OpenAI reports AI-driven efficiency gains in AMD chip designs
OpenAI claims its AI models improved AMD's flagship GPU designs by up to 14% in power, performance, and area, while also accelerating its own in-house chip development.
🔌Chips & HardwarePhoto: thenextweb.com
Key points
- OpenAI models achieved 14% improvements in AMD's flagship GPU power, performance, and area.
- Internal 'Jalapeño' chip components were reduced in size by up to 13% using AI design techniques.
- OpenAI is partnering with Synopsys to train a specialized model for professional chip design tools.
OpenAI has announced that its artificial intelligence models successfully optimized the design of AMD’s flagship graphics processing units, resulting in efficiency gains of up to 14% across power, performance, and area metrics. By rewriting the code responsible for circuit descriptions and utilizing Synopsys software to verify the integrity of the changes, OpenAI reported achieving roughly one year of traditional engineering progress in less than five months. Some of these AI-suggested modifications have already been integrated into hardware currently in production.
The company applied similar methodologies to its own internal chip project, codenamed Jalapeño. These AI-driven optimizations reduced the size of two critical chip components by 10% and 13%, facilitating a transition from initial design to manufacturing in just nine months. Additionally, OpenAI reported that its latest model, GPT-6.2 Astra, demonstrated superior performance in both refining existing processor designs and generating new ones from scratch.
Despite these advancements, the integration of AI into semiconductor design remains a cautious process. Richard Ho, OpenAI’s chip lead, noted that the company does not yet fully trust AI-generated design changes, necessitating rigorous manual verification for every modification. Looking ahead, OpenAI is collaborating with Synopsys to develop a specialized model, GPT-Synopsys, designed to integrate directly with standard industry engineering software.
What to watch next: The performance of the upcoming GPT-Synopsys model and whether AI-assisted design becomes a standard workflow for major semiconductor manufacturers.
Source thenextweb.com — thenextweb.com/news/openai-models-amd-gpu-chip-design-14-percent ↗
Read next
🚀Startups & FundingOpenAI CEO Sam Altman Addresses Upcoming Biographical Film
OpenAI CEO Sam Altman commented on the upcoming film 'Artificial,' which portrays his life and the 2023 leadership crisis at the company.
🚀Startups & FundingRadixArk Unveils DaisyRose-27B, Focused on Agentic Efficiency
Startup RadixArk has launched DaisyRose-27B, an AI model optimized for long-horizon agent tasks, claiming significant improvements in training efficiency and reasoning ca…
🚀Startups & FundingBest Buy Reintroduces Physical Media After Brief Exit
Best Buy has resumed selling Blu-ray discs directly through its website and physical retail locations, reversing a policy that saw the retailer exit the physical media ma…
🏢Big TechMeta Staff Flag Privacy Concerns Over Muse AI Agent
Internal reports reveal that Meta employees identified significant privacy risks and unauthorized data access while testing the company's Muse AI agent.
🏢Big TechLeaked images suggest Lenovo is developing a budget-friendly Legion Go Beam handheld
Lenovo appears to be preparing a new, lower-cost handheld gaming device dubbed the Legion Go Beam, potentially signaling a shift toward more affordable hardware.
⚖️Regulation & PolicyUS Lawmakers Push to Limit Forced Arbitration and Target Deepfake Creators
Congress is racing to pass legislation that would restrict the use of forced arbitration in child safety cases and provide legal recourse for victims of nonconsensual dee…