The New Stack Podcast13 Mai 2025

Google AI Infrastructure PM On New TPUs, Liquid Cooling and More

At Google Cloud Next '25, the company introduced Ironwood, its most advanced custom Tensor Processing Unit (TPU) to date. With 9,216 chips per pod delivering 42.5 exaflops of compute power, Ironwood doubles the performance per watt compared to its predecessor. Senior product manager Chelsie Czop explained that designing TPUs involves balancing power, thermal constraints, and interconnectivity.

Google's long-term investment in liquid cooling, now in its fourth generation, plays a key role in managing the heat generated by these powerful chips. Czop highlighted the incremental design improvements made visible through changes in the data center setup, such as liquid cooling pipe placements. Customers often ask whether to use TPUs or GPUs, but the answer depends on their specific workloads and infrastructure. Some, like Moloco, have seen a 10x performance boost by moving directly from CPUs to TPUs. However, many still use both TPUs and GPUs. As models evolve faster than hardware, Google relies on collaborations with teams like DeepMind to anticipate future needs.

Learn more from The New Stack about the latest AI infrastructure insights from Google Cloud:

Google Cloud Therapist on Bringing AI to Cloud Native Infrastructure

A2A, MCP, Kafka and Flink: The New Stack for AI Agents

Join our community of newsletter subscribers to stay on top of the news and at the top of your game.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(300)

A third option is emerging in the fight over AI and your data

The AI industry has faced a growing enterprise dilemma: companies want access to powerful proprietary AI models without risking sensitive data or intellectual property, while AI labs want to protect t...

23 Sep 30min

Drowning in AI pull requests: Harness's field CTO on code review and a Git repo built for agents

Harness Field CTO Martin Reynolds joins The New Stack to talk about what happens after coding agents start opening pull requests faster than anyone can review them. He explains how he first saw the bo...

7 Sep 26min

How to find failures without drowning in tracing data

Traces provide a detailed view of a request’s journey through data, microservices and applications, helping SREs pinpoint where failures occur and resolve issues faster. But while tracing can reduce d...

3 Sep 31min

Why CPUs still matter in the age of AI agents

As AI evolves from conversational chatbots to autonomous agents, CPUs are becoming an increasingly important part of the infrastructure equation. In this episode, The New Stack speaks with Bhumik Pate...

11 Aug 26min

Why Doist Says Less AI Can Deliver More

Doist CTO Gonçalo Silva says AI is reshaping software development, but success depends on restraint rather than rapid feature expansion. Instead of chasing every AI capability, Doist prioritizes “subt...

31 Jul 35min

Why your company should (try to) build its own AI SRE

As AI coding agents accelerate software development, they also create new challenges for site reliability engineers (SREs), who are increasingly responsible for debugging systems that no single human ...

30 Jul 30min

Nvidia

In this episode with The New Stack Agents, Frederic Lardinois, NVIDIA’s Joey Conway says advances in AI over the past year have dramatically improved the capabilities of local models, making them prac...

23 Jul 32min

Meet Brain, the AI that decides when Azure is officially down

In this episode, Mark Russinovich, CTO of Microsoft Azure revealed Brain, the AI-powered AIOps system that continuously monitors Azure’s health, detects incidents, identifies root causes, and increasi...

14 Jul 19min