Vector Memory-Access Shuffle Fused Instructions for FFT-Like Algorithms
- 1 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 32 (5) , 1077-1088
Abstract
The shuffle operations are the bottleneck when mapping the FFT-like algorithms to the vector single instruction multiple data (SIMD) architectures. We propose six (three pairs) innovative vector memory-access shuffle fused instructions, which have been proved mathematically. Combined with the proposed modified binary-exchange method, the innovative instructions can efficiently address the bottleneck problem for decimation-in-frequency or decimation-in-time (DIF/DIT) radix-2/4 FFT-like algorithms, reach a performance improvement by 17.9%-111.2% and reduce the code size by 5.4%-39.8%. In addition, the proposed instructions fit some hybrid-radix FFTs and are suitable for the terms of the initial or result data placement for general algorithms. The software and hardware costs of the proposed instructions are moderate.Keywords
Funding Information
- National Natural Science Foundation of China (61602493,61502508)
This publication has 10 references indexed in Scilit:
- High performance DSP for vision, imaging and neural networks2016
- FT-Matrix: A Coordination-Aware Architecture for Signal ProcessingIEEE Micro, 2013
- Designing Fast Fourier Transform Accelerators for Orthogonal Frequency-Division Multiplexing SystemsJournal of Signal Processing Systems, 2011
- Accelerating the data shuffle operations for FFT algorithms on SIMD DSPs2011
- AnySP2009
- Efficient gather and scatter operations on graphics processors2007
- The TM3270 Media-Processor2006
- Data alignment for sub-word parallelism in DSP2003
- The scalability of FFT on parallel computersIEEE Transactions on Parallel and Distributed Systems, 1993
- An Algorithm for the Machine Calculation of Complex Fourier SeriesMathematics of Computation, 1965