Hot spots and core-to-core thermal coupling in future multi-core architectures
- 1 February 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10652221,p. 205-210
Abstract
This paper studies hot spot and thermal coupling problems in future multicore architectures as CMOS technology scales from 65 nm feature size to 15 nm. We demonstrate that the thermal coupling between neighboring cores will dramatically increase as the technology scales to smaller feature sizes. The simulation studies were based on solving the heat equation using the analytical Green's function method. Our simulations indicate that the thermal coupling in the 15 nm feature size just after 100 ms of operation will increase from 20% to 42% and in the steady state might reach even 65%. This finding uncovers a major challenge for the design of future multi-core architectures as the technology keeps scaling down. This will require a holistic approach to the design of future multi-core architectures encompassing low power computing, thermal management technologies and workload distribution.Keywords
This publication has 8 references indexed in Scilit:
- Power/Performance/Thermal Design-Space Exploration for Multicore ArchitecturesIEEE Transactions on Parallel and Distributed Systems, 2008
- Thermal analysis of layered electronic circuits with Green's functionsMicroelectronics Journal, 2007
- Thousand core chipsProceedings of the 39th conference on Design automation - DAC '02, 2007
- Power-performance considerations of parallel computing on chip multiprocessorsACM Transactions on Architecture and Code Optimization, 2005
- Temperature and supply Voltage aware performance and power modeling at microarchitecture levelIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2005
- Application of high-κ gate dielectrics and metal gate electrodes to enable silicon and non-silicon logic nanotechnologyMicroelectronic Engineering, 2005
- Temperature-aware microarchitectureACM Transactions on Architecture and Code Optimization, 2004
- Cache performance of the SPEC92 benchmark suiteIEEE Micro, 1993