Leakage Energy Management in Cache Hierarchies

1
Leakage Energy Management in Cache Hierarchies
PACT-2002 Charlottesville, Virginia September
22-25, 2002

• L. Li, I. Kadayif, Y-F. Tsai, N. Vijaykrishnan,
  M. Kandemir,
• M. J. Irwin, and A. Sivasubramaniam Penn State
  University
• http//www.cse.psu.edu/mdl

2
Outline

• Motivation
• Related works
• Circuit support for leakage control
• Leakage optimization strategies
• Integration with other strategies
• Conclusion
• Future works

3
Motivation

• Leakage energy is projected to become the
  dominant portion of the chip power budget for
  0.10 micron technology and below.
• A. Chandrakasan et al., Design of
  High-Performance Microprocessor Circuits.
• Leakage energy is of particular concern in dense
  cache memories that form a major portion of the
  transistor budget.

4
Related Works

• M. D. Powell et al.
• An integrated circuit/architecture approach to
  reducing leakage in deep-submicron
  high-performance I-caches.(HPCA-7)
• S. Kaxiras et al.
• Cache decay exploiting generational behavior to
  reduce cache leakage power. (ISCA-28)
• H. Zhou et al.
• Adaptive mode control A static-power-efficient
  cache design. (PACT01)
• K. Flautner et al.
• Drowsy caches Simple techniques for reducing
  leakage power. (ISCA-29)
• Y-F. Tsai et al.
• A sizing model for SRAM data preserving sleep
  transistors. (ASIC02)

5
Circuit Support for Leakage Control

• State-destroying mechanism. (Gated-Vdd)
• Introduce a power-switch between the ground and
  the circuit to reduce leakage.
• Sizing to maximize the static power saving but
  lose data in cells.
• State-preserving mechanism. (Modified Gated-Vdd)
• Appropriately sizing NMOS power-switch to provide
  the required minimum supply voltage to maintain
  the state of a static memory cell.

6
State-preserving Leakage Control
7
Leakage Optimization Strategies

• Employ state-destroying or state-preserving
  mechanisms in cache.
• For single block, state-destroying mechanism
  saves more leakage energy than state-preserving
  mechanism.
• For whole cache hierarchies, state-destroying
  mechanism pays a higher miss penalty.
• Exploit data duplication in the cache hierarchy.
• Data duplication data in L2 subblocks also exist
  in L1 blocks.
• Implement five leakage reduction strategies.

8
Leakage Optimization Strategies (II)
9
Conservative
L1
L2

• Only deactivate dead L2 subblocks.
• Before written in L1, both two copies of data are
  in active mode.

10
Speculative-I
L1
L2

• Put L2 subblock in state-preserving mode when
  data is brought from L2 to L1.
• Not lose data in L2 and need time to reactivate
  L2 subblock when re-access.

11
Speculative-II
L1
L2

• Put L2 subblock in state-destroying mode when
  data is brought from L2 to L1.
• Lose data in L2 and need longer time to load
  data from main memory when re-access.

12
Speculative-III
L1
L2

• Similar to Speculative-I except that L2 subblock
  reactivated when L1 block is replaced.
• Hide reactivation time.

13
Speculative-IV
L1
L2

• Similar to Speculative-II except that L2 subblock
  is written back when L1 block is replaced.

14
Experimental Configuration
15
Result of Energy Saving
Conservative Speculative-I Speculative-II
Speculative-III Speculative-IV
16
Result of Energy-delay Saving
Conservative Speculative-I Speculative-II
Speculative-III Speculative-IV
17
Average Saving of Five Strategies
18
Integration With Other Strategies

• Cache decay
• Exploiting generational behavior and use
  state-destroying mechanism to reduce cache
  leakage energy.
• Implement four strategies

19
Result of Energy Saving
Decay-I Decay-II Speculative-Decay-I Speculative
-Decay-II
20
Result of Energy-delay Saving
Decay-I Decay-II Speculative-Decay-I Speculative-D
ecay-II
21
Average Savings of Strategies
22
Conclusion

• Duplication of data at different levels of memory
  hierarchy is costly from the leakage energy
  perspective.
• Applying state-preserving leakage control
  strategy to L2 cache can reduce energy
  consumption significantly.
• Our strategies can be combined with other
  techniques to provide additional energy gains.

23
Future Works

• More powerful combined optimization strategies.
• Combining state-preserving and state-destroying
  strategies.
• Software-based leakage optimization.
• Integrating hardware-based and software-based
  strategies.

24
Thanks !