Graph Attention Networks to Identify the Impact of Transistor Degradation on Circuit Reliability

可靠性(半导体) 降级(电信) 计算机科学 可靠性工程 晶体管 图形 工程类 电气工程 理论计算机科学 物理 电信 电压 量子力学 功率(物理)
作者
Tarek Mohamed,Victor M. van Santen,Lilas Alrahis,Ozgur Sinanoglu,Hussam Amrouch
出处
期刊:IEEE Transactions on Circuits and Systems I-regular Papers [Institute of Electrical and Electronics Engineers]
卷期号:71 (7): 3269-3281 被引量:4
标识
DOI:10.1109/tcsi.2024.3397460
摘要

Reliability is one of the key concerns in circuit design. The circuit must be able to tolerate transistor degradation to sustain reliability against timing failure. Whether a transistor is degraded due to noise, aging, or poor manufacturing, a circuit must uphold a timing error-free functionality over its entire projected lifetime. Transistors are hardened (designed stronger than necessary) to tolerate these degradations. However, hardening (e.g., widening the transistors) comes at the cost of additional area and power. Hence, it is necessary to identify and selectively harden specific transistors within a circuit. In this work, transistors that prolong a circuit's delay when they are degraded are termed "susceptible", and thus, are to be hardened. Identifying the susceptible transistors within a circuit is a complex task, for example, Monte Carlo circuit simulations require days to identify susceptible transistors in a single circuit. Consequently, current solutions are costly in terms of time and limited in their application. Instead, machine learning (ML) can offer a fast (inference in seconds) and universal (applicable to unseen circuits) alternative. However, traditional ML techniques struggle with inference on topology-based problems, while recent graph neural networks (GNNs) excel in these applications. Therefore, this work presents the first ML to classify susceptible transistors with GNNs. We use GNNs, specifically Graph Attention Networks (GAT), because the topology of the cell strongly affects how each transistor degradation affects performance. For instance, series-connected transistors amplify their impact, while parallel-connected ones can offset each other's influence. Our GAT-based approach employs a heterogeneous graph in combination with GAT's attention mechanism to capture the circuit's topology and its impact on the analysis. Our evaluation demonstrates the capability of our approach to classifying transistors according to their impact within the ASAP7 standard cell library's standard cells in mere 0.04 s (compared to days of Monte Carlo simulation time) while achieving 80.4% accuracy on unseen circuits.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
太阳没回头完成签到,获得积分10
1秒前
molihuakai的应助被机智铃铛采纳,获得10
2秒前
jackzzs完成签到,获得积分10
3秒前
俊逸吐司发布了新的文献求助10
3秒前
lemon发布了新的文献求助10
3秒前
3秒前
牧百川发布了新的文献求助10
3秒前
啵啵虎完成签到,获得积分10
4秒前
weimei发布了新的文献求助10
4秒前
烟花的应助被全能god采纳,获得10
5秒前
小马甲的应助被AA采纳,获得10
7秒前
fan的应助被胡萝卜卜采纳,获得10
7秒前
mmm发布了新的文献求助10
8秒前
葳蕤2发布了新的文献求助10
9秒前
9秒前
净心发布了新的文献求助10
9秒前
Orange的应助被妮妮采纳,获得10
10秒前
忧心的曼凝的应助被JQing采纳,获得10
11秒前
cindy发布了新的文献求助50
12秒前
12秒前
ltc0728发布了新的文献求助10
14秒前
wanci的应助被劳小呆采纳,获得10
14秒前
xiaoyaxxxx完成签到 ,获得积分10
15秒前
牧百川发布了新的文献求助10
16秒前
16秒前
科目三的应助被爱吃香菜采纳,获得10
18秒前
18秒前
不爱喝酒关注了科研通微信公众号
18秒前
爱科研的罗罗完成签到,获得积分10
18秒前
快乐铁身完成签到,获得积分10
19秒前
21秒前
HQQ完成签到,获得积分20
21秒前
11完成签到,获得积分10
22秒前
Lucas的应助被SherryZhang采纳,获得30
23秒前
烨采完成签到,获得积分10
23秒前
李春阳发布了新的文献求助10
23秒前
25秒前
水弘的应助被ltc0728采纳,获得10
25秒前
25秒前
HQQ发布了新的文献求助10
27秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183667
求助须知:如何正确求助?哪些是违规求助? 9572953
关于积分的说明 21828185
捐赠科研通 7780853
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558251
邀请新用户注册赠送积分活动 2480500