XCENA Raises $135 Million to Advance Memory Centric AI Chips

May 30, 2026
XCENA has raised $135 million in a Series B round to accelerate the development and deployment of its MX1 computational memory chip, which brings compute closer to memory to improve AI efficiency.
XCENA Raises $135 Million to Advance Memory Centric AI Chips

XCENA has raised $135 million in a Series B financing round to scale its global operations and accelerate deployment of its MX1 computational memory chip, announced in a press release. The funding values the company at $570 million and brings its total fundraising to $185 million.

The round was co-led by Atinum Investment and IMM Investment, with participation from Corstone Asia and several existing backers including SBI Investment and Mirae Asset Capital. The company plans to use the new capital to expand customer deployments, strengthen market reach, and continue development of its next generation memory centric computing solutions.

XCENA’s MX1 chip integrates compute capabilities directly within memory modules, allowing data processing to occur near where data is stored instead of routing it through separate CPUs and GPUs. Built on the Compute Express Link 3.x standard, the chip is designed to reduce latency and energy use while improving performance in AI infrastructure.

Founded by former engineers from Samsung and SK hynix, XCENA operates from offices in South Korea and California. The company expects to validate MX1 performance with enterprise partners and begin production by the end of 2026.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Funding Brief, Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Funding News AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

AI Funding Brief

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.