San Francisco-based semiconductor startup Volantis has raised $88 million in venture capital to develop technology aimed at addressing a major bottleneck in AI chips — the speed at which computing components can communicate with memory. The company is developing a system that uses beams of laser light instead of tiny electrical connections to transfer data between processors and memory chips, potentially allowing far more memory to be connected to a single GPU.
Volantis plans to use vertical-cavity surface-emitting lasers, or VCSELs, a technology already used in facial-recognition systems across millions of consumer devices, including iPhones. The company says its approach could increase the number of memory chips surrounding a GPU from about eight in current high-end systems to as many as 220. Volantis aims to deliver a chip next year that could accelerate AI workloads such as coding, according to CEO and co-founder Tapa Ghosh.
The funding round was led by Stripe veteran Lachy Groom and Abstract Ventures, with participation from John Doerr, VXI Capital, Triatomic and Susa Ventures. Angel investors including AI podcaster Dwarkesh Patel, AI chip veteran Naveen Rao and Anthropic researcher Sholto Douglas also participated. Volantis hopes its use of established optical and semiconductor technologies will help it overcome some of the supply-chain and advanced-packaging challenges facing the rapidly expanding AI chip industry.
Pic courtesy: google/ images are subject to copyright
