UMC and AP Memory Partner on Power Delivery for AI Systems

Oct 22, 2026
UMC and AP Memory are combining capacitor technology, chip designs and wafer manufacturing to improve power delivery in AI and high performance computing systems.

United Microelectronics Corporation (UMC) and AP Memory announced in a press release a technology and manufacturing collaboration for power delivery systems used in AI and high performance computing. The companies will combine UMC's deep trench capacitor technology and wafer manufacturing with AP Memory's silicon capacitor designs and system integration.

AP Memory completed tape out and initial functional validation of its S SiCap Gen2D discrete silicon capacitor designs in the third quarter of 2026. The companies will next conduct system level performance and reliability tests using capacitors in substrate packages across different capacitance and operating voltage requirements.

The capacitors can be integrated into an interposer, substrate or landside area of an advanced package. UMC and AP Memory are also considering capacitor embedded interposers and landside capacitors for other system designs.

We hope you enjoyed this article

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

Also, consider following us on social media:

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

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

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.