+ All Categories
Home > Documents > Predicting Performance Impact of DVFS for Realistic Memory Systems

Predicting Performance Impact of DVFS for Realistic Memory Systems

Date post: 22-Mar-2016
Category:
Upload: palila
View: 45 times
Download: 1 times
Share this document with a friend
Description:
Predicting Performance Impact of DVFS for Realistic Memory Systems. Rustam Miftakhutdinov Eiman Ebrahimi Yale N. Patt. Dynamic Voltage/Frequency Scaling. V. f. Image source: intel.com. Impact of Frequency Scaling. time. energy. power. f opt. frequency. Impact of Frequency Scaling. - PowerPoint PPT Presentation
Popular Tags:
31
Predicting Performance Impact of DVFS for Realistic Memory Systems Rustam Miftakhutdinov Eiman Ebrahimi Yale N. Patt
Transcript
Page 1: Predicting Performance Impact of DVFS for Realistic Memory Systems

Predicting Performance Impact of DVFSfor Realistic Memory Systems

Rustam MiftakhutdinovEiman Ebrahimi

Yale N. Patt

Page 2: Predicting Performance Impact of DVFS for Realistic Memory Systems

2

V

f

Dynamic Voltage/Frequency Scaling

Image source: intel.com

Page 3: Predicting Performance Impact of DVFS for Realistic Memory Systems

3

fopt

Impact of Frequency Scaling

frequency

time

power

energy

Page 4: Predicting Performance Impact of DVFS for Realistic Memory Systems

4

fo

Impact of Frequency Scaling

power

time

frequency

Page 5: Predicting Performance Impact of DVFS for Realistic Memory Systems

5

fopt

Prediction Overview

instructions

frequency

energy perinstruction

100K 200K 300K0

fo freq.

time

fo freq.

powerfo

fo freq.fopt

energy

our work

×

Page 6: Predicting Performance Impact of DVFS for Realistic Memory Systems

6

Outline

Intro to performance prediction

Why realistic memory systems?

Variable memory latency

Prefetching

Page 7: Predicting Performance Impact of DVFS for Realistic Memory Systems

7

V

f

Why Realistic Memory System?

Page 8: Predicting Performance Impact of DVFS for Realistic Memory Systems

8

Prior Work

• Stall time

• Leading loads (2010) S. Eyerman et al. G. Keramidas et al. B. Rountree

Evaluated withconstant access latency memory system

Page 9: Predicting Performance Impact of DVFS for Realistic Memory Systems

9

Energy Savings

Constant Access Latency

Realistic DRAM Realistic DRAM + Streaming Prefetcher

0123456789 Oracle

Stall timeLeading loadsOur predictor

Norm

. Ene

rgy

Savi

ngs

(%)

< 0.1

Gmean of relative savings for 13 memory-intensive SPEC 2006 benchmarks.Baseline: most energy-efficient static frequency for SPEC 2006

*

Page 10: Predicting Performance Impact of DVFS for Realistic Memory Systems

10

Energy Savings

Constant Access Latency

Realistic DRAM Realistic DRAM + Streaming Prefetcher

0123456789 Oracle

Stall timeLeading loadsOur predictor

Norm

. Ene

rgy

Savi

ngs

(%)

< 0.1

Gmean of relative savings for 13 memory-intensive SPEC 2006 benchmarks.Baseline: most energy-efficient static frequency for SPEC 2006

*

Page 11: Predicting Performance Impact of DVFS for Realistic Memory Systems

11

Outline

Intro to performance prediction

Why realistic memory systems?

