Emulation-based transient thermal modeling of 2D/3D systems-on-chip with active cooling

Abstract

Abstract-New tendencies envisage 2D/3D Multi-Processor System-On-Chip (MPSoC) as a promising solution for the consumer electronics market. MPSoCs are complex to design, as they must execute multiple applications (games, video), while meeting additional design constraints (energy consumption, time-to-market, etc.). Moreover, the rise of temperature in the die for MPSoCs, especially for forthcoming 3D chips, can seriously affect their final performance and reliability. In this context, transient thermal modeling is a key challenge to study the accelerated thermal problems of MPSoC designs, as well as to validate the benefits of active cooling techniques (e.g., liquid cooling), combined with other state-of-the-art methods (e.g., dynamic frequency and voltage scaling), as a solution to overcome run-time thermal runaway.In this paper, I present a novel approach for fast transient thermal modeling and analysis of 2D/3D MPSoCs with active cooling, which relies on the exploitation of combined hardwaresoftware emulation and linear thermal models for liquid flow. The proposed framework uses FPGA emulation as the key element to model the hardware components of 2D/3D MPSoC platforms at multi-megahertz speeds, while running real-life software multimedia applications. This framework automatically extracts detailed system statistics that are used as input to a scalable software thermal library, using different ordinary differential equation solvers, running in a host computer. This library calculates at run-time the temperature of on-chip components, based on the collected statistics from the emulated system and the final floorplan of the 2D/3D MPSoC. This approach creates a close-loop thermal emulation system that allows MPSoC designers to validate different hardware-and software-based thermal management approaches, including liquid cooling injection control, under transient and dynamic thermal maps. The experimental results with 2D/3D MPSoCs illustrate speed-ups of more than three orders of magnitude compared to cycle-accurate MPSoC thermal simulators, at the same time as preserving the accuracy of the estimated temperature within 3% of traditional approaches using finite-element simulations for 3D stacks and liquid cooling.

Efficient Worst-Case Temperature Evaluation for Thermal-Aware Assignment of Real-Time Applications on MPSoCs

“…Evaluating the temperature characteristics is typically a two-step process. First, the transient power dissipation is determined by a software-based [1,24] or hardware-based [26] power-aware simulator. Having the transient power dissipation, either the average temperature is calculated based on steady-state analysis [31] or the transient temperature evolution is obtained by simulating the system in a thermal simulator [12,21,22].…”

“…Similar to [17], we suppose that the square of the supply voltage scales linearly with the operation frequency even though the results of the paper also hold for any other monotonic relation between supply voltage and frequency. Now, we can write the total power consumption as: 3 • S(t) + ω (26) with diagonal matrix diag(f) of vector f and constant diagonal matrices ρ and ω. As the operation frequency is statically assigned at design-time, the thermal analysis method proposed in Eq.…”

Worst-case temperature analysis for different resource models

“…Estimating the temperature is typically a two-step procedure. First, the transient power dissipation of the system is determined by means of a power-aware simulator, either software-based [13,14] or hardware-based [15]. Afterwards, the power dissipation is used to evaluate the transient temperature evolution in a thermal simulator like HotSpot [16].…”

Thermal-aware floorplanner for 3D IC, including TSVs, liquid microchannels and thermal domains optimization

“…While the conventional air cooling has proved to be insufficient for 3D-ICs, the interlayer micro-channel liquid cooling provides a better option to address this problem. Some works like [9,10] have focused in thermal modeling with active cooling. These works have studied the effect of allocating liquid channels between active layers and their cooling effect.…”