10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

By Doug Black

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been instrumental to AMD’s datacenter market resurgence. Nanometer cachet is incalculable: on it, companies, careers and fortunes are made and lost.

But that cachet is coming into question. As with the Linpack benchmark for ranking HPC system performance, a growing chorus of voices is calling for other ways to assess and characterize chips.

Before further discussion, let’s define our terms. A nanometer is one billionth of a meter, also expressed as 0.000000001 or 10-9 meters (for perspective, hair grows at roughly 1 nm per second**). In chip design, “nm” refers to the length of a transistor gate – the smaller the gate the more processing power that can be packed into a given space.

Some chip technologists argue that the nanometer is too narrow a measure of chip advancement. Writing in IEEE last month, nine computer scientists from MIT, Stanford, University of California/Berkeley and Taiwan-based chip manufacturer TSMC have put forward a new “density metric” designed to be a more holistic gauge. The nanometer metric “is all but obsolete today,” they said, for not simultaneously accounting for logic, memory and packaging/integration technologies. What’s needed is to capture a broader set of system-level performance indicators, connecting “the device technology advances to system-level benefits in a comprehensive fashion while acknowledging the synergy between various components.”

Available at https://purl.stanford.edu/jj585np1768, the data “suggest that a balanced growth between logic, memory and connectivity has been an implicit guide for computing system optimization,” according to the authors.

Classifying chips by transistor gate length – the “node number” – has been around since the 1960s. But over the past decade, “driven by competitive marketing,” the nanometer metric has been pushed, pulled and distorted in several ways, the authors stated. For one, the node number “has become decoupled from, and can be several times smaller than, the actual minimum gate length.” For another, different semiconductor manufacturers brand similar logic technologies with “different node labels, thus creating further confusion.”

They also point out that while 5nm chips are slated to go into production next year, the next-generation node will be 3nm, so “we will soon run out of nanometers for naming future generations of technologies.” More importantly, 3nm is roughly the size of about 12 atoms, so small it could create doubts that semiconductor technology advancement is nearing physical limits.

“Yet, it is a foregone conclusion that the semiconductor industry will continue to make progress,” the authors asserted, “because there are still many ways to advance semiconductor technology beyond 2-D miniaturization and also because societal demand for more capable electronic systems is insatiable.”

In place of the nm node number, the authors’ proposed “LMC density metric” would be a three-part number reflecting the relationship between density and “benefits for more advanced computing systems — the primary driver for progress in semiconductor technology.”

The three numbers:

  • DL: density of logic transistors in #/mm2
  • DM: bit density of main memory (currently the off-chip DRAM density in #/mm2)
  • DC: density of connections between the main memory and logic (in #/mm2)

The authors said that, based on design specifics, today’s leading edge technologies can be characterized by [38M, 383M, 12K].

“These three components of the system metric contribute to the overall speed and energy efficiency of computing systems,” the authors said. “This balance is implicit in computer architectures and allows the improvement of overall system performance in an optimal fashion.” They also noted that historical data show a “correlated growth” in logic, memory and connectivity, suggesting “a balanced increase of DL, DM, and DC for the decades to come.”

The metric places particular focus on the integrations of logic, memory and connectivity, the authors said. “In addition to being consistent with historical trends and our intuition about computing systems, the LMC density metric is applicable and extensible to future logic, memory, and packaging/integration technologies.”

Acknowledging that chip vendors may “continue to use their preferred labels to market their technologies,” the authors said the LMC density metric could foster “clear communications” by serving “as a common language to gauge technology advances among semiconductor manufacturers.”

Above all, the authors said, the LMC density metric “takes the semiconductor industry out of the quandary of using the vanishing nanometer as a label to describe advancements in semiconductor technology that will remain very important to society for a very long time to come.”

*  Roughly corresponding to Intel’s (delayed) 10nm process node

**  See comments from Phil Moriarty, professor of physics, School of Physics and Astronomy, University of Nottingham

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!

