IBM Clears Path to 5nm with Silicon Nanosheets

By Tiffany Trader

June 5, 2017

Two years since announcing the industry’s first 7nm node test chip, IBM and its research alliance partners GlobalFoundries and Samsung have developed a process to build 5 nanometer (nm) chips by combining a novel switch architecture with advanced lithography techniques.

The heart of the R&D advance is a new gate-all-around architecture that employs stacked silicon nanosheets, replacing the FinFET structure used in today’s leading processors. Instead of having one single vertical fin, the horizontal “stack” can send signals through four gates, providing for better leakage control at smaller scales.

IBM Research scientist Nicolas Loubet holds a wafer of chips with 5nm silicon nanosheet transistors (Photo Credit: Connie Zhou)

“We understood that the FinFET structure is running out of steam at 7nm and we had to invent a new device structure which could continue the scaling for several more generations,” said Mukesh V Khare, vice president at IBM Research, in an interview with HPCwire.

According to IBM, the gate-all-around architecture paves the way for fingernail-sized chips (~600mm2, says Khare) packed with 30 billion transistors—50 percent more transistors than IBM’s 7nm process enables. IBM estimates that this would provide close to a 40 percent improvement in performance for the same power or 75 percent power savings at matched performance compared with today’s leading-edge 10nm technology.

The same Extreme Ultraviolet (EUV) lithography approach that IBM used to produce the 7nm test node was applied to the nanosheet transistor architecture. With EUV, the width of the nanosheets can be adjusted continuously, within a single manufacturing process. “This adjustability permits the fine-tuning of performance and power for specific circuits – something not possible with today’s FinFET transistor architecture production,” says IBM.

IBM and its research partners have built the transistors on 300mm wafers. “We put the entire process together, measure, validate and then our partners get full access to the technology to take it from proof point with us at IBM to manufacturing,” said Khare.

Khare emphasized, “These are not one chip or one device types of proof point; these are put together on a manufacturing scale fab which is used for research by IBM Research alliance, so this is a realistic toolset, the toolset that will eventually mature into the manufacturing toolset.”

Market analyst Jim McGregor of Tirias Research did not hesitate to call this a credible advance. “There are basically three pillars of innovation in semiconductor manufacturing,” he said. “One is the lithography process, which we’ve been completely constrained on but we’re slowly moving to EUV. The second is materials technology, which we’ve been advancing rapidly over the past decade through string silicon and other chemical makeups and the third area is transistor design. That has remained stagnant for many years, a couple decades, until we went to FinFET over the past couple years, however FinFETs are going to have their limitations architecturally and this [advance] is addressing that limitation and allows us to continue scaling, and continue basically Moore’s law. It also is injecting new materials that are going to be critical going forward, such as the the nanosheets and nanowires.”

As promising as the technical merits may be here, however, we cannot forget the economic considerations of Moore’s law, said McGregor, which will likely leave semiconductor makers like GlobalFoundries looking to leverage the FinFET technology for as long as possible to recoup the major investments that it and its partners have made. “I would estimate that at 5nm you will still see traditional FinFET,” said McGregor, “You may see IBM’s nanosheet architecture creep in later on, maybe as a sub-node to 5nm or a following process.”

IBM Research has already completed its work on the 7nm process that it introduced two years ago and transferred the technology to its manufacturing partners. IBM has said that its 7nm node will be reaching “manufacturing maturity” towards end of this year, or early next year. “The technology is very, very close,” said Khare, “and the cycle continues with another breakthrough. We will continue to work with our manufacturing partners to make this technology fully available, eventually they will decide the right timing based both on business leads as well as market drivers.”

Like the 7nm test chip before it, the latest semiconductor proof point is part of IBM’s $3 billion, five-year investment in chip R&D that was announced in 2014. As a fundamental building block for semiconductor technology, node advances will benefit all those market segments that can benefit from silicon technology scale, including high-performance computing, enterprise, and mobile. IBM, not surprisingly, is particularly focused on enhancing its cognitive computing and cloud platforms.

“Although a lot of people think of Intel when they think of semiconductor advancements, you have to remember that IBM and their development consortium accounts for a vast amount of innovation in semiconductor processing over the past 15 years or so especially,” said McGregor. “I’d say almost half of the major innovations have probably come from that alliance. It also helps push that new technology into manufacturing because these companies work so close together.”

