Samsung to Use TSMC Process for NVIDIA Custom Memory Chips

Oct 18, 2026
Samsung reportedly will use TSMC's 3 nanometer process to produce base dies for NVIDIA's custom high bandwidth memory chips.

Samsung Electronics will use the 3 nanometer process from Taiwan Semiconductor Manufacturing Company Limited, or TSMC, to make base dies for custom high bandwidth memory chips from NVIDIA, Reuters reports, citing the Seoul Economic Daily. This would be the first time Samsung has worked with TSMC during HBM manufacturing.

NVIDIA asked Samsung, SK hynix, and Micron Technology to use the TSMC process for NVHBM base dies and sixth generation DRAM technology for the core dies, according to the newspaper. NVHBM includes NVIDIA's custom memory controller in the base die to standardize its use across memory suppliers.

Samsung reportedly accepted the requirements after an internal review. The company plans to retain its own production model for standard HBM and custom products for other customers, while assessing whether its foundry could make NVHBM base dies if demand exceeds TSMC's capacity.

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.