DNN-based Fast Static On-chip Thermal Solver
DNN-based Fast Static On-chip Thermal Solver
复制标题
基于 DNN 的快速静态片上热解算器
DOI：
10.23919/semi-therm50369.2020.9142855
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ying
中科院分区：
文献类型：
--
作者：
Jimin Wen;S. Pan;N. Chang;Wentze Chuang;W. Xia;Deqi Zhu;Akhilesh Kumar;En;K. Srinivasan;Ying
准确预测芯片上的温度分布对于即将到来的5G、汽车和AI芯片封装系统的性能和可靠性至关重要。特别是，较大的温度梯度(芯片上的温度变化)会加速电迁移和老化，还会影响设计性能和功率。此外，通常存在对芯片结点的Tmax(最高温度)限制、移动设备或可穿戴设备的皮肤温度问题，以及用于动态电压和频率调节的片上热传感器的重要布局考虑。然而，使用有限元或计算流体力学(CFD)技术在芯片上获得准确和详细的温度梯度是非常耗时的。此外，对于不同的应用，有许多不同的功能场景，用户需要确定可能的片上Tmax位置。因此，行业中迫切需要在芯片封装系统或可能包括多个芯片的更复杂的3DIC设计中提供快速而准确的片上热解决方案。本文提出了一种使用数据驱动的基于DNN的热解算器的方法，与具有相同精度的传统的基于有限元的热解算器相比，根据芯片的大小，该热解算器可以快100-1000倍。
Accurate prediction of on-chip temperature distribution becomes important for the performance and reliability of upcoming 5G, automotive, and AI chip-package-systems. In particular, a large thermal gradient (the temperature variation across a chip) accelerates electromigration and aging, and also impacts design performance and power. Furthermore, there are usually Tmax (maximum temperature) constraints on junctions of a chip, skin temperature concerns for mobile devices or wearables, and important placement considerations of on-chip thermal sensors for use in dynamic voltage and frequency scaling. However, obtaining an accurate and detailed thermal gradient on-chip is very time-consuming using the finite element method (FEM) or computational fluid dynamics (CFD) technology. Furthermore, there are many different functional scenarios for various applications that users need to identify possible Tmax locations on-chip. Therefore, there is an urgent need in the industry to provide a fast, yet accurate on-chip thermal solution in a chip-package-system or more complicated 3DIC design, which may include multiple chips. This paper proposes a method to use a data-driven DNN-based thermal solver that can be 100–1000x faster depending on the size of the chip compared to traditional FEM-based thermal solvers with the same level of accuracy.