TPE-FFT: A Novel Two-Phase Execution Fast Fourier Transform for Ultra-Low-Latency Bioinformatics Architecture

Saravanakumar C (Department of Electronics and Communication Engineering, SRM Valliammai Engineering College)
Usha Bhanu N (Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, Kattankulathur, India)
Subhashini N (Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, Kattankulathur, India)
Preethi Sambandam Raju (Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, Kattankulathur, India)

Journal of Electronics, Electromedical Engineering, and Medical Informatics
Vol 8 No 4 (2026): October

The Fast Fourier Transform (FFT) is widely employed for frequency-domain analysis of genomic and biomedical signals; however, conventional block-oriented FFT processing generally requires the complete input sequence before the transform can be finalized. When genomic data are acquired sequentially, computations that depend on the final sample may remain unresolved until that sample arrives, resulting in additional post-arrival processing latency. This study presents a Two-Phase Execution Fast Fourier Transform (TPE-FFT), a dependency-aware execution strategy for radix-2 Decimation-in-Time (DIT) FFT processing. The proposed method exploits the linearity of the Discrete Fourier Transform (DFT) to separate the contribution of the final acquired sample from the contributions of the preceding samples. During Phase I, computations independent of the final sample are performed using a temporary zero representation, while the corresponding final-sample contribution is evaluated during Phase II and incorporated through an exact Fourier-domain correction. Variable-length genomic sequences are mapped to a common radix-2 transform length using zero-padding, and the proposed method is evaluated against a conventional radix-2 DIT-FFT implementation under the same computational conditions. A total of 1,075 genomic sequences are evaluated. TPE-FFT achieves positive measured execution-time reduction for 1,053 sequences (97.95%). The cumulative execution time decreases from 225.56469 s for the conventional implementation to 7.80065 s for TPE-FFT, corresponding to a 96.54% aggregate reduction and a 28.92× runtime ratio. For a representative 33,681-sample genomic sequence, execution time decreases from 15.15 s to 0.51 s, corresponding to a 96.63% reduction. The results indicate that dependency-aware scheduling can substantially reduce the computational workload remaining after final-sample arrival while retaining the underlying O(Nlog₂N) FFT complexity. The proposed strategy therefore provides a computational basis for further investigation of low-latency FFT processing in sequential genomic signal-processing applications.