Synopsys Users Group (SNUG)’s Post

Here is a great case study by Synopsys Inc's Johannes Stahl and Rebellions' CTO Jinwook Oh on how the combination of virtual prototyping and emulation accelerated validation and ensured scalability and flexibility to validate an expanding product line with a unified design flow for AI applications. "Rebellions' partnership with Synopsys and the integration of ZeBu and Virtualizer into its chip design workflow exemplify a synergistic approach to innovation in AI hardware for complex AI workloads. By exploiting the advantages of cutting-edge emulation technology, Rebellions not only enhances the performance and reliability of its AI accelerators but also accelerates its path to market readiness." #Synopsys #Rebellions #ArtificialIntelligenceAI https://bit.ly/4bI3ori

Moore's Law may be slowing down, but the semiconductor industry's innovation is far from over. Enter chiplets—a potential solution to the challenges of scaling. Instead of trying to fit more transistors on a single chip, chiplets allow for multiple smaller, specialized chips to be integrated into one package, enhancing flexibility, performance, and scalability. Sid Sheth, co-founder of AI chip startup d-Matrix, explains that chiplets can pack more functionality by splitting larger chips into smaller ones, boosting overall compute power without size limitations. d-Matrix’s Jayhawk II processor exemplifies this approach, using chiplets for AI models like large language models (LLMs). Chiplets also bring faster development and cost efficiency, as they are customizable and reusable. Companies like Tenstorrent and Netrasemi are leveraging chiplet-based architecture for AI and high-performance computing. While the concept isn’t new, advances in packaging and interposer technology make it more accessible today, pushing the chip industry towards a chiplet-based future. Sid Sheth | d-Matrix | Stan Sokorac

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.

Learn how Supermicro and NVIDIA enable #telecom companies to transform into trusted, sovereign AI factories for national governments, enterprises, and startups to build and deploy #generativeAI applications finetuned to local language and cultural standards.