Tensor Processing Unit, every mention
40 scenes across 5 shows · ← back to Tensor Processing Unit
tap a year for its mentions
Acquired 26
the Y Combinator Startup Podcast 13
BG2 Pod 12
Cheeky Pint 10
Another Podcast 1
every year every show Acquired 26 the Y Combinator Startup Podcast 13 BG2 Pod 12 Cheeky Pint 10 Another Podcast 1
Verbatim, from the transcripts: passages where Tensor Processing Unit comes up on Acquired, the Y Combinator Startup Podcast, BG2 Pod, Cheeky Pint, Another Podcast
Jeff Dean: The 1% Rule for Building in AI · Y Combinator
- ▶ 0:24 Diana Hu So, um, you built MapReduce, Bigtable, TensorFlow, the TPU, Gemini, we could spend a whole hour on all the things you've done.
- ▶ 6:40 Diana Hu And instead, you basically built a custom ship, and that was the origin story of the TPU. 7 times in the scene
- ▶ 40:13 Jeff Dean Yeah, I mean, I think, well, TPUs is a good example, like being able to specialize hardware for a very niche problem domain before that problem domain seemed as important as it is today, is one thought experiment.
- ▶ 55:07 Diana Hu Now, one last thing, I'm pretty sure someone in this room or multiple people will eventually build something as consequential as you've done with MapReduce, TPU, distillation, et cetera, et cetera.
The history and future of AI at Google, with Sundar Pichai
- ▶ 0:40 Sundar Pichai A lot of like, like TPUs, transformers were all done to solve a specific product need to some extent, right? 2 times in the scene
- ▶ 5:44 John Collison AI services for different things, but Gemini on TPUs is just so fast, and I'm curious how much this is part of the explicit product strategy and how you think of it, or it's much more nuanced than that.
- ▶ 52:27 John Collison We're now going to a world where, as you say, that's not the case with, ah, you know, TPUs and how you allocate that. 3 times in the scene
Reiner Pope of MatX on accelerating AI with transformer-optimized chips
- ▶ 0:01 John Collison He's a former math whiz and Haskell programmer who became a TPU architect for Google, and now he's teamed up with Google's former chief chip architect to design a better chip for AI. 4 times in the scene
How does OpenAI compete?
- ▶ 1:57 Benedict Evans And yes, you can have a whole data center and chip analyst argument about why TPUs are better than NVIDIA and why this, this company's data centers are more efficient than that one.
Google Part III: The AI Company. Google is amazingly well-positioned... will they win in AI? (Audio) · Acquired
- ▶ 3:27 Ben Gilbert They're a chip company with their Tensor Processing Units, or TPUs, which is the only real scale deployment of AI chips in the world besides Nvidia GPUs.
- ▶ 1:45:29 David Rosenthal Matrix multiplication, tensor multiplication, a tensor processing unit, you might say.
- ▶ 1:46:00 Ben Gilbert So enter, David, as you said, the tensor processing unit made just for neural networks that is far more efficient from GPUs at the time, with the trade-off that you can't really use it for anything else.
- ▶ 1:46:28 Ben Gilbert So the big idea behind the TPU, if you're trying to figure out, like, what was the core insight, they use reduced computational precision.
- ▶ 1:47:18 Ben Gilbert The whole thing is quite clever behind the TPU.
- ▶ 1:47:21 Ben Gilbert The other thing that has to happen with the TPU is it needs to happen now, because it's very clear speech to text is a thing.
- ▶ 1:47:49 Ben Gilbert So, the TPU was designed, verified, built, and deployed into data centers in 15 months.
- ▶ 1:48:19 Ben Gilbert The other thing they did is they fit the TPU into the form factor of a hard drive.
- ▶ 1:48:28 Ben Gilbert You just pop out a hard drive and you pop in a TPU without needing to do any physical re-architecture.
- ▶ 1:49:21 Ben Gilbert The other thing to know about the TPUs is they were done in time for the AlphaGo match.
- ▶ 1:49:25 Ben Gilbert So that match ran on a single machine with four TPUs in Google Cloud.
- ▶ 1:49:36 Ben Gilbert That's the TPU.
- ▶ 1:49:43 Ben Gilbert TPUs and GPUs look a lot more similar than they used to.
- ▶ 1:49:49 Ben Gilbert But today, Google, it's estimated, has two to three million TPUs.
- ▶ 1:50:14 Ben Gilbert The TPU is a giant deal in AI in a way that I think a lot of people don't realize.
- ▶ 1:50:44 Ben Gilbert And they built it in such a way that it doesn't just have to run on TPUs.
- ▶ 1:55:18 David Rosenthal All the efforts that are coming out of AlexNet and then the TPU project of parallelization.
- ▶ 3:28:30 Ben Gilbert But in Google Cloud, you can use TPUs, which they make a ton of, and everyone else is desperately begging NVIDIA for allocations to GPUs.
- ▶ 3:28:41 Ben Gilbert So if you're willing to not use CUDA and build on Google stack, they have an abundant amount of TPUs for you.
- ▶ 3:37:30 Ben Gilbert When working with Google on the TPU versus Nvidia's 80%, but that's still a huge difference to play with.
- ▶ 4:04:16 Ben Gilbert To Jonathan Ross, original team member on the TPU, and today the founder and CEO of Grok, that's Grok with a Q, making chips for inference.
Anthropic Head of Pretraining on Scaling Laws, Compute, and the Future of AI · Y Combinator
- ▶ 25:17 Ankit Gupta Or if you guys are using TPU versus GPU, are these, you know, Google TPU versus NVIDIA GPU, do you actually have to think as an engineer differently about what it means to train on these two? 3 times in the scene
NVIDIA: OpenAI, Future of Compute, and the American Dream | BG2 w/ Bill Gurley and Brad Gerstner · Bg2 Pod
- ▶ 40:53 Clark Tang Google's TPUs, Amazon's Tranium, and it seems like everyone from ARM to OpenAI to Anthropic are, you know, rumored to be building one. 4 times in the scene
China Open-Source, Compute Arms Race, Reordering Global Trade | BG2 w/ Bill Gurley and Brad Gerstner · Bg2 Pod
- ▶ 41:06 Sunny Madra And can I, can I put something there just to kind of hear your feedback on it, guys, which is look at Google and the TPU and Google is clearly, you know, by these numbers that we're seeing, right, putting out more tokens than anyone else,… 5 times in the scene
Coatue’s Laffont Brothers. AI, Public & VC Mkts, Macro, US Debt, Crypto, IPO's, & more | BG2 · Bg2 Pod
- ▶ 27:01 Philippe Laffont I, I even have a hard time believing that those are the numbers is I thought Google was more skewed to TPUs than NVIDIA. 2 times in the scene
AI Semiconductor Landscape feat. Dylan Patel | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 9:56 Dylan Patel With the TPU.
Nvidia Part III: The Dawn of the AI Era (2022-2023) (Audio) · Acquired
- ▶ 43:16 David Rosenthal To train these models is prohibitively expensive, and, you know, even Google at this point in time, this is when they start building their own chips, TPUs, because, you know, they're still buying tons of hardware from NVIDIA, but they're…
- ▶ 1:58:55 Ben Gilbert Google and the TPU.
- ▶ 2:09:47 Ben Gilbert I know we've been harping on NVIDIA, but Google TPUs are also manufactured at volume.
- ▶ 2:10:03 Ben Gilbert But it's certainly not an industry standard to use TPUs the way that it is to use NVIDIA's hardware.
- ▶ 2:10:09 Ben Gilbert I suspect a lot of the volume of the TPUs is being used internally by Google for BARD, for doing stuff in Google search.