Temperature aware microprocessor floorplanning considering application dependent power load

Authors:
Chun-Ta Chu;Xinyi Zhang;Lei He;Tom Tong Jing
Affiliations:
University of California at Los Angeles, CA;University of California at Los Angeles, CA;University of California at Los Angeles, CA;University of California at Los Angeles, CA
Venue:
Proceedings of the 2007 IEEE/ACM international conference on Computer-aided design
Year:
2007

Citing 7
Cited 1

Algorithms for VLSI Design Automation

Algorithms for VLSI Design Automation
SPEC CPU2000: Measuring CPU Performance in the New Millennium

Computer
Profile-guided microarchitectural floorplanning for deep submicron processor design

Proceedings of the 41st annual Design Automation Conference
Floorplanning optimization with trajectory piecewise-linear model for pipelined interconnects

Proceedings of the 41st annual Design Automation Conference
Microarchitecture evaluation with floorplanning and interconnect pipelining

Proceedings of the 2005 Asia and South Pacific Design Automation Conference
Temperature-aware floorplanning of microarchitecture blocks with IPC-power dependence modeling and transient analysis

Proceedings of the 2006 international symposium on Low power electronics and design
Temperature and supply Voltage aware performance and power modeling at microarchitecture level

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

Recent thermal management techniques for microprocessors

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper studies microprocessor floorplanning considering thermal and throughput optimization. We first develop a stochastic heat diffusion model taking into account the application dependent power load for thermal analysis. Then, we design the floorplanning algorithm based on this model. Experimental results show that, compared with the deterministic heat diffusion model, our model obtains up to 3.2°C reduction of the on-chip peak temperature, 1.25% reduction of the area, and 1.125x better CPI (cycles per instruction) performance, respectively. Compared with temperature aware floorplanning in the HOTSPOT tool set that ignores interconnect pipelining, our algorithm is up to 27x faster, reduces the peak temperature by up to 3°C, and also reduces CPI significantly with a negligible area overhead.