OpenAI helped AMD improve its upcoming flagship GPU design by 14% PPA — GPT models also helped Lisa Su's outfit boost its new CPUs
OpenAI helped AMD improve its upcoming flagship GPU design by 14% PPA — GPT models also helping Lisa Su's outfit boost its new CPUs
OpenAI has disclosed further details about its collaboration with AMD, where engineers utilized undisclosed AI models to refine the upcoming flagship GPU and CPU designs. The partnership resulted in a 14% improvement in power, performance, and area (PPA) for the GPU circuitry and smaller single-digit gains for the processor. OpenAI's models excel in rewriting code describing chip circuits, achieving results equivalent to condensing a year's worth of conventional chip design work into under 5 months.
The company expects to continue refining PPA improvements in both GPU and CPU designs. OpenAI's AI models have previously assisted in designing the OpenAI Jalapeño chip for Broadcom, which has been tested with engineering samples since June 2026. The collaboration with AMD builds on this success, with both companies anticipating further advancements in chip design using AI technology.
Written by urgent.news from Tom's Hardware's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.