TILTS: A Fast Architectural-Level Transient Thermal Simulation Method

被引:37
|
作者
Han, Yongkui [1 ]
Koren, Israel [1 ]
Krishna, C. M. [1 ]
机构
[1] Univ Massachusetts, Dept ECE, Amherst, MA 01002 USA
关键词
Thermal Simulation; Fast Method; Linear System; Performance Counters; Runtime Temperature Monitoring;
D O I
10.1166/jolpe.2007.106
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
As power density of microprocessors is increasing rapidly and resulting in high temperatures, the reliability of chips is greatly affected, making thermal simulation a necessity for CPU designs. Current thermal simulation methods (for example, the HotSpot simulator) are very useful, but are still inefficient when performing thermal analysis for long simulation times. In this paper, we propose a novel transient thermal simulation method for CPU chips at the architecture level, TILTS(Time Invariant Linear Thermal System), which utilizes the fact that the input power trace is discretized over a fixed sampling interval to accelerate thermal simulations. TILTSallo ws us to calculate transient temperatures on a chip over long simulation times. Based on a linear system formulation, TILTShas the same accuracy as that of traditional thermal simulation tools and is orders of magnitude faster than previous algorithms. Compared to the HotSpot simulator, TILTS achieves speedups of 1300 for the processors in our experiments for an appropriate sampling interval of 100 mu s. With some additional memory space, the improved algorithm CONTILTS(Con volutional TILTS) is about 6000 times faster than the HotSpot simulator for the processors in our experiments.
引用
收藏
页码:13 / 21
页数:9
相关论文
共 50 条
  • [1] Using architectural-level tools to estimate power
    Frenkil, J
    COMPUTER DESIGN, 1996, 35 (10): : 127 - &
  • [2] Architectural-Level Prediction of Interconnect Wirelength and Fanout
    Jeong, Kwangok
    Kahng, Andrew B.
    Samadi, Kambiz
    2009 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC 2009), 2009, : 53 - 56
  • [3] Architectural-level metrics for software systems
    Zhao, JJ
    COMPUTER SCIENCE AND TECHNOLOGY IN NEW CENTURY, 2001, : 29 - 33
  • [4] Evaluating the impact of architectural-level optimizations on clockpower
    Duarte, D
    Narayanan, V
    Irwin, MJ
    Kandemir, M
    14TH ANNUAL IEEE INTERNATIONAL ASIC/SOC CONFERENCE, PROCEEDINGS, 2001, : 447 - 451
  • [5] The Gadfly: An approach to architectural-level system comprehension
    Clements, P
    Krut, R
    Morris, E
    Wallnau, K
    FOURTH WORKSHOP ON PROGRAM COMPREHENSION, PROCEEDINGS, 1996, : 178 - 186
  • [6] Architectural-level risk analysis using UML
    Goseva-Popstojanova, K
    Hassan, A
    Guedem, A
    Abdelmoez, W
    Nassar, DEM
    Ammar, H
    Mili, A
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2003, 29 (10) : 946 - 960
  • [7] Architectural-level fault tolerant computation in nanoelectronic processors
    Rao, WJ
    Orailoglu, A
    Karri, R
    2005 IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN: VLSI IN COMPUTERS & PROCESSORS, PROCEEDINGS, 2005, : 533 - 539
  • [8] Wattch: A framework for architectural-level power analysis and optimizations
    Brooks, D
    Tiwari, V
    Martonosi, M
    PROCEEDING OF THE 27TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, 2000, : 83 - 94
  • [9] Parallel GPU Architecture Simulation Framework Exploiting Architectural-Level Parallelism with Timing Error Prediction
    Lee, Sangpil
    Ro, Won Woo
    IEEE TRANSACTIONS ON COMPUTERS, 2016, 65 (04) : 1253 - 1265
  • [10] Architectural-level synthesis of digital microfluidics-based biochips
    Su, F
    Chakrabarty, K
    ICCAD-2004: INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, IEEE/ACM DIGEST OF TECHNICAL PAPERS, 2004, : 223 - 228