Why did Cerebras choose to build a dinner-plate-sized wafer-scale chip?
Replied byAndrew Feldman
Co-founder & CEO at Cerebras Systems
Niche: Technology
Revenue: Approx. $72 Million/month
Location: Sunnyvale, California, United States
Started: 2016
SRAM memory is exceptionally fast but cannot store much data per unit area. To hold the weights of modern AI models on fast SRAM, we had to build a chip that was forty-six thousand square millimeters, which is fifty-eight times larger than a standard GPU.
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
Why did Rivian choose to develop its own in-house AI inference chip?
By RJ Scaringe
Technology
Approx. $460 Million /mo
Why does Cerebras's wafer-scale engine process AI workloads faster than standard GPUs?
By Andrew Feldman
Technology
Approx. $72 Million/mo
How does Cerebras manage chip defects and yield reliability at the wafer scale?
By Andrew Feldman
Technology
Approx. $72 Million/mo
Why did you decide to build a factory capable of producing one rocket per month?
By Pawan Kumar Chandana
Technology
Pre-Revenue/mo
Why do you choose not to wear a watch or manage your life with an outlook calendar?
By Jensen Huang
Technology
$1M+/mo
What inspired you to leave Wall Street and build a space company?
By Srinath Ravichandran
Technology
Pre-revenue/mo
What advice would you give entrepreneurs who want to build something big?
By Fabricio Bloisi
Technology
$1M+/mo