HARDWARE

Samsung Foundry: 2nm silicon in 2025


One of the key semiconductor technologies outside of 3D FinFET transistors are Gate-All-Around transistors, which promise to help expand the ability to manage processors and components to higher performance and lower power. Samsung has always announced that its first generation GAA technology will align with its ‘3nm’ nodes, with its 3GAE and 3GAP processes. As part of the Samsung Foundry Forum today, more insight into the timeline of the introduction is given, as well as a discussion of its 2nm process.

It was generally expected that, after the standard FinFET consumed money, the semiconductor manufacturing industry would shift to GAAFET design. Each of the leading manufacturers calls its implementation something different (RibbonFET for Intel, MBCFET for Samsung), but they all use the same basic principle – a flexible-width transistor with several layers that help start the current of the transistor. Where FinFETs rely on multiple quantized source / drain fins and cell height with multiple fin traces, GAAFETs allow single variable-length fins, allowing current for each individual cell device to be optimized for power, performance, or area.

All major manufacturers have been discussing GAAFETs at technical semiconductor conferences for many years. For example, at the International VLSI Conference in June 2020, the then Intel CTO, Dr. Mike Mayberry, presented a diagram with improved electrostatics of the transition to GAA design. At the time, we asked about Intel’s time frame for extensive GAA implementation, and we were told we expected them “within 5 years”. Currently Intel’s RibbonFET should come with a 20A process, which is likely to be produced by the end of 2024. TSMC in contrast presents its equivalent technology with its 2nm process nodes, stating that they can extend the life of their FinFET technology by another generation in 3nm . The exact time frame for the introduction of TSMC is still quite unclear at this time, as the company expects its N5 and N3 offerings to be extensive nodes with a long lifespan.

Samsung actually surprised us a few years ago, announcing that it had a prototype version of its GAA technology in early 2019. The company said it would deliver its v0.1 development package to its partners, allowing them to experiment with the design rules required by Samsung. That has improved over time, and at a presentation a few months ago at a conference in China alone, the company said a version of its 3nm GAA technology would be on track to be implemented in 2022. Today, Samsung is reaffirming and expanding those expectations.

In an interview with Samsung’s MoonSoo Kang, senior vice president of Samsung’s foundry market strategy, he presented the following schedule for Samsung’s GAA process nodes:

  • 3GAE will go into mass production by EoY 2022
  • 3GAP follows in a year for mass production at EoY 2023
  • 2GAP will need a few more years, mass production in 2025

He added a warning that these are mass production schedules – the products on the shelves will depend on customers and their own distribution. Of this, we usually add one or two quarters (3-6 months) after these times, so 2GAP is realistically a 2026 end-user product based on these schedules.

This is the first thing Samsung says about its 2nm process technology, and it comes as an iterative optimization with what Samsung expects to offer with 3nm variants. Exact details about the performance expectations of these process nodes can be presented later today at the Samsung Foundry Forum 2021. Follow us for additional coverage.



Source link

Naveen Kumar

Friendly communicator. Music maven. Explorer. Pop culture trailblazer. Social media practitioner.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button