TSMC Chip
Image Credit: TSMC

Naming convention, and nomenclature, can potentially affect the successful marketing of products and product lines. Head of Marketing Godfrey Cheng of Taiwan Semiconductor Manufacturing Company recently spoke about this dynamic. As a guest on AMD’s ‘Meet the Experts‘ he goes into some detail regarding the current node naming convention.

The current path

TSMC is well known for leading the race for the incredible shrinking die. Their node process has helped propel AMD back to for forefront of the consumer market. AMD’s current Ryzen and Navi product lines both use TSMC’s 7nm or N7 nodes. The next increment will be 5nm, or N5, and then 3nm, or N3. Samsung recently announced they’ve begun producing a 3nm node. Obviously we’ll soon hit a point where this naming convention will no longer work. However it seems that this standard is not as accurate of a descriptor as it would seem. Mr. Cheng explained that this has been the case since nodes were at the 0.35 micron level. He goes on to elaborate that the current descriptor does not accurately represent the physical transistor density.

Godfrey Cheng is not alone in this observation. Intel has spoken up about this numerous times. PCGamesN noted one such blog post from 2017. In that post Mark Bohr referenced Moore’s Law and its relation to the industry standard. He notes the current practice simply names by 0.7 times smaller such as 90nm, 65nm, 45nm, etc. This practice is used even when a particular manufacturer does not indeed have said transistor density. Both share the opinion that the current naming convention does not require manufacturers to accurately describe the architecture or transistor density. In turn it prevents customers from being able to easily identify unique processes of each node. Intel has proposed going to a transistor naming density formula instead.

Don’t Miss Out on More FPS Review Content!

Our weekly newsletter includes a recap of our reviews and a run down of the most popular tech news that we published.

Peter Brosdahl

As a child of the 70’s I was part of the many who became enthralled by the video arcade invasion of the 1980’s. Saving money from various odd jobs I purchased my first computer from a friend of my...

Join the Conversation

5 Comments

  1. They wouldn’t need to change the naming convention , ef everyone just stuck to the standard that already exists instead of lying and coming up with “marketing numbers” for node size, based on a combinantion of gate length and half pitch.

    You don’t get to have a new standard just because you have been lying about what your process is for years.

    ITRS defined it. Stick to the original ITRS definition.

    Shoot everyone in marketing in the head.

    Problem solved.

  2. Actually, here is some interesting information I was unaware of [URL=’https://en.wikichip.org/wiki/technology_node’]courtesy of WikiChip[/URL]:

    So, process nodes were originally named after gate length.

    This held up until 1997. At that point the gates actually shrunk FASTER than the names. At the time Intel hit their 45nm process, the gate length was actually 25nm, so they were using a higher number for their nodes than was accurate.

    That’s where further gate shrinkage did not work. Other features kept getting smaller, but gates kept the same size or got larger. 32nm actually had larger gates than 45nm.

    Gates have not really shrunk since Intel’s 45nm process (when they were 25nm in size), but all other features have kept shrinking and ocverall chips have become more and more dense, despite the gates staying at or above 25nm.

    The part I don’t understand is why the ITRS definition of a process node which is [I]”the smallest half-pitch of contacted metal 1 lines allowed in the fabrication process”[/I] can’t still be used.

    Unless I have misunderstood the terminology, this seems to not care about what feature you are talking about (gate or whatever) and is more concerned with the smallest feature a process can support, which seems like a very reasonable way of measuring a process.

    The only reason fabs don’t do this – I presume – is for marketing purposes.

    So, I stand by my statement that marketers should be shot.

  3. As a person in the enterprise space… I really wish the sales people of corporations were not full of attractive women that brought along engineers and more. Engineers… Be use I wouldn’t entertain so many offers that are meaningless. 😉

Leave a comment