TPU
Google's purpose-built accelerator for tensor arithmetic.
Overview
A TPU is an application-specific chip designed for the matrix operations neural networks are made of, rather than a general-purpose processor adapted to them. It solves the same cost problem as a GPU but by removing the generality, which makes it more efficient per operation and less flexible. It exists because a workload this narrow can be served better by dedicated silicon, and it is reachable mainly through Google's cloud rather than as hardware you buy.
Technology Graph
How TPU connects to the rest of the stack.
Applied to
- Deep Learning concept Algorithms TPU used for Deep Learning High ✓ source
- LLM concept Models TPU used for LLM High ✓ source
Alternatives
Comparisons
Side-by-side breakdowns with the alternatives above.