Dynamic frequency scaling
Encyclopedia
Dynamic frequency scaling (also known as CPU throttling) is a technique in computer architecture
whereby the frequency
of a microprocessor can be automatically adjusted "on the fly," either to conserve power
or to reduce the amount of heat generated by the chip. Dynamic frequency scaling is commonly used in laptop
s and other mobile devices, where energy comes from a battery and thus is limited. It is also used in quiet computing settings
and to decrease energy and cooling costs for lightly loaded machines. Less heat output, in turn, allows the system cooling fans to be throttled down or turned off, reducing noise levels and further decreasing power consumption. It is also used for reducing heat in insufficiently cooled systems when the temperature reaches a certain threshold, such as in poorly cooled overclocked systems.
The dynamic power (switching power) dissipated by a chip is C·V2·f, where C is the capacitance
being switched per clock cycle, V is voltage
, and f is the switching frequency (as a unitless quantity). As frequency changes, the dynamic power will change linearly with it. Dynamic power does not account the total power of the chip however, as there is also static power, which is primarily due to various leakage currents. Leakage current
has become more and more important as feature sizes has become smaller and threshold levels lower. In state-of-the-art deep submicrometre technologies in 2008, dynamic power accounts for approximately two-thirds of the total chip power, which limits the effectiveness of frequency scaling.
Dynamic voltage scaling
is another power conservation technique that is often used in conjunction with frequency scaling, as the frequency that a chip may run at is related to the operating voltage.
The efficiency of some electrical components, such as voltage regulators, decreases with increasing temperature, so the power used may increase with temperature. Since increasing power use may increase the temperature, increases in voltage or frequency may increase system power demands even further than the CMOS formula indicates, and vice-versa.
Dynamic frequency scaling by itself is rarely worthwhile as a way to conserve switching power. Saving the most power requires dynamic voltage scaling too, because of the V2 component and the fact that modern CPUs are strongly optimized for low power idle states. In most constant-voltage cases it is more efficient to run briefly at peak speed and stay in a deep idle state for longer (called "race to idle"), than it is to run at a reduced clock rate for a long time and only stay briefly in a light idle state. However, reducing voltage along with clock rate can change those tradeoffs.
A related-but-opposite technique is overclocking
, whereby processor performance is increased by ramping the processor's (dynamic) frequency beyond the manufacturer's design specifications.
One major difference between the two is that in modern PC systems overclocking is mostly done over the Front Side Bus
(mainly because the multiplier is normally locked), but dynamic frequency scaling is done with the multiplier
. Moreover, overclocking is often static, while dynamic frequency scaling is always dynamic. Software can often incorporate overclocked frequencies into the frequency scaling algorithm, if the chip degradation risks are allowable.
, is used in its mobile CPU line. AMD employs two different CPU throttling technologies. AMD's Cool'n'Quiet
technology is used on its desktop and server processor lines. The aim of Cool'n'Quiet is not to save battery life, as it is not used in AMD's mobile processor line, but instead with the purpose of producing less heat, which in turn allows the system fan to spin down to slower speeds, resulting in cooler and quieter operation, hence the name of the technology. AMD's PowerNow!
CPU throttling technology is used in its mobile processor line, though some supporting CPUs like the AMD K6-2+
can be found in desktops as well.
According to the ACPI
Specs, the C0 working state of a modern-day CPU can be divided into the so called "P"-states (performance states) which allow clock rate reduction and "T"-states (throttling states) which will further throttle down a CPU (but not the actual clock rate) by inserting STPCLK (stop clock) signals and thus omitting duty cycles.
Computer architecture
In computer science and engineering, computer architecture is the practical art of selecting and interconnecting hardware components to create computers that meet functional, performance and cost goals and the formal modelling of those systems....
whereby the frequency
Clock rate
The clock rate typically refers to the frequency that a CPU is running at.For example, a crystal oscillator frequency reference typically is synonymous with a fixed sinusoidal waveform, a clock rate is that frequency reference translated by electronic circuitry into a corresponding square wave...
of a microprocessor can be automatically adjusted "on the fly," either to conserve power
Power management
Power management is a feature of some electrical appliances, especially copiers, computers and computer peripherals such as monitors and printers, that turns off the power or switches the system to a low-power state when inactive. In computing this is known as PC power management and is built...
or to reduce the amount of heat generated by the chip. Dynamic frequency scaling is commonly used in laptop
Laptop
A laptop, also called a notebook, is a personal computer for mobile use. A laptop integrates most of the typical components of a desktop computer, including a display, a keyboard, a pointing device and speakers into a single unit...
s and other mobile devices, where energy comes from a battery and thus is limited. It is also used in quiet computing settings
Quiet PC
A quiet PC is a personal computer that makes little noise. Common uses for quiet PCs include video editing, sound mixing, home servers, and home theater PCs. A typical quiet PC uses quiet cooling and storage devices and energy-efficient parts....
and to decrease energy and cooling costs for lightly loaded machines. Less heat output, in turn, allows the system cooling fans to be throttled down or turned off, reducing noise levels and further decreasing power consumption. It is also used for reducing heat in insufficiently cooled systems when the temperature reaches a certain threshold, such as in poorly cooled overclocked systems.
The dynamic power (switching power) dissipated by a chip is C·V2·f, where C is the capacitance
Capacitance
In electromagnetism and electronics, capacitance is the ability of a capacitor to store energy in an electric field. Capacitance is also a measure of the amount of electric potential energy stored for a given electric potential. A common form of energy storage device is a parallel-plate capacitor...
being switched per clock cycle, V is voltage
Voltage
Voltage, otherwise known as electrical potential difference or electric tension is the difference in electric potential between two points — or the difference in electric potential energy per unit charge between two points...
