Jump to content

Clock rate

From Wikipedia, the free encyclopedia
(Redirected fromClock speed)
Microprocessor clock speed measures the number of pulses per second generated by an oscillator that sets the tempo for the processor. It is measured in hertz (pulses per second).

Incomputing,theclock rateorclock speedtypically refers to thefrequencyat which theclock generatorof aprocessorcan generatepulses,which are used tosynchronizethe operations of its components,[1]and is used as an indicator of the processor's speed. It is measured in theSIunit of frequencyhertz(Hz).

The clock rate of the first generation of computers was measured in hertz or kilohertz (kHz), the firstpersonal computers(PCs) to arrive throughout the 1970s and 1980s had clock rates measured in megahertz (MHz), and in the 21st century the speed of modernCPUsis commonly advertised in gigahertz (GHz). This metric is most useful when comparing processors within the same family, holding constant other features that may affectperformance.

Determining factors[edit]

Binning[edit]

Representation of a clock signal and clock rate

Manufacturers of modern processors typically charge higher prices for processors that operate at higher clock rates, a practice calledbinning.For a given CPU, the clock rates are determined at the end of the manufacturing process through testing of each processor. Chip manufacturers publish a "maximum clock rate" specification, and they test chips before selling them to make sure they meet that specification, even when executing the most complicated instructions with the data patterns that take the longest to settle (testing at the temperature and voltage that gives the lowest performance). Processors successfully tested for compliance with a given set of standards may be labeled with a higher clock rate, e.g., 3.50 GHz, while those that fail the standards of the higher clock rate yet pass the standards of a lower clock rate may be labeled with the lower clock rate, e.g., 3.3 GHz, and sold at a lower price.[2][3]

Engineering[edit]

The clock rate of a CPU is normally determined by thefrequencyof anoscillator crystal.Typically a crystal oscillator produces a fixedsine wave—the frequency reference signal. Electronic circuitry translates that into asquare waveat the same frequency for digital electronics applications (or, when using aCPU multiplier,some fixed multiple of the crystal reference frequency). Theclock distribution networkinside the CPU carries thatclock signalto all the parts that need it. AnA/D Converterhas a "clock" pin driven by a similar system to set thesampling rate.With any particular CPU, replacing the crystal with another crystal that oscillates at half the frequency ( "underclocking") will generally make the CPU run at half the performance and reducewaste heatproduced by the CPU. Conversely, some people try to increase performance of a CPU by replacing the oscillator crystal with a higher frequency crystal ( "overclocking").[4]However, the amount of overclocking is limited by the time for the CPU to settle after each pulse, and by the extra heat created.

After each clock pulse, the signal lines inside the CPU need time to settle to their new state. That is, every signal line must finish transitioning from 0 to 1, or from 1 to 0. If the next clock pulse comes before that, the results will be incorrect. In the process of transitioning, some energy is wasted as heat (mostly inside the driving transistors). When executing complicated instructions that cause many transitions, the higher the clock rate the more heat produced. Transistors may be damaged by excessive heat.

There is also a lower limit of the clock rate, unless a fullystatic coreis used.

Historical milestones and current records[edit]

The first fully mechanical analog computer, theZ1,operated at 1 Hz (cycle per second) clock frequency and the first electromechanical general purpose computer, theZ3,operated at a frequency of about 5–10 Hz. The first electronic general purpose computer, theENIAC,used a 100 kHz clock in its cycling unit. As each instruction took 20 cycles, it had an instruction rate of 5 kHz.

The first commercial PC, theAltair 8800(by MITS), used an Intel 8080 CPU with a clock rate of 2 MHz (2 million cycles per second). The originalIBM PC(c. 1981) had a clock rate of 4.77 MHz (4,772,727 cycles per second). In 1992, both Hewlett-Packard and Digital Equipment Corporation (DEC) exceeded 100 MHz withRISCtechniques in the PA-7100 and AXP 21064DEC Alpharespectively. In 1995,Intel'sP5Pentiumchip ran at 100 MHz (100 million cycles per second). On March 6, 2000,AMDdemonstrated passing the 1 GHz milestone a few days ahead of Intel shipping 1 GHz in systems. In 2002, an IntelPentium 4model was introduced as the first CPU with a clock rate of 3 GHz (three billion cycles per second corresponding to ~ 0.33nanosecondsper cycle). Since then, the clock rate of production processors has increased more slowly, with performance improvements coming from other design changes.

