OpenAI Models Identify Up to 14% PPA Improvements in AMD Flagship GPU IP
OpenAI partnered with AMD, and its models identified up to 14% PPA improvements in less than five months for flagship GPU IP that engineers had already optimized for years. The same approach also improved Jalapeño, OpenAI’s first custom inference chip, with the gains validated in real silicon; OpenAI is working with Synopsys to bring model capabilities together with EDA design and verification tools to more chip designers. https://t.co/4BNcPIqfIQ
Why read this
SelectedAI score 68
These results demonstrate the quantifiable benefits of using models in chip design optimization and provide a case study extending from design evaluation to validation in real silicon.
Topics
Body
Working with @AMD, our models identified up to 14% PPA improvement on flagship GPU IP in less than five months—building on designs AMD’s engineers had already spent years optimizing.
The same approach helped improve Jalapeño, our first custom inference chip, with gains verified on real silicon.
New evaluations also show our models getting better at certain chip design tasks.
We’re sharing these results and how we’re working with @Synopsys to bring our model capabilities and their trusted EDA design and validation tools to more chip designers.
https://t.co/4BNcPIqfIQ
AI Trends