Work

Predictive Modeling of FPGA Resource and Power Consumption for Configurable CNN Operators

Year: 2025

Type: conference-paper

Abstract: As Convolutional Neural Networks (CNNs) continue to grow in complexity and accuracy, their deployment on embedded platforms requires hardware-aware optimizations to meet stringent constraints on logic resources, power, and latency. FPGAs offer an attractive solution because of their parallelism, reconfigurability, and energy efficiency. However, conventional FPGA design flows remain time-consuming and often lack early-stage estimation capabilities. This work introduces a library of parameterizable Intellectual Properties (IPs) for convolution, activation, and pooling, developed in VHDL and optimized for fixed-point arithmetic. IPs were designed to address various architectural trade-offs involving logic usage, DSP allocation strategy, parallelism, and power efficiency, while also supporting faster development through modular reuse. To accelerate design space exploration, a methodology is proposed for generating predictive mathematical models capable of estimating key FPGA resource metrics as functions of input bit widths. The models were validated with low prediction errors and coefficient of determination (R2) values greater than 0.94, allowing accurate estimation of the resources and dynamic power without synthesis. This supports fast architectural decisions and paves the way for automated, resource-aware CNN deployment on FPGAs.

Source: IEEE International Conference on Electronics, Circuits and Systems (ICECS)

DOI: 10.1109/icecs66544.2025.11270578

Authors: Philippe Magalhães, Virginie Fresse, Benoît Suffran, Olivier Alata

Institutions: Centre National de la Recherche Scientifique, Laboratoire Hubert Curien, Université Jean Monnet, STMicroelectronics (France)

Language: English

Topic: Embedded Systems Design Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: green

Funders: BP, Bpifrance, Région Auvergne-Rhône-Alpes