Questa sezione non è ancora tradotta. Il contenuto seguente è mostrato in inglese, come pubblicato. Leggi la versione inglese.
Google adds TPU 8tx for confidential computing and the dual-chip TPU 8i Max, with AMD EPYC hosts
What changed
Google Cloud said on 9 November that it is adding two systems to its eighth-generation TPU family, as reported by Silicon Report: the TPU 8tx, built on the same die as the TPU 8t training chip and packaged for confidential inference and small-scale training, and the TPU 8i Max, which puts two TPU 8i chips on one package. Google says the dual-chip package fits existing rack footprints and doubles the silicon deployed per rack, which raises compute per rack and so the power and heat each rack must handle. AMD said the same day that its 5th Gen EPYC processors are the host CPUs for TPU 8tx. Google has not published rack power or cooling figures for the new systems.
View original source (opens in a new tab)
Read the original: AMD (press release) and Silicon Report: Google adds TPU 8tx for confidential computing and the dual-chip TPU 8i Max, with AMD EPYC hosts (opens in a new tab)
We summarise in our own words and link the source. Figures are as reported by the source and not independently verified. Report a correction.
Related index data
A supplier link means the company is named in the story or offers this kind of product. It does not mean a contract unless the story says so.
Related on CoolPower Index: Chip power and cooling.
More in AI and Data Centre Chips
- CoreWeave's chief executive cancels his share sale plan after Q3 results, keeping 1.85 GW of active power as the end-2026 target 11 Nov 2026
- AMD makes 6th Gen EPYC 'Venice' server CPUs generally available, with Helion agentic AI racks in liquid-cooled and air-cooled versions 10 Nov 2026
- Anthropic's amended IPO filing raises its Microsoft compute commitment to at least US$47.2 billion and says a US$34.9 billion Lambda agreement can now be terminated 10 Nov 2026