DFT implementations. To further enhance the performance, the proposed architecture is being ported onto the newly released Xilinx ML605 board. The simulation results show that 2 K × 2 K images with complex 64-bit precision can be processed in less than 27 ms.
AB - Multidimensional (MD) discrete Fourier transform (DFT) is a key kernel algorithm in many signal processing applications. In this paper we describe an MD-DFT intellectual property (IP) generator and a bandwidth-efficient MD DFT IP for high performance implementations of 2-D and 3-D DFT on field-programmable gate array (FPGA) platforms. The proposed architecture is generated automatically and is based on a decomposition algorithm that takes into account FPGA resources and the characteristics of off-chip memory access, namely, the burst access pattern of the synchronous dynamic RAM (SDRAM). The IP generator has been integrated into an in-house FPGA development platform, AlgoFLEX, for easy verification and fast integration. The corresponding 2-D and 3-D DFT architectures have been ported onto the BEE3 board and their performance measured and analyzed. The results shows that the architecture can maintain the maximum memory bandwidth throughout the whole procedure while avoiding matrix transpose operations used in most other MD DFT implementations. To further enhance the performance, the proposed architecture is being ported onto the newly released Xilinx ML605 board. The simulation results show that 2 K × 2 K images with complex 64-bit precision can be processed in less than 27 ms.
UR - http://www.scopus.com/inward/record.url?scp=79953272919&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79953272919&partnerID=8YFLogxK
U2 - 10.1109/TCSI.2010.2078750
DO - 10.1109/TCSI.2010.2078750
M3 - Article
AN - SCOPUS:79953272919
SN - 1549-8328
VL - 58
SP - 755
EP - 764
JO - IEEE Transactions on Circuits and Systems I: Regular Papers
JF - IEEE Transactions on Circuits and Systems I: Regular Papers
IS - 4
M1 - 5608525
ER -