Cambridge IGCSE Computer Science (0478) · lesson 17 of 35 · 25 min
Inside the CPU
Cache Memory
Cache is much faster than RAM but much smaller and more expensive. Modern CPUs have multiple cache levels:
When the CPU needs data, it checks L1 first, then L2, then L3, then RAM. A cache hit means the data was found in cache; a cache miss means it must be fetched from slower RAM.
Factors Affecting CPU Performance
Clock speed (GHz): number of fetch-execute cycles per second. Higher = faster. Number of cores: each core can execute instructions independently. More cores = better multitasking. Cache size: larger cache reduces cache misses and RAM accesses. Word size: wider data bus (32-bit vs 64-bit) processes more data per cycle.
Which CPU component performs arithmetic and logical operations?
- CU
- MAR
- ALU
- CIR
Answer: ALU
The ALU (Arithmetic Logic Unit) handles all arithmetic and logical operations.
What is stored in the MAR?
- The current instruction
- The address of the memory location being accessed
- The result of the last calculation
- The next instruction address
Answer: The address of the memory location being accessed
MAR = Memory Address Register; holds the address for the current memory operation.
A larger cache generally results in:
- Slower CPU performance
- More cache misses
- Fewer RAM accesses and faster performance
- Higher power consumption only
- Answer: 2
More cache means more data can be stored close to the CPU, reducing slow RAM accesses.
Previous lesson: Von Neumann architecture and the fetch-execute cycle
Back to Cambridge IGCSE Computer Science (0478)
Next lesson: Primary memory: RAM and ROM