, and f is the switching frequency (as a unitless quantity). As frequency changes, the dynamic power will change linearly with it. Dynamic power does not account the total power of the chip however, as there is also static power, which is primarily due to various leakage currents. Leakage current
Subthreshold leakage
The Subthreshold conduction or the subthreshold leakage or the subthreshold drain current is the current that flows between the source and drain of a MOSFET when the transistor is in subthreshold region, or weak-inversion region, that is, for gate-to-source voltages below the threshold voltage. The...
has become more and more important as feature sizes has become smaller and threshold levels lower. In state-of-the-art deep submicrometre technologies in 2008, dynamic power accounts for approximately two-thirds of the total chip power, which limits the effectiveness of frequency scaling.
Dynamic voltage scaling
Dynamic voltage scaling
Dynamic voltage scaling is a power management technique in computer architecture, where the voltage used in a component is increased or decreased, depending upon circumstances. Dynamic voltage scaling to increase voltage is known as overvolting; dynamic voltage scaling to decrease voltage is known...
is another power conservation technique that is often used in conjunction with frequency scaling, as the frequency that a chip may run at is related to the operating voltage.
The efficiency of some electrical components, such as voltage regulators, decreases with increasing temperature, so the power used may increase with temperature. Since increasing power use may increase the temperature, increases in voltage or frequency may increase system power demands even further than the CMOS formula indicates, and vice-versa.
Performance impact
Dynamic frequency scaling reduces the number of instructions a processor can issue in a given amount of time, thus reducing performance. Hence, it is generally used when the workload is not CPU-bound.Dynamic frequency scaling by itself is rarely worthwhile as a way to conserve switching power. Saving the most power requires dynamic voltage scaling too, because of the V2 component and the fact that modern CPUs are strongly optimized for low power idle states. In most constant-voltage cases it is more efficient to run briefly at peak speed and stay in a deep idle state for longer (called "race to idle"), than it is to run at a reduced clock rate for a long time and only stay briefly in a light idle state. However, reducing voltage along with clock rate can change those tradeoffs.
A related-but-opposite technique is overclocking
Overclocking
Overclocking is the process of operating a computer component at a higher clock rate than it was designed for or was specified by the manufacturer, but some manufacturers purposely underclock their components to improve battery life. Many people just overclock or 'rightclock' their hardware to...
, whereby processor performance is increased by ramping the processor's (dynamic) frequency beyond the manufacturer's design specifications.
One major difference between the two is that in modern PC systems overclocking is mostly done over the Front Side Bus
Front side bus
A front-side bus is a computer communication interface often used in computers during the 1990s and 2000s.It typically carries data between the central processing unit and a memory controller hub, known as the northbridge....
(mainly because the multiplier is normally locked), but dynamic frequency scaling is done with the multiplier
CPU multiplier
In computing, the clock multiplier measures the ratio of an internal CPU clock rate to the externally supplied clock. A CPU with a 10x multiplier will thus see 10 internal cycles for every external clock cycle...
. Moreover, overclocking is often static, while dynamic frequency scaling is always dynamic. Software can often incorporate overclocked frequencies into the frequency scaling algorithm, if the chip degradation risks are allowable.
Implementations
Intel's CPU throttling technology, SpeedStepSpeedStep
SpeedStep is a trademark for a series of dynamic frequency scaling technologies built into some Intel microprocessors that allow the clock speed of the processor to be dynamically changed by software...
, is used in its mobile CPU line. AMD employs two different CPU throttling technologies. AMD's Cool'n'Quiet
Cool'n'Quiet
Cool'n'Quiet is a CPU speed throttling and power saving technology introduced by AMD with its Athlon 64 processor line. It works by reducing the processor's clock rate and voltage when the processor is idle. The aim of this technology is to reduce overall power consumption and lower heat...
technology is used on its desktop and server processor lines. The aim of Cool'n'Quiet is not to save battery life, as it is not used in AMD's mobile processor line, but instead with the purpose of producing less heat, which in turn allows the system fan to spin down to slower speeds, resulting in cooler and quieter operation, hence the name of the technology. AMD's PowerNow!
PowerNow!
PowerNow! is speed throttling and power saving technology of AMD's processors used in laptops. The CPU's clock speed and VCore are automatically decreased when the computer is under low load or idle, to save battery power, reduce heat and noise...
CPU throttling technology is used in its mobile processor line, though some supporting CPUs like the AMD K6-2+
AMD K6-2
The K6-2 was an x86 microprocessor introduced by AMD on May 28, 1998, and available in speeds ranging from 266 to 550 MHz. An enhancement of the original K6, the K6-2 introduced AMD's 3D-Now! SIMD instruction set, featured a larger 64 KiB Level 1 cache , and an upgraded system-bus interface...
can be found in desktops as well.
According to the ACPI
Advanced Configuration and Power Interface
In computing, the Advanced Configuration and Power Interface specification provides an open standard for device configuration and power management by the operating system....
Specs, the C0 working state of a modern-day CPU can be divided into the so called "P"-states (performance states) which allow clock rate reduction and "T"-states (throttling states) which will further throttle down a CPU (but not the actual clock rate) by inserting STPCLK (stop clock) signals and thus omitting duty cycles.