Nvidia, every mention
19 scenes (2024), the whole family · ← back to Nvidia
tap a year for its mentions
every year 2024 anyone Shayle Kann 28Varun Sivaram 20Jeremy Eliahu-Ontiveros 13Chase Lockmiller 12John Koomey 5Brian Janous 4Drew Baglino 3Stephen Lacey 2Nick Chaset 2Chris Sharp 2
Verbatim, from the transcripts: the passages where Nvidia comes up
Explaining the 'Watt-Bit Spread'
- ▶ 28:38 Brian Janous So if, if I'm downstream in the system, so I'm data center operators, I'm cloud providers, I'm NVIDIA, I'm open AI, uh, I'm very much thinking about the world in terms of theory of constraints, because again, the cost of the base…
Frontier Forum: An energy-first approach to data centers
- ▶ 9:37 Chase Lockmiller Yeah, I mean, we, we need to address it head-on, because, you know, and I think what you're seeing is that, like, I mean, just, if you think about just the power consumption of an H 100, right, which is the current generation of NVIDIA… 2 times in the scene
- ▶ 9:37 Chase Lockmiller Yeah, I mean, we, we need to address it head-on, because, you know, and I think what you're seeing is that, like, I mean, just, if you think about just the power consumption of an H 100, right, which is the current generation of NVIDIA… 3 times in the scene
- ▶ 19:47 Stephen Lacey Like, when you look at future efficiencies of chip design, how are you, like, NVIDIA chip design, how are you collaborating on data center design to, like, 2 times in the scene
- ▶ 20:09 Chase Lockmiller If you look at, like, the last generation NVIDIA chip, it was the Ampere, uh, so the A-one hundred, um, that, that consumed about 300 watts per chip.
- ▶ 20:09 Chase Lockmiller If you look at, like, the last generation NVIDIA chip, it was the Ampere, uh, so the A-one hundred, um, that, that consumed about 300 watts per chip.
- ▶ 20:18 Chase Lockmiller The Hopper, the current generation, the H-one hundred, H-two hundred, um, those are about 700 watts per chip.
- ▶ 20:18 Chase Lockmiller The Hopper, the current generation, the H-one hundred, H-two hundred, um, those are about 700 watts per chip.
- ▶ 20:18 Chase Lockmiller The Hopper, the current generation, the H-one hundred, H-two hundred, um, those are about 700 watts per chip.
- ▶ 20:24 Chase Lockmiller Um, and the Blackwell is sort of the next generation, the GB 200, um, that'll be about 1200 watts per chip.
- ▶ 20:24 Chase Lockmiller Um, and the Blackwell is sort of the next generation, the GB 200, um, that'll be about 1200 watts per chip.
Can chip efficiency slow AI's energy demand?
- ▶ 3:55 Shayle Kann First one from NVIDIA. 2 times in the scene
- ▶ 3:56 Shayle Kann So when NVIDIA unveiled what they call their Blackwell chips, their next generation GPU, they said that the Blackwell chip has 25 X lower energy consumption. 2 times in the scene
- ▶ 16:27 Shayle Kann I think NVIDIA, when they released the Blackwell chip, said it's like 25 4 times in the scene
- ▶ 16:27 Shayle Kann I think NVIDIA, when they released the Blackwell chip, said it's like 25 3 times in the scene
- ▶ 22:30 Shayle Kann Two is chips, like Nvidia's sold out for years, and there's only so many chips in the world, and three is energy.
Under the hood of data center power demand
- ▶ 41:25 Brian Janous And, you know, there's a lot of discussion right now about efficiency and what if Nvidia comes out with a, you know, more efficient chip that's, which they have, and they continue to innovate and come out with more efficient chips. 2 times in the scene
Drew Baglino on Tesla’s Master Plan
- ▶ 30:03 Drew Baglino And then on the other side, you have, you know, NVIDIA is doing a good job and, and other companies to, to reduce the, the Watts per flop of, of useful compute. 3 times in the scene
- ▶ 33:22 Shayle Kann I mean, maybe NVIDIA's production capacity is, like, up there, too, but otherwise, it's energy, and so the combination of those two things makes me think it is, it's highly likely we're going to see some