The eighth-generation TPU: An architecture deep dive
meetpateltech
67 points
10 comments
April 22, 2026
Related Discussions
Found 5 related stories in 108.3ms across 10,324 title embeddings via pgvector HNSW
- Our eighth generation TPUs: two chips for the agentic era xnx · 427 pts · April 22, 2026 · 77% similar
- TorchTPU: Running PyTorch Natively on TPUs at Google Scale mji · 105 pts · April 23, 2026 · 63% similar
- Google to sell TPU chips to select customers gmays · 23 pts · May 06, 2026 · 56% similar
- Google unveils chips for AI training and inference in latest shot at Nvidia wslh · 12 pts · April 22, 2026 · 52% similar
- FP8 Is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail matt_d · 11 pts · June 08, 2026 · 52% similar
Discussion Highlights (5 comments)
zshn25
Splitting TPUs into dedicated training vs inference chips feels like an admission that the bottleneck has shifted from FLOPs to memory bandwidth + latency. Are future gains to come more from memory/system design than raw compute scaling? What’s that saying about Scaling laws?
ricardo81
dupe https://news.ycombinator.com/item?id=47862497
ttul
No matter how smart your large language model is, if you can’t find the energy to power it, it won’t run. I could imagine Google winning merely because their chips are more efficient. Of course, the other labs are capable of making chips, but Google has been doing it for years.
speedping
2.764 petabytes of HBM per 8i? So that's where all the RAM went.
juancn
Super interesting but it's so damn hard to find any detail. I would love to see an instruction set reference for one of these, all you have is hardware architectural diagrams or high level APIs.