ECM 1413 Energy Efficient Computing

Question 1

The energy problem:

Answer 1

our sources of energy are steadily decreasing, whilst our demand for energy is steadily increasing

the emission of greenhouse gases is now seen

by most climatologists as being linked to global warming

Question 2

Rising Electricity demand by 2030

Answer 2

Electricity demand for information and communications technologies (ICT) might rise to 8% of total electricity demand by 2030, in the best case, or 21% in the worst case

Question 3

The technology developed by Intel, Microsoft, to combat high energy usage on current-day systems

Answer 3

The Advanced Configuration and Power Interface (ACPI)

Question 4

ACPI States

Answer 4

1 per-system power states G0-G3
2 per-device (disks, keyboards, etc.) power states D0-D3
3 per-processor power states C0-C3 (substates of G0)
4 per-device/processor performance states P0-P15 (substates of D0/C0)

The G0, D0, C0, and P0 states have normal power consumption; others have successively lower power consumption.

Question 5

Global State G0 Name

Answer 5

Powered on

Question 6

Global State G1 Name

Answer 6

Sleeping

Question 7

Global State G2 Name

Answer 7

Powered off

Question 8

Global State G3 Name

Answer 8

Unplugged

Question 9

Sleep State S0 Description

Answer 9

Standard operation

Question 10

Sleep state S1 Description

Answer 10

CPU stops running. CPU caches are shut down. Lower power states of hardware devices

Question 11

Sleep state S2 Description

Answer 11

CPU Powered off

Question 12

Sleep state S3 Description

Answer 12

Shut down more devices. Makes it harder for devices to wake the system

Question 13

Sleep state S4 description

Answer 13

Save memory to disk and shut down memory

Question 14

Device state D0 Description

Answer 14

Fully operational

Question 15

Device states D1, D2 description

Answer 15

Intermediate states (optional)

Question 16

Device state D3 Description

Answer 16

Device is off

Question 17

Processor State C0 Description

Answer 17

Fully operational

Question 18

Processor State C1 Description

Answer 18

The processor stops executing instructions. Caches are maintained. Short wake time. Must wake when receiving an interrupt

Question 19

Processor states C2, C3 Description

Answer 19

Similar to C1 but deeper sleep and longer wait time (optional)

Question 20

Performance States P0 -> P15

Answer 20

A processor could save energy by scaling down the power and clock frequency (P0 ⇒ P1, . . . , P15).

Question 21

Device power states differ in terms of

Answer 21

Power consumption
Device context retainment
Device driver behavior
Restore time Wake-up capability

Most transitions go to or from D0.

Question 22

Magnetic Disks saving energy

Answer 22

A magnetic disk could save energy by
turning off spindle motor (D0 ⇒ D1)
turning off controller (D0 ⇒ D3)

Question 23

Keyboards saving energy

Answer 23

A keyboard could save energy by
only providing wake functionality, turning off indicator lamps, while preserving device context such as the state of lock keys (D0 ⇒ D1)
turning off when not needed (D0 ⇒ D3)

Question 24

Processor states are applied to individual cores
Synergy effects occur when…

Answer 24

… shutting down multiple cores within the same domain/processor/computer since you then can also shut down resources that these cores share

Smartphones have both high-performance cores and energy-saving cores, and can apply different processor states to these

Question 25

Traditional Cloud Data Centres PUE

Answer 25

Traditional cloud data centres using off-the-shelf components have a Power Usage Effectiveness (PUE) of 2.0, far from a perfect 1.0.

Question 26

Hyperscale Cloud Data Centres

Answer 26

The Open Compute Project is driven by large companies that have an interest in building more efficient data centres.
The project shares designs and best practices on data centres at no cost.

Hyperscale cloud data centres using Open Compute Project components have a Power Usage Effectiveness (PUE) of 1.2, close to a perfect 1.0.
One Open Compute Project server replaces 3.75 traditional ones.

Question 27

Among the ways to lower power usage effectiveness are:

Answer 27

1 bespoke hardware
larger processors, more memory, more disk storage, remove graphics cards, lights, etc.
2 smarter cooling
use locations with a cold climate
3 mobile computing
let mobile devices do a larger share of the work