MFIT: Multi-Fidelity Thermal Modeling for 2.5D and 3D Multi-Chiplet Architectures
Authors:
- Lukas PfrommLPLukas Pfromm
- Alish KananiAKAlish Kanani
- Harsh SharmaHSHarsh Sharma
- Parth SolankiPSParth Solanki
- Eric TervoETEric Tervo
- Jaehyun ParkJPJaehyun Park
- Janardhan Rao DoppaJDJanardhan Rao Doppa
- Partha Pratim PandePPPartha Pratim Pande
- Umit Y. OgrasUOUmit Y. Ogras
Preprint
Abstract
Rapidly evolving artificial intelligence and machine learning applications require ever-increasing computational capabilities, while monolithic 2D design technologies approach their limits. Heterogeneous integration of smaller chiplets using a 2.5D silicon interposer and 3D packaging has emerged as a promising paradigm to address this limit and meet performance demands. These approaches offer a significant cost reduction and higher manufacturing yield than monolithic 2D integrated circuits. However, the compact arrangement and high compute density exacerbate the thermal management challenges, potentially compromising performance. Addressing these thermal modeling challenges is critical, especially as system sizes grow and different design stages require varying levels of accuracy and speed. Since no single thermal modeling technique meets all these needs, this paper introduces MFIT, a range of multi-fidelity thermal models that effectively balance accuracy and speed. These multi-fidelity models can enable efficient design space exploration and runtime thermal management. Our extensive testing on systems with 16, 36, and 64 2.5D integrated chiplets and 16x3 3D integrated chiplets demonstrates that these models can reduce execution times from days to mere seconds and milliseconds with negligible loss in accuracy.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- SWAP: A Server-Scale Communication-Aware Chiplet-Based Manycore PIM AcceleratorIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022
- Full-Chip Power Density and Thermal Map Characterization for Commercial Microprocessors Under Heat Sink CoolingIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021
- PACT: An Extensible Parallel Thermal Simulator for Emerging Integration and Cooling TechnologiesIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021
- Temperature-Aware DRAM Cache Management—Relaxing Thermal Constraints in 3-D SystemsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2019
- NeuroSim: A Circuit-Level Macro Model for Benchmarking Neuro-Inspired Architectures in Online LearningIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- 3D-ICE: A Compact Thermal Model for Early-Stage Design of Liquid-Cooled ICsIEEE Transactions on Computers, 2013
- Accurate Direct and Indirect On-Chip Temperature Sensing for Efficient Dynamic Thermal ManagementIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2010
- Modeling of Cylindrical Pin-Fin Heat Sinks for Electronic PackagingIEEE Transactions on Components and Packaging Technologies, 2008
- Power, Thermal, and Reliability Modeling in Nanometer-Scale MicroprocessorsIEEE Micro, 2007
- Characterization of compact heat sink models in natural convectionIEEE Transactions on Components and Packaging Technologies, 2002