Feature image caption: A scan of IBM Research Alliance’s 5nm transistor, built using an industry-first process to stack silicon nanosheets as the device structure (Photo credit: IBM)

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

ARM, Fujitsu Targeting Open-source Software for Power Efficiency in 2-nm Chip

July 19, 2024

Fujitsu and ARM are relying on open-source software to bring power efficiency to an air-cooled supercomputing chip that will ship in 2027. Monaka chip, which will be made using the 2-nanometer process, is based on the Read more…

SCALEing the CUDA Castle

July 18, 2024

In a previous article, HPCwire has reported on a way in which AMD can get across the CUDA moat that protects the Nvidia CUDA castle (at least for PyTorch AI projects.). Other tools have joined the CUDA castle siege. AMD Read more…

Quantum Watchers – Terrific Interview with Caltech’s John Preskill by CERN

July 17, 2024

In case you missed it, there's a fascinating interview with John Preskill, the prominent Caltech physicist and pioneering quantum computing researcher that was recently posted by CERN’s department of experimental physi Read more…

Aurora AI-Driven Atmosphere Model is 5,000x Faster Than Traditional Systems

July 16, 2024

While the onset of human-driven climate change brings with it many horrors, the increase in the frequency and strength of storms poses an enormous threat to communities across the globe. As climate change is warming ocea Read more…

Researchers Say Memory Bandwidth and NVLink Speeds in Hopper Not So Simple

July 15, 2024

Researchers measured the real-world bandwidth of Nvidia's Grace Hopper superchip, with the chip-to-chip interconnect results falling well short of theoretical claims. A paper published on July 10 by researchers in the U. Read more…

Belt-Tightening in Store for Most Federal FY25 Science Budets

July 15, 2024

If it’s summer, it’s federal budgeting time, not to mention an election year as well. There’s an excellent summary of the curent state of FY25 efforts reported in AIP’s policy FYI: Science Policy News. Belt-tight Read more…

SCALEing the CUDA Castle

July 18, 2024

In a previous article, HPCwire has reported on a way in which AMD can get across the CUDA moat that protects the Nvidia CUDA castle (at least for PyTorch AI pro Read more…

Aurora AI-Driven Atmosphere Model is 5,000x Faster Than Traditional Systems

July 16, 2024

While the onset of human-driven climate change brings with it many horrors, the increase in the frequency and strength of storms poses an enormous threat to com Read more…

Shutterstock 1886124835

Researchers Say Memory Bandwidth and NVLink Speeds in Hopper Not So Simple

July 15, 2024

Researchers measured the real-world bandwidth of Nvidia's Grace Hopper superchip, with the chip-to-chip interconnect results falling well short of theoretical c Read more…

Shutterstock 2203611339

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and imple Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the softw Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three Read more…

Generative AI to Account for 1.5% of World’s Power Consumption by 2029

July 8, 2024

Generative AI will take on a larger chunk of the world's power consumption to keep up with the hefty hardware requirements to run applications. "AI chips repres Read more…

US Senators Propose $32 Billion in Annual AI Spending, but Critics Remain Unconvinced

July 5, 2024

Senate leader, Chuck Schumer, and three colleagues want the US government to spend at least $32 billion annually by 2026 for non-defense related AI systems.  T Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Everyone Except Nvidia Forms Ultra Accelerator Link (UALink) Consortium

May 30, 2024

Consider the GPU. An island of SIMD greatness that makes light work of matrix math. Originally designed to rapidly paint dots on a computer monitor, it was then Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock_1687123447

Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

AMD Clears Up Messy GPU Roadmap, Upgrades Chips Annually

June 3, 2024

In the world of AI, there's a desperate search for an alternative to Nvidia's GPUs, and AMD is stepping up to the plate. AMD detailed its updated GPU roadmap, w Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

Intel’s Next-gen Falcon Shores Coming Out in Late 2025 

April 30, 2024

It's a long wait for customers hanging on for Intel's next-generation GPU, Falcon Shores, which will be released in late 2025.  "Then we have a rich, a very Read more…

Leading Solution Providers

Contributors

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire