Hacker News new | ask | show | jobs
by westurner 228 days ago
A TPU is supposed to do more Tensor ops TOPS/wHr than a GPU.

Though, some GPUs have a TPU. For example Nvidia DLSS3 is a TPU.

"A PCIe Coral TPU Finally Works on Raspberry Pi 5" (2023) https://news.ycombinator.com/item?id=38310063

"ARM adds neural accelerators to GPUs" (2025) https://news.ycombinator.com/item?id=44919793

From "The von Neumann bottleneck is impeding AI computing?" (2025) https://news.ycombinator.com/item?id=45398473 :

> How does Cerebras WSE-3 with 44GB of 'L2' on-chip SRAM compare to Google's TPUs, Tesla's TPUs, NorthPole, Groq LPU, Tenstorrent's, and AMD's NPU designs?

Tensor Processing Unit: https://en.wikipedia.org/wiki/Tensor_Processing_Unit

..

- "Ask HN: Are you paying electricity bills for your service?" (2024) https://news.ycombinator.com/item?id=42454547 re: Zero Water datacenters

- "Show HN: LangSpend – Track LLM costs by feature and customer (OpenAI/Anthropic)" (2025-10) https://news.ycombinator.com/item?id=45771618

1 comments

To make electronic and photonic TPUs (and CPUs, GPUs, and QPUs) faster, we should make them out of graphene and carbon nanotubes and other allotropes of carbon (instead of photoresisting and doping silicon and copper)