How does Cerebras manage chip defects and yield reliability at the wafer scale?
Replied byAndrew Feldman
Co-founder & CEO at Cerebras Systems
Niche: Technology
Revenue: Approx. $72 Million/month
Location: Sunnyvale, California, United States
Started: 2016
Our architecture features a million identical tiles with built-in redundancies. If a single tile fails, we shut it down and route the calculations to a redundant tile. We also water-cool the systems, running them much colder than GPUs to reduce temperature-related failures.
0
From the Full Interview
This answer is part of a full interview with Andrew Feldman, Co-founder & CEO at Cerebras Systems.
Share this Answer
Found this insight valuable? Share it with your network to help others learn from Andrew Feldman's experience.
Cite This Answer
Use this answer in your research, article, or academic work
Related Answers
How does the current AI chip demand cycle differ from historical semiconductor boom-and-bust cycles?
By Jensen Huang
Technology
$1M+/mo
How does your custom chip architecture compare to standard options?
By RJ Scaringe
Technology
Approx. $460 Million /mo
How do you manage content moderation at YouTube's scale?
By Neal Mohan
Technology
Approximately $4.5 Billion USD/mo
What does speed mean in terms of user experience metrics?
By Andrew Feldman
Technology
Approx. $72 Million/mo
How does the Netflix evolution analogy apply to the impact of fast inference?
By Andrew Feldman
Technology
Approx. $72 Million/mo
How do you define the different choices made in the specialized chip landscape?
By Andrew Feldman
Technology
Approx. $72 Million/mo
What is Broadcom's Jalapeno chip, and how does it fit into OpenAI's strategy?
By Andrew Feldman
Technology
Approx. $72 Million/mo