OpenAI Says Its Model Improved the PPA of AMD GPU IP by Up to 14% in Less Than Five Months
OpenAI partnered with AMD to improve the power, performance, and area metrics of AMD’s flagship GPU IP by up to 14% in less than five months, with some changes already incorporated into designs sent for fabrication. GPT-6.2 Astra also achieved the best result of any model generation in tests on an open RISC-V processor core. Anthropic says Mythos completed in three days prompt-processing work for the AMD MI355X GPU that would normally take 6 to 12 months.
Why read this
SelectedAI score 78
The two companies’ chip design case studies provide clear timeline and performance data that can help illustrate efficiency gains in AI-assisted hardware engineering.
Topics
Body
Working with AMD, OpenAI achieved up to 14 percent PPA improvement (power, performance, and chip area) on AMD's flagship GPU IP in less than five months. According to OpenAI , that equals about a year's worth of progress on top of designs AMD's engineers had already optimized for years. AMD has already folded some of the changes into a design sent to manufacturing, OpenAI says.
The same method also helped with Jalapeño , OpenAI's first custom inference chip. In tests with open RISC-V processor cores, the new GPT-6.2 Astra model delivered the best results across model generations. OpenAI is also working with Synopsys on GPT-Synopsys , a model that uses Synopsys's EDA tools to make AI-assisted chip design more broadly accessible.
Anthropic is using AI in chip work too . Its Mythos model handled prompt processing for a model on AMD MI355X GPUs in just three days instead of the six to twelve months Anthropic says the task normally takes. The company now runs Claude on four chip families to optimize cost and performance per dollar.
AI Trends