Practice Flashcards
Flip to reveal answersWhat is the core difference between a CPU and a GPU?
Track your progress — Sign up free to save your progress and get smart review reminders based on spaced repetition.
All 5 Flashcards — CPU vs GPU
Sign up free to track progress and get spaced-repetition review schedules.
Question
What is the core difference between a CPU and a GPU?
Answer
A **CPU** has a few powerful cores optimised for **latency** on one stream. A **GPU** has thousands of simple cores optimised for **throughput** on many values at once.
Question
Why is a GPU poor at branching?
Answer
Its cores run in **lockstep** on the same instruction, so a branch forces some to idle while the others proceed.
Question
What is the test for whether a GPU will help?
Answer
**Are the operations independent?** Can they run in any order, simultaneously, without needing each other's results?
Question
Why does training need a GPU but inference often not?
Answer
Training is enormous **parallel matrix arithmetic** over a whole dataset. Inference is one input, one pass — small enough for a CPU or a phone.
Question
Why can moving a program to a GPU make it slower?
Answer
If the work is sequential or branch-heavy it cannot parallelise, each GPU core is slower than a CPU core, and the data must be **copied there and back**.
Read the notes
Full study notes for CPU vs GPU
Topic 1.1 hub
Hardware and operation
More from Topic 1.1
All flashcards in this topic
Computer Science exam skills
Paper structures & tips
Track your progress with spaced repetition
Sign up free — Aimnova tells you exactly which cards to review and when, so you remember everything before your IB exam.
Start Free