HPE and NVIDIA Join Forces and Plan Conquest of Enterprise AI Frontier

June 20, 2024

The HPE Discover 2024 conference is currently in full swing, and the keynote address from Hewlett-Packard Enterprise (HPE) CEO Antonio Neri on Tuesday, June 18, was an unforgettable event. Other than being the first busi Read more…

Slide Shows Samsung May be Developing a RISC-V CPU for In-memory AI Chip

June 19, 2024

Samsung may have unintentionally revealed its intent to develop a RISC-V CPU, which a presentation slide showed may be used in an AI chip. The company plans to release an AI accelerator with heavy in-memory processing, b Read more…

ASC24 Student Cluster Competition: Who Won and Why?

June 18, 2024

As is our tradition, we’re going to take a detailed look back at the recently concluded the ASC24 Student Cluster Competition (Asia Supercomputer Community) to see not only who won the various awards, but to figure out Read more…

Qubits 2024: D-Wave’s Steady March to Quantum Success

June 18, 2024

In his opening keynote at D-Wave’s annual Qubits 2024 user meeting, being held in Boston, yesterday and today, CEO Alan Baratz again made the compelling pitch that D-Wave’s brand of analog quantum computing (quantum Read more…

Apple Using Google Cloud Infrastructure to Train and Serve AI

June 18, 2024

Apple has built a new AI infrastructure to deliver AI features introduced in its devices and is utilizing resources available in Google's cloud infrastructure.  Apple's new AI backend includes: A homegrown foun Read more…

Argonne’s Rick Stevens on Energy, AI, and a New Kind of Science

June 17, 2024

The world is currently experiencing two of the largest societal upheavals since the beginning of the Industrial Revolution. One is the rapid improvement and implementation of artificial intelligence (AI) tools, while the Read more…

HPE and NVIDIA Join Forces and Plan Conquest of Enterprise AI Frontier

June 20, 2024

The HPE Discover 2024 conference is currently in full swing, and the keynote address from Hewlett-Packard Enterprise (HPE) CEO Antonio Neri on Tuesday, June 18, Read more…

Slide Shows Samsung May be Developing a RISC-V CPU for In-memory AI Chip

June 19, 2024

Samsung may have unintentionally revealed its intent to develop a RISC-V CPU, which a presentation slide showed may be used in an AI chip. The company plans to Read more…

Qubits 2024: D-Wave’s Steady March to Quantum Success

June 18, 2024

In his opening keynote at D-Wave’s annual Qubits 2024 user meeting, being held in Boston, yesterday and today, CEO Alan Baratz again made the compelling pitch Read more…

Shutterstock_666139696

Argonne’s Rick Stevens on Energy, AI, and a New Kind of Science

June 17, 2024

The world is currently experiencing two of the largest societal upheavals since the beginning of the Industrial Revolution. One is the rapid improvement and imp Read more…

Under The Wire: Nearly HPC News (June 13, 2024)

June 13, 2024

As managing editor of the major global HPC news source, the term "news fire hose" is often mentioned. The analogy is quite correct. In any given week, there are Read more…

Labs Keep Supercomputers Alive for Ten Years as Vendors Pull Support Early

June 12, 2024

Laboratories are running supercomputers for much longer, beyond the typical lifespan, as vendors prematurely deprecate the hardware and stop providing support. Read more…

MLPerf Training 4.0 – Nvidia Still King; Power and LLM Fine Tuning Added

June 12, 2024

There are really two stories packaged in the most recent MLPerf  Training 4.0 results, released today. The first, of course, is the results. Nvidia (currently Read more…

Highlights from GlobusWorld 2024: The Conference for Reimagining Research IT

June 11, 2024

The Globus user conference, now in its 22nd year, brought together over 180 researchers, system administrators, developers, and IT leaders from 55 top research 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…

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…

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…

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…

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…

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…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. 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…

Leading Solution Providers

Contributors

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... 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…

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…

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 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…

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…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to 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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire