wunder beta📘 How CPUs Work
A central processing unit is a fast, general-purpose machine for changing bits according to instructions. A program is stored as data, and the CPU repeatedly reads an instruction, interprets its fields, obtains any needed operands, performs
What you’ll learn
- The CPU's jobExplain the CPU as a machine that changes state by following encoded instructions.Programs become instruction streams, and the CPU uses control state to choose what happens next.
- The instruction cycleDescribe fetch, decode, execute, and write-back as a useful model of instruction processing.The CPU repeatedly obtains instructions, interprets them, performs operations, and records results.
- PipeliningExplain how overlapping stages improves throughput and why branches can cause stalls.Pipelining keeps multiple stages busy, while dependencies and wrong-path predictions create bubbles.
- Registers and addressesDistinguish registers, the program counter, virtual addresses, page tables, and the TLB.Close CPU state and address translation let instructions find and use protected data.
- CachesExplain cache hits, misses, cache lines, and the tradeoff among cache levels.Caches use locality to keep likely-needed instructions and data closer to the core.
- Memory hierarchy and multicoreRelate the memory hierarchy to multicore sharing and cache coherence.Layers trade speed for capacity; multiple cores need parallel software and protocols to keep shared data consistent.
- Putting it togetherTrace a load-and-add operation and evaluate performance beyond clock speed.CPU performance emerges from the interaction of the pipeline, caches, memory, and workload.
Questions this course answers
Put the simplified instruction cycle in order.
The CPU first obtains and interprets an instruction, then performs its operation and records the result. Real processors overlap these stages, but the conceptual order remains useful.
What is the main benefit of pipelining?
Pipelining overlaps stages across instructions, increasing throughput even though each instruction still passes through multiple stages.
What is a cache hit?
A hit means the current cache contains the requested line, so the CPU can avoid going to a slower level for it.
Match each CPU structure to its role.
These structures all reduce delay or track state, but they store different kinds of information.
Why can a CPU with a higher clock speed still be slower for a task?
Frequency is only one factor. The pipeline, caches, memory path, instruction mix, and software determine how much useful work each cycle produces.
Grounded in trusted sources
- Intel, The Journey Inside: Microprocessors - Fetch, Decode, and Execute: https://www.intel.com/content/www/us/en/education/k12/the-journey-inside/explore-the-curriculum/microprocessors.html
- Intel, Technologies Defined for Intel Processors - Cache Information: https://www.intel.com/content/www/us/en/support/articles/000006513/processors.html
- Intel, VTune Tuning Guide - The uOp Pipeline: https://www.intel.com/content/dam/develop/external/us/en/documents/tuningguide-intel-apollolake-181827.pdf
- Linux kernel documentation, Concepts overview - virtual memory and address translation: https://docs.kernel.org/admin-guide/mm/concepts.html
- Arm Community, Exploring how cache coherency accelerates heterogeneous compute: https://developer.arm.com/community/arm-community-blogs/b/architectures-and-processors-blog/posts/exploring-how-cache-coherency-accelerates-heterogeneous-compute
- Stanford Computer Science, Pipelining: https://cs.stanford.edu/people/eroberts/courses/soco/projects/risc/pipelining/index.html
- Wikimedia Commons MediaWiki API image records: https://commons.wikimedia.org/w/api.php
Every Wunder lesson is built from real, reputable sources — never invented.
Related courses
Wunder is a personalized learn-anything platform — tell it any topic and it builds a beautiful, fact-checked course in minutes, with narration, a knowledge check, and a college-style University track.
© 2026 Wunder Learning LLC · Terms & Privacy