Our eighth generation TPUs: two chips for the agentic era • Hacker News Board

Re: Our eighth generation TPUs: two chips for the agentic era

#31

Post by WarmWash » Wed, Apr 22, 2026, 1:38 PM UTC

Keyframe wrote: post #4

As others have been capturing news cycle eyes, seems to me Google has been going from strength to strength quietly in the background capturing consumer market share and without much (any?) infrastructure problems considering they're so vertically integrated in AI since day one? At one point they even seemed like a lost cause, but they're like a tide.. just growing all around.

AI adoption isn't existential to Google like it is to OAI and Anthropic. They also can't produce hype like the other two, because anything they say is just going to come off as corporate drivel.

Re: Our eighth generation TPUs: two chips for the agentic era

#32

Post by FuriouslyAdrift » Wed, Apr 22, 2026, 1:38 PM UTC

xnx wrote: post #24

fulafel wrote: post #21

"TPU 8t and TPU 8i deliver up to two times better performance-per-watt over the previous generation" sounds impressive especially as the previous generation is so recent (2025). Interesting that there's separate inference and training focused hardware. Do companies using NV hardware also use different hardware for each task or is their compute more fungible?

Nvidia said in March that they're working on specialized inference hardware, but they don't have any right now. You can do inference from Nvidia's current hardware offerings, but it's not as efficient.

AMD has been doing inference chips for many years and are the leader for HPC.

https://www.amd.com/en/products/accelerators/instinct.html

Re: Our eighth generation TPUs: two chips for the agentic era

#33

Post by varispeed » Wed, Apr 22, 2026, 1:40 PM UTC

I can't help but think we will be "laughing" at this in 10 years time like we laugh at steam engines or abacus.

Re: Our eighth generation TPUs: two chips for the agentic era

#34

Post by zozbot234 » Wed, Apr 22, 2026, 1:40 PM UTC

fulafel wrote: post #21

"TPU 8t and TPU 8i deliver up to two times better performance-per-watt over the previous generation" sounds impressive especially as the previous generation is so recent (2025). Interesting that there's separate inference and training focused hardware. Do companies using NV hardware also use different hardware for each task or is their compute more fungible?

The "training" chips will probably be quite usable for slower, higher-throughput inference at scale. I expect that to be quite popular eventually for non-time-sensitive uses.

Re: Our eighth generation TPUs: two chips for the agentic era

#35

Post by wina » Wed, Apr 22, 2026, 1:42 PM UTC

cmptrnerd6 wrote: post #27

Which company is building the silicon for Google? Is it tsmc? What node size? I didn't see it with a quick search, sorry if it was in the post.

tsmc through broadcom

Re: Our eighth generation TPUs: two chips for the agentic era

#36

Post by zozbot234 » Wed, Apr 22, 2026, 1:42 PM UTC

paulmist wrote: post #14

At $15/GB of HBM4 the 331.8TB of HBM4 per pod is 5 million...

$15/GB is retail price for DIMM sticks. Is HBM4 really that cheap?

Re: Our eighth generation TPUs: two chips for the agentic era

#37

Post by iandanforth » Wed, Apr 22, 2026, 1:43 PM UTC

Anyone know if these are already powering all of Gemini services, some of them, or none yet? It's hard to tell if this will result in improvements in speed, lower costs, etc, or if those will be invisible, or have already happened.

Re: Our eighth generation TPUs: two chips for the agentic era

#38

Post by hkpack » Wed, Apr 22, 2026, 1:43 PM UTC

sigmoid10 wrote: post #13

pmb wrote: post #11

At this point, when you are doing big AI you basically have to buy it from NVidia or rent it from Google. And Google can design their chips and engine and systems in a whole-datacenter context, centralizing some aspects that are impossible for chip vendors to centralize, so I suspect that when things get really big, Google's systems will always be more cost-efficient. (disclosure: I am long GOOG, for this and a few o…

I'd bet that too if their management wasn't so incredibly uninspiring. Like, Apple under Cook was also pretty mild and a huge step down from Jobs, but Google feels like it fell off a cliff. If it wasn't for OpenAI releasing ChatGPT, they might still be sitting on that tech while only testing it internally. Now it drives their entire chip R&D.

I am not fan of the era when CEO is expected to be a cult leader type person.

Cook did very well in all areas as well as in not trying to create a cult.

Re: Our eighth generation TPUs: two chips for the agentic era

#39

Post by kamranjon » Wed, Apr 22, 2026, 1:44 PM UTC

It's interesting that, of the large inference providers, Google has one of the most inconvenient policies around model deprecation. They deprecate models exactly 1 year after releasing them and force you to move onto their next generation of models. I had assumed, because they are using their own silicon, that they would actually be able to offer better stability, but the opposite seems to be true. Their rate limiting is also much stricter than OpenAI for example. I wonder how much of this is related to these TPU's, vs just strange policy decisions.

Re: Our eighth generation TPUs: two chips for the agentic era

#40

Post by hgoel » Wed, Apr 22, 2026, 1:45 PM UTC

NitpickLawyer wrote: post #20

vibe42 wrote: post #16

The pics of the cooling system is pretty good sci-fi / cyberpunk / steampunk inspo. If the whole AI bubble spectularly collapes, at least we got a lot of cool pics of custom hardware!

> If the whole AI bubble spectularly collapes Every other news for the past month has been about lacking capacity. Everyone is having scaling issues with more demand than they can cover. Anthropic has been struggling for a few months, especially visible when EU tz is still up and US east coast comes online. Everything grinds to a halt. MS has been pausing new subscriptions for gh Copilot, also because a lack of capac…

There's a massive amount of demand at the current price point, this does not exclude a bubble considering that the current cost to consumers is lower than what capacity expansion costs.

Though nowadays it feels like the bubble is going to end up being mainly an OpenAI issue. The others are at least vaguely trying to balance expansion with revenue, without counting on inventing a computer god.