AMD, like other major chip designers, has already started using artificial intelligence in its chip design. In fact, AMD’s chief executive, Lisa Su, says his AI-enabled tools will eventually dominate chip design as the complexity of modern processors increases exponentially. I think so.
At the 2023 World Artificial Intelligence Conference (WAIC) in Shanghai, Su said he believes AI will dominate certain areas of chip design. She also emphasized the need for interdisciplinary collaboration to enable better hardware designs in the future, her report said. Digi Times.
Previously, Nvidia CEO Jensen Huang and AMD Chief Technology Officer Mark Papermaster said chip development was an ideal application for AI. AMD already uses AI to design, test and validate its semiconductors. The company also intends to use generative AI more extensively in future chip design applications.
At AMD, AI has already been introduced into chip design, particularly the “place and route” stage, where sub-blocks of the chip design are placed and optimized for increased performance and reduced energy consumption, Papermaster said. Told. tom’s hardware in May. AI’s ability to continuously iterate and learn from patterns greatly accelerates the process of achieving optimized layouts, improving performance and energy efficiency. Papermaster said AI will extend to more important aspects of chip design, such as microarchitectural design, especially after certain hurdles to protect intellectual property are overcome.
AI is already being employed in verification suites to reduce the time required to find bugs during the chip development process, from concept to verification to validation stages. Additionally, AI assists in generating test patterns. Chip designs contain billions of transistors, and comprehensive test coverage is essential to ensure defect-free products leave the manufacturing floor. The ability of AI to learn from each successive run, identify gaps in test coverage, and adjust test focus accordingly, greatly speeds up the process and enhances test coverage.
Artificial intelligence (AI) is playing an increasingly important role in supporting and assisting chip design. All three major manufacturers of electronic design automation (EDA) tools (Ansys, Cadence, and Synopsys) offer AI-enabled software to their customers, but he believes Synopsys is a bit ahead of its competitors when it comes to AI-enabled tools. seems to be going
Earlier this year, Synopsys launched Synopsys.ai, the first end-to-end AI-driven EDA solution. This will enable developers to use AI at every stage of chip development, from architecture to design to manufacturing.