A 0.37mm2 LTE/Wi-Fi compatible, memory-based, runtime-reconfigurable 2n3m5k FFT accelerator integrated with a RISC-V core in 16nm FinFET

Dedicated hardware accelerators enable energy-efficient implementations of radio and imaging basebands. Multistandard, multi-mode radio basebands require an on-the-fly reconfigurable fast Fourier transform (FFT) accelerator that implements many different FFT sizes. An instance of a runtime-reconfigurable 2n3m5k FFT accelerator was generated by a custom hardware generator to meet the requirements of common wireless standards (Wi-Fi, LTE). The accelerator is integrated with a RISC-V processor, and the measured 16nm FinFET chip runs up to 940MHz and consumes 0.46 to 22.6mW of power when running FFT benchmarks for Wi-Fi and LTE symbol lengths.

[1]  Bin Wu,et al.  An efficient prime factor memory-based FFT processor for LTE systems , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[2]  Borivoje Nikolic,et al.  A generator of memory-based, runtime-reconfigurable 2N3M5K FFT engines , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Chen-Yi Lee,et al.  A Generalized Mixed-Radix Algorithm for Memory-Based FFT Processors , 2010, IEEE Transactions on Circuits and Systems II: Express Briefs.

[4]  Jianhao Hu,et al.  Hardware Efficient Mixed Radix-25/16/9 FFT for LTE Systems , 2015, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[5]  Franz Franchetti,et al.  SPIRAL: Code Generation for DSP Transforms , 2005, Proceedings of the IEEE.

[6]  John Wawrzynek,et al.  Chisel: Constructing hardware in a Scala embedded language , 2012, DAC Design Automation Conference 2012.

[7]  Jonathan Bachrach,et al.  A GENERATOR OF MEMORY-BASED , RUNTIME-RECONFIGURABLE 2 N 3 M 5 K FFT ENGINES , 2016 .

[8]  Adam M. Izraelevitz,et al.  The Rocket Chip Generator , 2016 .