energy model for multiprocess applications

12
Energy Model for Multiprocess Applications Texas Tech University

Upload: john

Post on 25-Feb-2016

20 views

Category:

Documents


2 download

DESCRIPTION

Texas Tech University. Energy Model for Multiprocess Applications. Faster Computers = More Energy. Texas Tech University. Moore’s law predicted 2 fold yearly increase in transistor count for inexpensive devices - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Energy Model for Multiprocess Applications

Energy Model for Multiprocess Applications

Texas Tech University

Page 2: Energy Model for Multiprocess Applications

Faster Computers = More Energy• Moore’s law predicted 2 fold yearly increase

in transistor count for inexpensive devices• Transistor size has decreased to the point

where size can longer be major factor in speed• Multicore processors now fairly common• Increased performance from larger transistor

counts and multiple cores has increased energy usage

Texas Tech University

Page 3: Energy Model for Multiprocess Applications

Faster Computers = More Energy• An hour of usage on a super computer today

uses the same amount of energy that a moderate home will during the most extreme months of the year

• Google estimates their data centers use the same amount of power as 200,000 homes each year.

Texas Tech University

Page 4: Energy Model for Multiprocess Applications

Energy Aware Motivations• Energy Costs• Device Battery Life• Green Computing Initiatives

Texas Tech University

Page 5: Energy Model for Multiprocess Applications

Energy Aware Research

• Most work being done in hardware design• CPUs now have multiple operating states to save

energy when not in use• Advanced Control Power Interface(ACPI) was

developed to give Operating Systems the ability to reduce power consumption of computers

• Most models & scheduling techniques rely on altering CPU operating frequency, which user applications cannot directly access

Texas Tech University

Page 6: Energy Model for Multiprocess Applications

CPU Energy Usage

• Energy is the amount of power used for a specified amount of time,

• If the power varies with time then, • With N processors, the total energy is the sum

of each processor’s usage,

Texas Tech University

Page 7: Energy Model for Multiprocess Applications

CPU Energy Usage (continued)

• The electrical power of a CPU is estimated as , is a physical constant and F is the operating frequency.

• As the frequency of a processor can vary with time, the energy usage of a multicore processor is

• CPUs only operate at S number of frequencies, • Developers cannot select the frequency of the CPU,

only if it is idle or not, so there are only 2 frequencies we consider, ON & OFF,

Texas Tech University

Page 8: Energy Model for Multiprocess Applications

Sequential Application Energy

• Sequential Applications only use 1 processor, so the other (N-1) processors are idle.

• The energy usage is reduced to

Texas Tech University

Page 9: Energy Model for Multiprocess Applications

Amdahl’s Law• Can be used to give a comparison between

sequential & parallel application performance• For this model, it gives us , the ratio of the

sequential energy usage to the parallel energy usage on an N processor system.

• is constant, so

Texas Tech University

Page 10: Energy Model for Multiprocess Applications

Observations

• Increasing CPU utilization increases Energy Efficiency

• “Racing to idle” means that the CPU will return to an idle state sooner

• Less time executing also means other components will be using less energy too

Texas Tech University

Page 11: Energy Model for Multiprocess Applications

Turning Off Idle Processors

• If is zero, then a parallel application uses the same power as its sequential version

• If runtime is fixed, additional processors are unnecessary

• Idle CPUs are not turned off and only waste energy

• Newer devices have too many CPUs, i.e. Smart Cell Phones

Texas Tech University

Page 12: Energy Model for Multiprocess Applications

No Idle Power States

• If , then = • Should only happen if power management

settings set incorrectly or poorly• Optimization only way to increase energy

efficiency

Texas Tech University