一句话：提出 FlexiFlow 寿命感知设计框架，通过碳足迹建模与面积优化的 RISC-V 核，实现一次性柔性电子上的极端边缘可持续计算。
论文面向物品级智能（ILI）——把计算直接集成到食品包装、医疗贴片等一次性产品中。柔性电子成本远低于硅，但受限于 kHz 级速度与数千门规模；更关键的是，ILI 应用的工作寿命差异高达 1000 倍，在万亿级部署规模下，传统架构设计决策不再最优。为此作者提出 FlexiFlow 框架，以应用特定寿命为基础，对隐含碳足迹与运行碳足迹之间的权衡进行建模，并包含三部分：面向可持续应用（从食品腐败检测到健康监测）的负载套件 FlexiBench；采用 1/4/8 位数据通路的面积优化 RISC-V 核 FlexiBits，单次负载执行能效提升 2.65–3.50 倍；以及依据部署特征选择最优架构的碳感知模型。评估表明，寿命感知的微架构设计可将碳足迹降低 1.62 倍，算法层面的决策可降低达 14.5 倍。作者还使用全开源工具与柔性电子 PDK 完成首次流片，实现 30.9 kHz 运行，说明极端边缘计算需要重新审视常规设计方法。
We present FlexiFlow, a lifetime-aware design framework for item-level intelligence (ILI) where computation is integrated directly into disposable products like food packaging and medical patches. Our framework leverages natively flexible electronics which offer significantly lower costs than silicon but are limited to kHz speeds and several thousands of gates. Our insight is that unlike traditional computing with more uniform deployment patterns, ILI applications exhibit 1000× variation in operational lifetime, fundamentally changing optimal architectural design decisions when considering trillion-item deployment scales. To enable holistic design and optimization, we model the trade-offs between embodied carbon footprint and operational carbon footprint based on application-specific lifetimes. The framework includes: (1) FlexiBench, a workload suite targeting sustainability applications from spoilage detection to health monitoring; (2) FlexiBits, area-optimized RISC-V cores with 1/4/8-bit datapaths achieving 2.65× to 3.50× better energy efficiency per workload execution; and (3) a carbon-aware model that selects optimal architectures based on deployment characteristics. We show that lifetime-aware microarchitectural design can reduce carbon footprint by 1.62×, while algorithmic decisions can reduce carbon footprint by 14.5×. We validate our approach through the first tape-out using a PDK for flexible electronics with fully open-source tools, achieving 30.9\,kHz operation. FlexiFlow enables exploration of computing at the Extreme Edge where conventional design methodologies must be reevaluated to account for new constraints and considerations. FlexiFlow is available at https://github.com/harvard-edge/FlexiFlow.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{PrakashCKAKKRTK26,
title = {Lifetime-Aware Design for Item-Level Intelligence at the Extreme Edge},
author = {Shvetank Prakash and Andrew Cheng and Olof Kindgren and Ashiq Ahamed and Graham Knight and Jedrzej Kufel and Francisco Rodriguez and Arya Tschand and David Kong and Mariam Elgamal and Jerry Huang and Emma Chen and Gage Hills and Richard Price and Emre Ozer and Vijay Janapa Reddi},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790182}
}