How does David Patterson explain the difference between a CPU, a GPU and a TPU?

David Patterson frames the three as rising levels of specialization. A CPU is general-purpose, with 50 to 100 cores much like designs of 20 years ago. A GPU is a heavily multithreaded design built for graphics, with modest 16- and 32-bit floating point. Google's TPU is dedicated to machine learning, built around one large matrix-multiply unit with the general-purpose machinery stripped out.

• Patterson's textbooks carry a translation table between NVIDIA's own GPU terminology and mainstream processor-design terms.
• The first TPU had a single processor, unlike multicore CPUs and GPUs.

Source: our own transcription of the episode. The full conversation is on Ryan Peterman (2026-11-04). Read the whole episode summary →

▸More from this episode