Coupled Power and Thermal Simulation with Active Cooling

Power is rapidly becoming the primary design constraint for systems ranging from server computers to handhelds. In this paper we study microarchitecture-level coupled power and thermal simulation considering dynamic and leakage power models with temperature and voltage scaling. We develop an accurate temperature-dependent leakage power model and efficient temperature calculation, and show that leakage energy can be different by up to 10X for temperatures between 35°C and 110°C. Given the growing significance of leakage power and its sensitive dependence on temperature, no power simulation without considering dynamic temperature calculation is accurate. Furthermore, we discuss the thermal runaway induced by the interdependence between leakage power and temperature, and show that in the near future thermal runaway could be a severe problem. We also study the microarchitecture level coupled power and thermal management by novel active cooling techniques that reduce packaging thermal resistance. We show that the direct water-spray cooling technique reduces thermal resistance from 0.8°C/W for conventional packaging to 0.05°C/W, and increases system maximum clock by up to 2.44X under the same thermal constraints.

[1]  G. Sohi,et al.  A static power model for architects , 2000, Proceedings 33rd Annual IEEE/ACM International Symposium on Microarchitecture. MICRO-33 2000.

[2]  Kevin Skadron,et al.  Temperature-aware microarchitecture , 2003, ISCA '03.

[3]  Lei He,et al.  Microarchitecture level power and thermal simulation considering temperature dependent leakage model , 2003, Proceedings of the 2003 International Symposium on Low Power Electronics and Design, 2003. ISLPED '03..

[4]  M. C. Shaw,et al.  Enhanced thermal management by direct water spray of high-voltage, high power devices in a three-phase, 18-hp AC motor drive demonstration , 2002, ITherm 2002. Eighth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (Cat. No.02CH37258).

[5]  Mahmut T. Kandemir,et al.  The design and use of simplePower: a cycle-accurate energy estimation tool , 2000, Proceedings 37th Design Automation Conference.

[6]  H. B. Bakoglu,et al.  Circuits, interconnections, and packaging for VLSI , 1990 .

[7]  T.H. Lee,et al.  A 600 MHz superscalar RISC microprocessor with out-of-order execution , 1997, 1997 IEEE International Solids-State Circuits Conference. Digest of Technical Papers.

[8]  Lei He,et al.  Leakage power modeling and reduction with data retention , 2002, IEEE/ACM International Conference on Computer Aided Design, 2002. ICCAD 2002..

[9]  Shin'ichiro Mutoh,et al.  1-V power supply high-speed digital circuit technology with multithreshold-voltage CMOS , 1995, IEEE J. Solid State Circuits.

[10]  Norman P. Jouppi,et al.  Cacti 3. 0: an integrated cache timing, power, and area model , 2001 .

[11]  Vivek Tiwari,et al.  Reducing power in high-performance microprocessors , 1998, Proceedings 1998 Design and Automation Conference. 35th DAC. (Cat. No.98CH36175).

[12]  William J. Bowhill,et al.  Design of High-Performance Microprocessor Circuits , 2001 .

[13]  R.W. Brodersen,et al.  A dynamic voltage scaled microprocessor system , 2000, IEEE Journal of Solid-State Circuits.

[14]  Stefan Rusu,et al.  A 1.5GHz third generation Itanium 2 processor , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[15]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[16]  Vikas Agarwal,et al.  Static energy reduction techniques for microprocessor caches , 2001, Proceedings 2001 IEEE International Conference on Computer Design: VLSI in Computers and Processors. ICCD 2001.

[17]  Kevin Skadron,et al.  Control-theoretic techniques and thermal-RC modeling for accurate and localized dynamic thermal management , 2002, Proceedings Eighth International Symposium on High Performance Computer Architecture.

[18]  W. Robert Daasch,et al.  TEM2P2EST: A Thermal Enabled Multi-model Power/Performance ESTimator , 2000, PACS.