AI Dictionary › Fondamenti AI

GPU and TPU

GPU e TPU

GPUs and TPUs are the hardware engines that make modern AI possible. The GPU (Graphics Processing Unit) was born for video games, but its ability to do thousands of simple calculations in parallel turned out perfect for neural networks. The TPU (Tensor Processing Unit) is a chip designed from scratch by Google specifically for AI. Picture the difference between an ordinary processor and these accelerators as that between a lone cook making a thousand dishes one by one and a brigade of a thousand cooks working together: for repetitive parallel tasks, the brigade wins decisively. Both excel at matrix multiplications, the core of model computation.

Definition

GPUs and TPUs matter because without them training or running a large model would take years instead of weeks. Their availability and cost decide who can afford to build AI.

Related terms

• Compute
• FLOPS
• Deep Learning
• Inference
• Parameters

More in Fondamenti AI

• LLM (Large Language Model)
• Token
• Context Window
• Temperature
• AI Hallucination
• Fine-tuning
• RAG (Retrieval Augmented Generation)
• Embedding

Put it into practice

• Real scenario: apply this concept with an instant AI verdict.
• Daily gym: short drills to train dictionary concepts.
• Playoff game: challenge other players, elimination-style.

📱 Download the Android app (beta) iOS coming soon

Say what you mean. Get what you need.

Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.