Skip to main content
EnglandComputer ScienceSyllabus dot point

Why is one processor faster than another, and why does adding cores not always double the speed?

The factors that affect CPU performance: clock speed, the number of cores, and the size and use of cache memory, and how each one changes how quickly programs run.

An Eduqas GCSE Computer Science answer on the three factors that affect CPU performance (clock speed, number of cores, and cache size), why doubling cores rarely doubles speed, and how cache hits reduce waiting time.

Generated by Claude Opus 4.810 min answer

Reviewed by: AI editorial process; not yet individually human-reviewed

Have a quick question? Jump to the Q&A page

Jump to a section
  1. What this dot point is asking
  2. Clock speed
  3. The number of cores
  4. Cache
  5. Try this

What this dot point is asking

Eduqas wants you to name and explain the three factors that affect how fast a CPU runs programs: clock speed, the number of cores, and cache. The marks are in the explanation, not the list, so you must say why each one changes performance, and be able to explain why more cores does not simply mean proportionally more speed.

Clock speed

The number of cores

However, the gain is usually less than the number of cores. Many tasks are sequential: each step depends on the result of the previous one, so they cannot be split and run on a single core no matter how many are available. Cores also share resources such as memory and parts of the cache, and software has to be specifically written to use multiple cores. So a quad-core CPU is faster than a dual-core for parallel work, but it does not make every program run twice as fast.

Cache

A larger or faster cache holds more frequently used instructions and data, so a greater proportion of requests are cache hits, and the CPU spends less time waiting. There is a cost: cache is expensive to build and the more you add the smaller the extra benefit, which is why CPUs use a small, very fast cache rather than making all memory that fast.

Try this

Q1. State the unit used to measure CPU clock speed. [1 mark]

  • Cue. Hertz (Hz), usually gigahertz (GHz).

Q2. State what is meant by a cache hit. [1 mark]

  • Cue. When the instruction or data the CPU needs is found in the cache, so it does not have to be fetched from slower RAM.

Q3. Give one reason a quad-core CPU may not run a program twice as fast as a dual-core CPU. [1 mark]

  • Cue. Sequential programs cannot be split across cores (or: cores share resources, or the software is not written to use multiple cores).

Exam-style practice questions

Practice questions written in the style of WJEC Eduqas exam questions on this dot point, with worked answer explainers. The year tag is the paper they imitate, not the source.

Eduqas Component 1, 20223 marksExplain how the clock speed of a CPU affects its performance.
Show worked answer →

Clock speed is the number of fetch-decode-execute cycles the CPU performs each second, measured in hertz (a 3 GHz processor performs about three billion cycles per second).

A higher clock speed means more cycles per second, so more instructions are processed in the same time, and programs generally run faster (1 mark for "more cycles per second", 1 mark for "more instructions executed", 1 mark for linking to faster programs).

Markers reward the link from cycles per second to instructions per second to speed. A common cap is reached by candidates who only write "it is faster" without explaining why.

Eduqas Component 1, 20234 marksA computer has a dual-core processor. Explain why replacing it with a quad-core processor may not make every program run twice as fast.
Show worked answer →

A quad-core processor can run more instruction streams at once, so tasks that can be split across cores (or several programs running together) can speed up.

However, many programs are at least partly sequential: a step depends on the result of the previous one, so it cannot be split across cores and runs on a single core regardless of how many are available (up to 2 marks for the sequential-dependency point).

Cores also share resources such as memory and cache, which limits the gain, and some software is not written to use multiple cores (up to 2 marks). So the speed-up is usually less than the number of cores.

Markers reward the idea that not all work can be parallelised and that cores share resources, rather than just restating "four is more than two".

Related dot points

Sources & how we know this