Pipelining and parallel processing, interrupt handling in depth, the interrupt service routine, virtual memory and paging, page faults, and thrashing.
Improving processor performance
Beyond clock speed and cores, the CPU uses techniques to do more work per cycle:
Pipelining — overlapping the fetch, decode and execute stages of successive instructions, like a production line, so a new instruction starts before the previous one finishes.
Parallel processing — multiple cores/processors execute instructions simultaneously (true parallelism), suited to tasks that can be split into independent parts.
Cache memory — small, very fast memory holding recently/frequently used data and instructions, reducing slow main-memory accesses.
Viewing only
This content is free to read on superexams.com and cannot be printed or downloaded.
Read the full note, free
Create a free account to read this note in full. Every free account gets 2 complete revision notes, no card needed.