OpenAI says its models matched a year of AMD chip optimization in under five months
OpenAI says its models delivered a year's worth of chip optimization on top of AMD's own engineering
OpenAI says that working with AMD, its models achieved up to 14 percent PPA improvement on AMD's flagship GPU IP in less than five months, which OpenAI describes as roughly a year's worth of progress on top of designs AMD engineers had already optimized for years. AMD has already folded some of the changes into a design sent to manufacturing, and the same method helped with Jalapeño, OpenAI's first custom inference chip. OpenAI adds that the GPT-6.2 Astra model gave the best results across model generations in tests with open RISC-V processor cores, and that it is working with Synopsys on GPT-Synopsys to make AI-assisted chip design more broadly accessible.
OpenAI reports a 14 percent PPA gain on AMD's flagship GPU IP in under five months, offering a concrete case of AI models contributing to chip design work.
Source:The Decoder · the-decoder.com