Set in 2011, theGuinness World Recordfor the highest CPU clock rate is 8.42938 GHz with anoverclockedAMD FX-8150Bulldozer-based chip in anLHe/LN2cryobath, 5 GHzon air.[5][6]This is surpassed by theCPU-Zoverclockingrecord for the highest CPU clock rate at 8.79433 GHz with an AMD FX-8350Piledriver-based chip bathed inLN2,achieved in November 2012.[7][8]It is also surpassed by the slightly slower AMD FX-8370 overclocked to 8.72 GHz which tops off theHWBOTfrequency rankings.[9][10]These records were broken in late 2022 when an Intel Core i9-13900K was overclocked to 9.008 GHz.[11]

The highestbase clockrate on a production processor is thei9-14900KS,clocked at 6.2 GHz, which was released in Q1 2024[12].

Research[edit]

Engineers continue to find new ways to design CPUs that settle a little more quickly or use slightly less energy per transition, pushing back those limits, producing new CPUs that can run at slightly higher clock rates. The ultimate limits to energy per transition are explored inreversible computing.

The first fully reversible CPU, the Pendulum, was implemented using standard CMOS transistors in the late 1990s at the Massachusetts Institute of Technology.[13][14][15][16]

Engineers also continue to find new ways to design CPUs so that they complete more instructions per clock cycle, thus achieving a lowerCPI(cycles or clock cycles per instruction) count, although they may run at the same or a lower clock rate as older CPUs. This is achieved through architectural techniques such asinstruction pipeliningandout-of-order executionwhich attempts to exploitinstruction level parallelismin the code.

Comparing[edit]

The clock rate of a CPU is most useful for providing comparisons between CPUs in the same family. The clock rate is only one of several factors that can influence performance when comparing processors in different families. For example, an IBM PC with anIntel 80486CPUrunning at 50 MHz will be about twice as fast (internally only) as one with the same CPU and memory running at 25 MHz, while the same will not be true for MIPS R4000 running at the same clock rate as the two are different processors that implement different architectures and microarchitectures. Further, a "cumulative clock rate" measure is sometimes assumed by taking the total cores and multiplying by the total clock rate (e.g. a dual-core 2.8 GHz processor running at a cumulative 5.6 GHz). There are many other factors to consider when comparing the performance of CPUs, like the width of the CPU'sdata bus,the latency of the memory, and thecachearchitecture.

The clock rate alone is generally considered to be an inaccurate measure of performance when comparing different CPUs families. Softwarebenchmarksare more useful. Clock rates can sometimes be misleading since the amount of work different CPUs can do in one cycle varies. For example,superscalarprocessors can execute more than one instruction per cycle (on average), yet it is not uncommon for them to do "less" in a clock cycle. In addition, subscalar CPUs or use of parallelism can also affect the performance of the computer regardless of clock rate.

See also[edit]

References[edit]

  1. ^Clockat theFree On-line Dictionary of Computing
  2. ^US 6826738,"Optimization of die placement on wafers".
  3. ^US 6694492,"Method and apparatus for optimizing production yield and operational performance of integrated circuits".
  4. ^Soderstrom, Thomas (11 December 2006)."Overclocking Guide Part 1: Risks, Choices and Benefits: Who Overclocks?"."Overclocking" early processors was as simple – and as limited – as changing the discrete clock crystal... The advent of adjustable clock generators has allowed "overclocking" to be done without changing parts such as the clock crystal.
  5. ^"Highest clock frequency achieved by a silicon processor".
  6. ^Chiappetta, Marco (23 September 2011)."AMD Breaks 8 GHz Overclock with Upcoming FX Processor, Sets World Record with AMD FX 8350".HotHardware. Archived fromthe originalon 2015-03-10.Retrieved2012-04-28.
  7. ^"CPU-Z Validator – World Records".
  8. ^"8.79GHz FX-8350 is the Fastest Ever CPU | ROG – Republic of Gamers Global".
  9. ^James, Dave (16 December 2019)."AMD's Ryzen rules overclocking world records… but can't beat a 5 year-old chip".pcgamesn.Retrieved23 November2021.
  10. ^"CPU Frequency: Hall of Fame".hwbot.org.HWBOT.Retrieved23 November2021.
  11. ^White, Monica J (22 December 2022)."Overclockers surpassed the elusive 9GHz clock speed. Here's how they did it".digitaltrends.Retrieved20 January2023.
  12. ^"Products formerly Raptor Lake".www.intel.com.Retrieved2024-07-05.
  13. ^ Frank, Michael."The Reversible and Quantum Computing Group (Revcomp)".www.cise.ufl.edu.Retrieved2024-03-17.
  14. ^ Swaine, Michael (2004)."Backward to the Future".Dr. Dobb's.Retrieved2024-03-17.
  15. ^ Michael P. Frank."Reversible Computing: A Requirement for Extreme Supercomputing".
  16. ^ Matthew Arthur Morrison."Theory, Synthesis, and Application of Adiabatic and Reversible Logic Circuits For Security Applications".2014.