With plans to go into mass production next year, Silicon Valley startup d-Matrix recently announced that shipments of its first artificial intelligence (AI) chip are underway. The chip is made to improve communication with AI systems, allowing for quicker and more effective responses in applications like chatbots and video production.
The Santa Clara, California-based company aised more than $160 million, including funding from Microsoft’s venture capital arm. Sample chips are already being tested by early customers, and wider availability is anticipated next year. While specific customer information is still undisclosed, d-Matrix confirmed that it will work with Super Micro Computer to incorporate these innovative chips into servers.
The company’s chips are designed to complement those of AI chipset giants like Nvidia, whose capabilities are mostly used for training AI systems on large datasets. In contrast, the chips from d-Matrix are designed for “inference” — rapidly handling user requests once the system has been trained. Even when customers request new responses or visual modifications, the chips are able to manage tasks effectively since they can handle several user requests on a single chip at once.
According to d-Matrix CEO Sid Sheth, there is a lot of interest in video-related applications. Customers want to create videos that enable individual user interactions. This growing demand highlights the chip’s potential to satisfy the evolving requirements of advanced digital experiences.
“We are getting a lot of interest in video use cases where we have customers coming and saying, ‘Hey, look, we want to generate videos, and we want a collection of users, all interacting with their own respective video,'” stated the CEO, according to a report by Reuters.
Notably, this development comes shortly after Microsoft’s announcement of many more features for Copilot, its generative AI-based assistant, at its Ignite 2024 conference.
- Apple iOS 18.3 to Have Exciting New Features! - January 13, 2025
- Google is Assembling an Advanced ‘world modeling’ AI team - January 9, 2025
- The Year in AI: Top Breakthroughs that Redefined Technology in 2024 - January 7, 2025
