A multi-core mapping implementation of 3780-point FFT

In This paper, we present a multi-core mapping implementation of 3780-point FFT as an application in DTMB system. By using SIMD commands and optimizing of specific modules, complication is decreased. Through the proper task arrangement we avoid the synchronizations and conflicts. A multi-core mapping based on multi-core processor can reach a high throughput up to 32.64 M Sample/s while the platform is running in 750MHz. The throughput of output is even higher than the VLSI result. The energy efficiency is given which is close to the VLSI result.

[1]  S. Winograd.  On computing the Discrete Fourier Transform. , 1976, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Yan Zhao,et al.  A smart platform with cognitive techniques for narrowband power line communication , 2012, 2012 International SoC Design Conference (ISOCC).

[3]  Rui Lv,et al.  Hardware design and implementation of 3780 points FFT based on FPGA in DTTB , 2010, 2010 4th International Conference on Application of Information and Communication Technologies.

[4]  Dejan Markovic,et al.  Power and Area Minimization of Reconfigurable FFT Processors: A 3GPP-LTE Example , 2012, IEEE Journal of Solid-State Circuits.

[5]  Rui Lv,et al.  A novel 3780-point FFT , 2010, 2010 IEEE International Conference on Wireless Communications, Networking and Information Security.

[6]  Nanning Zheng,et al.  Design and implementation of a video display processing SoC for full HD LCD TV , 2012, 2012 International SoC Design Conference (ISOCC).

[7]  Irving John Good,et al.  The Interaction Algorithm and Practical Fourier Analysis , 1958 .

[8]  Gang Cheng,et al.  A 3780-point FFT algorithm and its FPGA implementation , 2010, 2010 International Symposium on Next Generation Electronics.

[9]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[10]  Bevan M. Baas,et al.  A low-power, high-performance, 1024-point FFT processor , 1999, IEEE J. Solid State Circuits.

[11]  Zhiyi Yu,et al.  A novel multi-core processor for communication applications , 2010, 2010 10th IEEE International Conference on Solid-State and Integrated Circuit Technology.