Transient Thermal Analysis for M.2 SSD Thermal Throttling: Detailed CFD Model vs Network-Based Model

Abstract

Solid State Drive (SSD) technology continues to advance toward smaller footprints with higher bandwidth and adoption of new I/O interfaces in the PC market segment. Power performance requirements are tightening in the design process to address specific requirement along with the development of SSD technology. To meet this aggressive requirement of performance, one major issue is thermal throttling. As the NAND and ASIC junction temperatures approach their safe operating limits, performance throttling is triggered and thus power consumption would drop accordingly. Therefore, robust thermal understanding on system level as well as reliable and fast thermal prediction are becoming essential in the process of system thermal design to optimize performance in a quick turnaround manner. In this paper, we present two different modeling approaches on the system level to model and simulate M.2 2280 SSD thermal throttling behavior in a typical laptop working environment. One approach is to establish a detailed three dimensional CFD (computational fluid dynamics) model using traditional CFD tools. In this model, the motherboard is enclosed in a case or chassis. Major heat sources of components and packages on the motherboard are considered including CPU, GPU, M.2 SSD, DRAM etc. Advanced cooling solutions like heat pipe and blowers are also modeled. In order to accurately capture thermal behavior of the SSD, detailed structure and geometry of NAND, PMIC and ASIC packages are included. Both natural and force convection as well as radiation are considered in this model. Both steady state and transient simulation results are presented in this paper. Further, the simulation results are validated with experimental data to predict thermal throttling behavior. The experiment is carried out with the SSD running in a laptop and temperatures of NAND and platform are logged during the test. In this paper, a second approach to generate accurate thermal models is presented for electronic parts. The thermal model of an electronic part is extracted from its detailed geometry configuration and material properties, so multiple thermal models can form a thermal network for complex steady-state and transient analyses of a system design. The extracted thermal model has the following advantages,1.It can accurately predict both static and dynamic thermal behaviors of the electronic parts;2.It can accurately predict the temperature at any probing node pre-defined in the electronic part;3.It is independent of boundary condition and can accurately predict the thermal behavior regardless of the environment and cooling conditions.With the accurate dynamic thermal models, a large thermal system can be decoupled into multiple domains such as air flows, chassis, heat sinks, PCB boards, packages, etc. The whole system can be consequently reconstructed as an integrated model-based network, and thermal simulation can be performed using fast network simulators. In comparison to the traditional CFD or FEM tools, the network-based approach improves efficiency in both thermal system construction and simulation. This approach is demonstrated through thermal simulation of the SSD drive within a laptop environment under natural convection in its working condition. The simulated system includes packages, M.2 PCB, motherboard, heat sink, and chassis.