Voltage Emergency Prediction: Using Signatures to Reduce Operating - - PowerPoint PPT Presentation

▶
voltage emergency prediction using signatures to reduce
SMART_READER_LITE
LIVE PREVIEW

Voltage Emergency Prediction: Using Signatures to Reduce Operating - - PowerPoint PPT Presentation

Mar 14, 2024 28 likes •267 views

Voltage Emergency Prediction: Using Signatures to Reduce Operating Margins Vijay Janapa Reddi, Meeta S. Gupta, Glenn Holloway, Gu-Yeon Wei, Michael D. Smith, David Brooks Presented by: Divya Ramesh and John Chung 1 Why Do We Care? Feature

slide-1
SLIDE 1

Voltage Emergency Prediction: Using Signatures to Reduce Operating Margins

Vijay Janapa Reddi, Meeta S. Gupta, Glenn Holloway, Gu-Yeon Wei, Michael D. Smith, David Brooks

1

Presented by: Divya Ramesh and John Chung

slide-2
SLIDE 2

Why Do We Care?

  • Feature size reduction => increased sensitivity to voltage fluctuations
  • Voltage fluctuations cause timing issues and reduce transistor lifetimes
  • Conservative operating margins lead to degraded performance
  • Timing margins can be up to 20% of supply voltage

2

slide-3
SLIDE 3

Proposed Solutions

  • Voltage Emergency Prediction
  • Signature-based Voltage Emergency Reduction
  • Efficient Predictor Implementation

3

slide-4
SLIDE 4

Previous Work and Limitations

4

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-5
SLIDE 5

Goals

5

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-6
SLIDE 6

A 10,000 FT View

6

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-7
SLIDE 7

How Does it Work?

I know nothing...

7

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-8
SLIDE 8

How Does it Work?

I know nothing... Emergency!

8

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-9
SLIDE 9

How Does it Work?

Emergency! Predictor needs to remember this moment... Recover, Resume execution

9

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-10
SLIDE 10

How Does it Work?

Predictor needs to remember this moment... Recover, Resume execution Roger that!

10

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-11
SLIDE 11

How Does it Work?

I can prevent it!

Eme….!

11

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-12
SLIDE 12

What Does the Predictor Need to Know?

Flush in 2 causes an emergency sometimes, but does not other times.

12

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-13
SLIDE 13

Flush in 2 causes an emergency sometimes, but does not other times. Combination of contexts can signal the future emergency!

13

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

What Does the Predictor Need to Know?

slide-14
SLIDE 14

Flush in 2 sometimes causes emergency, but sometimes does not → Combination of contexts can signal the future emergency!

Voltage emergencies are quite repetitive and stable thus enabling their PREDICTION!

14

slide-15
SLIDE 15

How Do We Get Predictions?

  • Predict possible emergencies from event history register
  • Capture interleaved sequence of control flow instructions and architectural

events that give rise to an emergency

15

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-16
SLIDE 16

Contents of Signals for Prediction

  • Program Control Flow : Out-of-Order Issue > In-order Fetch and Decode >

In-order Commit

  • Microarchitectural events increase the accuracy even more!

16

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-17
SLIDE 17

Size of Entries for Prediction

More entries => better accuracy. But, cost of prediction might get expensive!

17

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

Signature size =4

slide-18
SLIDE 18

Hardware Overhead Reduction

  • Signature encoding: 3 bit encoding + Anchor PC (the program counter for

the most recently taken branch)

  • Signature compaction: Measure similarity with Manhattan distance →

compact signatures with similarity higher than 0.9

○ 67% signature reduction for 403. gcc

18

slide-19
SLIDE 19

Predictor Accuracy Evaluation

19

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-20
SLIDE 20

Comparison of Schemes

20

Reddi, Vijay Janapa, et al. "Voltage emergency prediction: Using signatures to reduce operating margins." High Performance Computer Architecture, 2009. HPCA 2009. IEEE 15th International Symposium on. IEEE, 2009.

slide-21
SLIDE 21

Discussion (1)

Voltage emergency prediction suffers from cold-start problem, which requires that the chip to first experience emergency before the predictor can learn predictions.

  • Is the cold-start problem be trivial, with no need to be cared?
  • Can we pre-train the predictor to avoid cold-start problem?

21

slide-22
SLIDE 22

Discussion (2)

Compare checkpoint recovery schemes with prediction-based throttling schemes.

  • What are some of the advantages and disadvantages of each approach?

22

slide-23
SLIDE 23

Discussion (3)

Does the velocity of voltage drop matter?

  • Does voltage drop differ between different types of emergencies?
  • Can this technique consider the velocity of the voltage drop?

23