Variable memory latency

Prefetching

✓✓

Page 12: Predicting Performance Impact of DVFS for Realistic Memory Systems

12

Execution Example

chipactivity

memoryrequests A

BC

DE

1 2 3 4time

Page 13: Predicting Performance Impact of DVFS for Realistic Memory Systems

13

T = Tmemory + Tcomputeindependent offrequency

proportional tocycle time

Page 14: Predicting Performance Impact of DVFS for Realistic Memory Systems

14

to

Linear Modelexecution time T

cycle time t

Tmemory

Tcompute

0

Page 15: Predicting Performance Impact of DVFS for Realistic Memory Systems

15

Measuring Tmemory

chipactivity

memoryrequests

time

Page 16: Predicting Performance Impact of DVFS for Realistic Memory Systems

16

Measuring Tmemory

chipactivity

memoryrequests

time

Page 17: Predicting Performance Impact of DVFS for Realistic Memory Systems

17

Causes of Request Dependences

next

next

next

Pointer Chasing

instruction window

miss miss

Finite Chip Resources

Page 18: Predicting Performance Impact of DVFS for Realistic Memory Systems

18

Measuring Tmemory

chipactivity

memoryrequests

time

Page 19: Predicting Performance Impact of DVFS for Realistic Memory Systems

Critical Path Algorithm

at Tstart 1. record Tstart and Tmemory

TendTstart time

Tmemory

19

at Tend 2. compute path = Tmemory(Tstart) + (Tend - Tstart)old critical path request latency

3. set Tmemory = max(Tmemory, path)

new Tmemory

(length of critical path)

Page 20: Predicting Performance Impact of DVFS for Realistic Memory Systems

20

to

Linear Modelexecution time T

cycle time t

Tmemory

Tcompute

0

Page 21: Predicting Performance Impact of DVFS for Realistic Memory Systems

21

Linear Model

to

execution time T

cycle time t

Tmemory

Tcompute

0

to cycletime

Tm

time

fo freq.

time

fo freq.

power

fo freq.fopt

energy

×

Page 22: Predicting Performance Impact of DVFS for Realistic Memory Systems

22

Critical Path: Variable Access Latency

chipactivity

memoryrequests

time

Leading Loads: Constant Access Latency

timechipactivity

memoryrequests

Page 23: Predicting Performance Impact of DVFS for Realistic Memory Systems

23

to

Leading Loadsexecution time T

cycle time t

Tmemory

Tcompute

0

leading loads

Page 24: Predicting Performance Impact of DVFS for Realistic Memory Systems

24

Leading Loads

to

execution time T

cycle time t

Tmemory

Tcompute

0

leading loads

to cycletime

Tm

time

fo freq.

time

fo freq.

power

fo freq.fopt

energy

×

Page 25: Predicting Performance Impact of DVFS for Realistic Memory Systems

25

Energy Savings

Constant Access Latency

Realistic DRAM0

1

2

3

4

5

6

7

8 OracleStall timeLeading loadsOur predictor

Norm

. Ene

rgy

Savi

ngs (

%)

Gmean of relative savings for 13 memory-intensive SPEC 2006 benchmarks.Baseline: most energy-efficient static frequency for SPEC 2006

*

Page 26: Predicting Performance Impact of DVFS for Realistic Memory Systems

26

Outline

Intro to performance prediction

Why realistic memory systems?

Variable memory latency

Prefetching

✓✓✓

Page 27: Predicting Performance Impact of DVFS for Realistic Memory Systems

27

chipactivity

memoryrequests

time

Prefetcher OFF

Prefetcher ON

chipactivity

memoryrequests

Streaming Workload

Page 28: Predicting Performance Impact of DVFS for Realistic Memory Systems

28

Limited Bandwidth Modelexecution time T

cycle time t

Tdemand

TcomputeTmemorymin

tcrossover0

Page 29: Predicting Performance Impact of DVFS for Realistic Memory Systems

Energy Savings

29Gmean of relative savings for 13 memory-intensive SPEC 2006 benchmarks.Baseline: most energy-efficient static frequency for SPEC 2006

*

Constant Access Latency

Realistic DRAM Realistic DRAM + Streaming Prefetcher

0123456789 Oracle

Stall timeLeading loadsOur predictor

Norm

. Ene

rgy

Savi

ngs

(%)

< 0.1

Page 30: Predicting Performance Impact of DVFS for Realistic Memory Systems

30

Recap

Intro to performance prediction

Why realistic memory systems?

Variable memory latency

Prefetching

✓✓✓✓

Page 31: Predicting Performance Impact of DVFS for Realistic Memory Systems

31

Final Thought

Performance predictors need realistic evaluation


Recommended