1. Overview Motivation (Kevin) Thermal issues (Kevin)
Power modeling (David)
Thermal management (David)
Optimal DTM (Lev)
Clustering (Antonio)
Power distribution (David)
What current chips do (Lev)
HotSpot (Kevin)

2. Power and thermal management
What current chips do
Power and thermal management

3. Controllers Inputs (power, temperature, etc.) Response time Tuning
Simplicity of implementation
Performance, reliability
Power management / thermal management

4. Controllers (cont’d) ? A non-trivial tradeoff Performance Reliability
Cost

5. * Other names and brands may be claimed as the property of others
Real processors:
IBM* PowerPC* G3/G4 Cache throttling
AMD* PowerNow!* Technology
Transmeta* Longrun* technology
Intel® SpeedStep® technology
Enhanced Intel® SpeedStep technology
* Other names and brands may be claimed as the property of others

6. PowerPC G3 Microprocessor
On-chip temperature sensor (junction temperature)
Based on differential voltage change across 2 diodes of different sizes
Implemented in PowerPC G3/G4 processors
OS required for control
Instruction Cache Throttling used to dynamically lower junction temperature
From Micro-35 tutorial

7. Transmeta LongRun** LongRun power management Crusoe* processor***
Code Morphing* software (processor-internal)
Performance demands are determined by sampling the idle time
Crusoe* processor***
Voltage changes in steps of 25 mV
Frequency changes in steps of 33 MHz
*Other names and brands may be claimed as the property of others
** Source:
*** Data dated 2001

8. Transmeta LongRun (cont’d)
Idle time  decrement V&f
Activity  increment V&f (if possible)
Performance mode  V&f adjustment
Source:

9. Previous Intel microprocessors1
Thermal monitor mechanism
A two-point mechanism using voltage scaling (for battery life)
1Information on Intel microprocessors is based on Efraim Rotem’s presentation in the TACS workshop 06/2004

10. Thermal monitor Based on clock throttling
Full operational mode: maximal frequency
Minimal operation mode: clocks are stalled for a part of the duty cycle
Activation options:
By OS (e.g., ACPI)
By a special hardware

11. Static voltage scaling (for battery life)
Performance mode
Maximal frequency & Vcc
AC outlet or set by user
Power saving mode
Low frequency & Vcc
Upon request or while the user changed the usage mode

12. The Intel Pentium® M Processor
Targets the mobile market
Improved power efficiency
Advanced ACPI interface
Enhanced SpeedStep architecture

13. DVS in the Pentium M Processor
Changes both voltage and frequency at the runtime
Efficiently switches between different DVS control points

14. Thermal sensors Two thermal sensors
Maximal temperature reached  throttling
Critical shutdown point reached  shutdown

15. Operation modes Software control mechanism (e.g., ACPI) Self throttle
Track the junction temperature
Initiate the appropriate policy
Self throttle
Digital temperature detector initiates one of the power control cycles
Used as a fail-safe mechanism since it is much faster than the software

16. Enhanced Intel SpeedStep technology
Implements DVS
Upon a thermal trigger or SW request, CPU halts execution and locks PLL at a new frequency (a few msec)
Once finished, the Vcc starts changing to the new value (order of 1mV/msec)
Transition up is done in the reverse order

17. DVS cycle

18. DVS transitions
Frequency transition is fast enough to allow non-interrupted application execution
DVS transitions can be utilized for energy and thermal control during the normal operation flow
The target frequency and voltage are programmable by BIOS or OS
Support for multiple voltage/ frequency points

19. Adaptive policy (for battery life)
Uninterrupted power state transition
User selectable policy
Increases frequency on demand, and decreases power and frequency while idle for a long time

20. Info
More specific information on Pentium M will be available at Efraim Rotem’s presentation in the TACS workshop 06/2004

21. ACPI and OSPM1
ACPI = Advanced Configuration and Power Interface (an open industry specification)
OSPM = Operating System-directed configuration and Power Management
Cooling decisions are based on the application load and the thermal heuristics of the system
1Source: The ACPI specification 2.0, see

22. Cooling policies
Active cooling – a direct action by OSPM (e.g., turning on a fan)
Passive cooling – reducing the power consumption (e.g., throttling)
Critical trip points – shutdown

23. Example of SW-based clock throttling
DP[%] = _TC1 * (Tn – Tn-1) + _TC2 * (Tn –Tt)
Tn – current temperature
Tt – target temperature
Pn = Pn-1 + HW[-DP]
Pn is in %
The coefficients are set by the OEM