This chip startup just raised $135M on a bet that AI’s biggest bottleneck isn’t compute — it’s memory
AI-summarised brief · reviewed before publication
XCENA, a four-year-old startup, has raised $135 million in a Series B funding round at a valuation of $570 million. The company aims to solve the bottleneck in AI infrastructure by designing a chip that places compute capabilities closer to DRAM, reducing the need for costly round trips between CPUs, GPUs, and memory. XCENA's MX1 chip connects to the CPU through CXL, processing data before it leaves the memory module, and the company claims it can potentially run on just one server what used to require 10.