An Optimized Floating-Point Unit Set for FPGA-Based DSP: Improving Area, Energy, and Throughput Trade-Offs
Electronics · 30.06.2026 · 15 (13) · 2850
DOI: 10.3390/electronics15132850 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 30.06.2026. Verfasst von Fernando Flores und 5 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade de Vigo/CISUG.
Abstract (Originalsprache)
Floating-point arithmetic provides the dynamic range that fixed-point lacks for digital signal processing (DSP) algorithms with widely varying operand magnitudes. This work presents a parameterizable floating-point unit set for field programmable gate array (FPGA)-based DSP. The set consists of five units: adder/subtractor, multiplier, multiply–accumulate (MAC), fixed-to-float and float-to-fixed converters. Two architectural choices distinguish the proposed format from IEEE-754: configurable exponent and mantissa widths during synthesis and a 0.f significand encoding that reduces corner-case logic at the cost of one additional mantissa bit. The format is therefore IEEE-754-inspired rather than fully compliant: special values (NaN, ±∞) are not implemented, and overflow and underflow are handled through saturation to predefined constants. The design is implemented in standard VHDL-2008 without relying on high-level synthesis (HLS) tools or vendor-specific primitives, ensuring portability across different FPGA families and application-specific integrated circuits (ASICs). The multiplier and MAC are evaluated in two configurations: inferring DSP blocks or look-up table (LUT)-only, both close timing at 300MHz on Artix-7 and Kintex Ultrascale devices. The proposed blocks outperform vendor IP Cores and recent academic designs in terms of area-throughput-power (ATP), achieving improvements from 10% to 108%, except for the adder/subtractor, which does not outperform two optimized Xilinx IP cores (HS-R and HS-P) and is therefore included for design coherence rather than as a strict resource improvement over all vendor IPs. All these blocks meet the theoretical error bound, and a representative 200-tap finite impulse response (FIR) filter built from them closes timing at 300MHz with 76% LUT utilization.
Förderung
- Universidade de Vigo/CISUG
Zitieren
APA
Flores, F., Queimaño, J. P., Pazo, J. M. C., Valdés-Peña, M. D., Graña, C. Q., & Sánchez, J. M. V. (2026). An Optimized Floating-Point Unit Set for FPGA-Based DSP: Improving Area, Energy, and Throughput Trade-Offs. Electronics, 15(13), 2850. https://doi.org/10.3390/electronics15132850
Vancouver
Flores F, Queimaño JP, Pazo JMC, Valdés-Peña MD, Graña CQ, Sánchez JMV. An Optimized Floating-Point Unit Set for FPGA-Based DSP: Improving Area, Energy, and Throughput Trade-Offs. Electronics. 2026;15(13):2850. doi:10.3390/electronics15132850
BibTeX
@article{Flores2026,
author = {Flores, Fernando and Queimaño, Juan Portela and Pazo, Jesús Manuel Costa and Valdés-Peña, María Dolores and Graña, Camilo Quintáns and Sánchez, José Manuel Villapún},
title = {An Optimized Floating-Point Unit Set for FPGA-Based DSP: Improving Area, Energy, and Throughput Trade-Offs},
journal = {Electronics},
year = {2026},
volume = {15},
number = {13},
pages = {2850},
doi = {10.3390/electronics15132850}
}
EUVIMED