Richie CottonSenior Data Evangelist, DataCamp · Ask me about data and AI upskilling

How hardware will change AI #ai #cost

Name: How hardware will change AI #ai #cost
Uploaded: 2024-09-19T12:01:06+00:00
Duration: 59 s
Channel: Richie Cotton
Description: In this talk, the speaker argues that rising cost pressures will spur AI hardware innovation. He notes that most AI research today runs on large clusters…

19 Sept 2024 · 1 min

Watch on YouTube

0:59

In this talk, the speaker argues that rising cost pressures will spur AI hardware innovation. He notes that most AI research today runs on large clusters of general‑purpose processors, which are not optimal for deep‑learning workloads and drive up costs. Cerebras has created a purpose‑built AI processor designed from the ground up for neural‑network training. According to the speaker, this processor can train models an order of magnitude faster than comparable GPU systems while using less power. The speed and efficiency gains translate into faster developer iteration—allowing more experiments per unit time—and lower overall energy consumption, positioning specialized hardware as a key lever for reducing AI development costs.

Chapters

Cost pressure I think is going to drive innovation. But second, I think we as a community are really using in some sense a lot of the traditional AI work that's been done today has been done on traditional general purpose infrastructure and that's one of the big cost factors in innovation. Right. So people are building models on large clusters of small general purpose processors. Those processors are suitable but they're not optimal for this work. At Cerebras we've built a completely new class of processor that's built from the ground up for AI and as a result it's faster but it's also more efficient. So that means that if you're say training a model right, you can go an order of magnitude faster than you could on an equivalent GPU system and it's going to be more efficient not only in terms of developer iteration, being able to test more ideas per unit time but it's also going to be more power efficient underneath the hood.