FFT Acceleration in a NAND Flash Memory

FFT is utilized in a wide range of spectrum analysis applications. As the data volume dramatically increases in multi-sensor or wideband RF systems, advances in FFT acceleration are required to realize a high-performance back-end digital signal processing unit. A million-point FFT accelerator that is feasible for a single-chip solution is introduced here using an in-memory technique in a NAND flash memory. The million-point FFT accelerator is developed using a compact SONOS NAND flash model with a Gaussian noise distribution. With a 1-bit memory depth, SQNR reaches approximately 110dB. It is comparable to conventional accelerators using FPGAs with a 20-bit twiddle factor and 32-bit output word length, which will be references for the realization of a single-chip solution.

Authors

Institutions

Publication Details

Published
2025-05-25
DOI
https://doi.org/10.1109/iscas56072.2025.11043388
Primary Topic
Advanced Data Storage Technologies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

FFT Acceleration in a NAND Flash Memory

Su‐in Yi, Sungho Kim, Sungyoun Seo
Advanced Data Storage Technologies
article

FFT Acceleration in a NAND Flash Memory

Su‐in Yi, Sungho Kim, Sungyoun Seo
article en

Abstract

FFT is utilized in a wide range of spectrum analysis applications. As the data volume dramatically increases in multi-sensor or wideband RF systems, advances in FFT acceleration are required to realize a high-performance back-end digital signal processing unit. A million-point FFT accelerator that is feasible for a single-chip solution is introduced here using an in-memory technique in a NAND flash memory. The million-point FFT accelerator is developed using a compact SONOS NAND flash model with a Gaussian noise distribution. With a 1-bit memory depth, SQNR reaches approximately 110dB. It is comparable to conventional accelerators using FPGAs with a 20-bit twiddle factor and 32-bit output word length, which will be references for the realization of a single-chip solution.

University of Rhode Island (US), Texas A&M University (US)
Office of Naval Research
Affordable and clean energy
Openalex Percentile: Top 84%
Advanced Data Storage Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.