FPGA Architectures to Enable Concurrent LUT and Adder Chain Usage
Open Access
- 21 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 19 (4) , 1-25
Abstract
Flexibility and customization make Field-Programmable Gate Arrays (FPGAs) attractive for arbitrary-precision arithmetic-heavy workloads such as sparse and mixed-precision DNN inference. However, in modern logic blocks, the hardware adder chain is typically driven only by look-up table (LUT) outputs, preventing adders and LUTs from being used independently and concurrently within a logic element, and reducing the hardware resource utilization efficiency. We propose Double-Duty , a logic block architecture that decouples LUTs and adder chains by augmenting four extra inputs of the logic element to bypass LUTs and directly drive the adders. We model the added circuits at the transistor level and implement full CAD support in open source tools, including improved arithmetic synthesis to provide a realistic baseline. On a Stratix-10-like architecture, Double-Duty reduces area by 21.6% on Kratos adder-intensive circuits and by 9.3% and 8.2% on the Koios and VTR suites, respectively, improving average area-delay product by 9.7% across all benchmarks with minimal impact on critical path delay. Additionally, we combined Double-Duty with prior arithmetic-oriented optimized architectures, and the fused designs achieve up to 20% area-delay product reduction in geometric mean across multiple benchmarks compared to the baseline.Keywords
Funding Information
- Intel Corporation, the National Science Foundation (Grant No. 2303626)
- CN Yang Scholars Programme, Nanyang Technological University
This publication has 37 references indexed in Scilit:
- High-efficiency Compressor Trees for Latest AMD FPGAsACM Transactions on Reconfigurable Technology and Systems, 2024
- PolyLUT: Learning Piecewise Polynomials for Ultra-Low Latency FPGA LUT-based Inference2023
- Koios 2.0: Open-Source Deep Learning Benchmarks for FPGA Architecture and CAD ResearchIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023
- FPGA Logic Block Architectures for Efficient Deep Learning InferenceACM Transactions on Reconfigurable Technology and Systems, 2020
- Fractal Synthesis2019
- COFFE 2ACM Transactions on Reconfigurable Technology and Systems, 2019
- Fast inference of deep neural networks in FPGAs for particle physicsJournal of Instrumentation, 2018
- Pipelined compressor tree optimization using integer linear programming2014
- The VTR project2012
- Efficient synthesis of compressor trees on FPGAs2008