{"data":{"slug":"google-tpu-pod","etype":"server","name":"Google TPU Pods","cat":"Cluster Reference","subtitle":"Google's unit of training: thousands of TPUs behind optical circuit switches.","summary":"Google scales TPUs in pods — 4,096 chips (v4), 8,960 (v5p), 9,216 (Ironwood) — wired by inter-chip interconnect in a 3D torus and reconfigured through optical circuit switches that route around failures without touching a cable. Gemini trains across multiple pods over the Jupiter network; the pod, not the server, is Google's hardware product.","attrs":[{"b":"Vendor spec","g":"Overview","l":"Scale","v":"v4: 4,096 · v5p: 8,960 · Ironwood: 9,216 chips"},{"b":"Published paper","g":"Overview","l":"Interconnect","v":"3D-torus ICI + optical circuit switching"}],"kf":{"chips":"up to 9,216 TPUs per pod","maker":"Google"},"aliases":["TPU pod","superpod"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Shipping","region":null,"asof":"2026-01-15","sources":[{"url":"https://cloud.google.com/tpu/docs/system-architecture-tpu-vm","label":"Google Cloud TPU architecture"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T11:46:53+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}