Monday, October 12th 2026

GlobalFoundries Returns to Advanced-Node Race With 7 nm-Class FDX Fusion

Back in the now distant 2018, the semiconductor industry had three major players in contract leading-edge node manufacturing: TSMC, Samsung, and GlobalFoundries. At that time, Intel did not accept external clients. However, as node design became increasingly expensive—requiring multi-billion dollar investments—and more complex, with many players encountering yield and manufacturing difficulties, GlobalFoundries announced that it was stopping its 7 nm node development indefinitely. This left only two companies in the leading-edge race, but GlobalFoundries continued to develop unique semiconductor solutions that did not focus on smaller transistor sizes.

Today, the company is back at a similar stopping point but with a unique solution called FDX Fusion, based on fully-depleted silicon-on-insulator (FD-SOI) technology. Unlike traditional CMOS, GlobalFoundries takes substrate isolation a step further by creating a fully insulating layer beneath the channel. This enables highly specialized capabilities, such as ultra-low-power in-memory computing, seamless integration of embedded non-volatile memory (like eMRAM), and highly efficient dense logic designs. With FDX Fusion, GlobalFoundries claims 7 nm-class node characteristics in terms of size and twice the transistor density of the first-generation 22FDX node, which was designated as a 22 nm-class design.
For manufacturing, GlobalFoundries plans to start FDX Fusion mass production in 2028 at its advanced facility in Dresden, Germany. This facility will be one of the strongest manufacturing regions in Europe, making chip sovereignty another important factor with the start of mass production. Customers can expect to receive initial technology demos next year, with PDK shipping in mid-2027. GlobalFoundries sees this node as a highly specialized solution for physical AI layers, applicable in areas from automotive and ASIC to the physical world, with sensing, heavy computations, and new requirements.
Source: GlobalFoundries
Add your own comment

8 Comments on GlobalFoundries Returns to Advanced-Node Race With 7 nm-Class FDX Fusion

#1
kondamin
22 to 7 is a significant jump, I hope glofo scores a big hit with the node
Posted on Reply
#2
john_
kondamin22 to 7 is a significant jump, I hope glofo scores a big hit with the node
They used to manufacture 12nm processors for AMD and even had exclusivity agreements (Wafer Supply Agreements) that prohibited AMD from using other foundries (like TSMC) without paying a penalty or being forced to renegotiate those contracts. They had also started working on 7nm, until they finally decided that the development cost of the 7nm manufacturing technology could not be justified, thereby releasing AMD from their relevant contractual obligations. This is as far as I can remember. Ultimately, the high demand for advanced manufacturing nodes, combined with the fact that China has literally flooded the market with fabs producing chips on mature nodes, probably pushed them to rethink their strategy. They are not starting from scratch, but they will have to take the financial risk they avoided in the past and see where it leads them. Armed at least with a 7nm node today and a 5nm node tomorrow, they will maintain a technological edge over the majority of Chinese foundries, with the exception of SMIC.
Posted on Reply
#3
kondamin
john_They used to manufacture 12nm processors for AMD and even had exclusivity agreements (Wafer Supply Agreements) that prohibited AMD from using other foundries (like TSMC) without paying a penalty or being forced to renegotiate those contracts. They had also started working on 7nm, until they finally decided that the development cost of the 7nm manufacturing technology could not be justified, thereby releasing AMD from their relevant contractual obligations. This is as far as I can remember. Ultimately, the high demand for advanced manufacturing nodes, combined with the fact that China has literally flooded the market with fabs producing chips on mature nodes, probably pushed them to rethink their strategy. They are not starting from scratch, but they will have to take the financial risk they avoided in the past and see where it leads them. Armed at least with a 7nm node today and a 5nm node tomorrow, they will maintain a technological edge over the majority of Chinese foundries, with the exception of SMIC.
That wasn't on the depleted silicon it's announcing here.
A 3090 on this node would be interesting.**
**no, it wouldn't performance is just 7nm like, it's nothing like 7nm I should have read more carefully
Posted on Reply
#4
user556
kondaminThat wasn't on the depleted silicon it's announcing here.
A 3090 on this node would be interesting.
And reading into it a little I'd speculate that GlobF haven't just done this off their own bat. German government appears to have had a hand. A lighter touch of what US Government did for Intel.
Posted on Reply
#5
Athena
Announcing is one thing, but proving the tech is solid with a high yield rate is the only real thing that matters

Let's hope the $1.5B was worth it
Posted on Reply
#6
john_
kondaminThat wasn't on the depleted silicon it's announcing here.
You are right.
I am reading they tried going to 12nm FDX, but canceled it. Now they are trying to go one step further.
Posted on Reply
#7
Wye
Awwwww.
Someone shoot this sick dog.
Posted on Reply
#8
kondamin
WyeAwwwww.
Someone shoot this sick dog.
it's in a healthy financial position and doing well in it's niche
Posted on Reply
Nov 12th, 2026 04:39 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts