This site may earn affiliate commissions from the links on this page. Terms of utilise.

Nvidia-Feature

Nvidia's Pascal GPU family unit has been tremendously successful, but the company is already looking ahead to a new architecture, codenamed Volta. Details on the scrap are scarce, though Nvidia has previously given guidance that Volta would exist its kickoff consumer HBM2 product and would characteristic a stacked memory architecture. Now, rumors are flying that the fleck will actually be built on TSMC's "new" 12nm node.

The reason we've put the word in quotes is because 12nm isn't really a new node at all. Here'due south how TSMC'southward CC Wei described information technology in TSMC's concluding quarterly conference phone call.

[O]ur strategy is continuously to improve every node in the performance, such equally 28 nanometer. And are continuing to meliorate the 16 nanometers engineering. And we have some very good progress, and you lot might call it the 12 nanometer because we're improve in the density, classical density, operation and power consumption. Yes, we have that.

TSMC appears to be performing the same kind of optimization and improvement to existing nodes that every foundry performs over fourth dimension. Information technology'south just that this fourth dimension, they're calling it something a piffling unlike.

TSMC-28nm

This photo shows TSMC's various types of 28nm technology and their respective characteristics at a very high level. The deeper you drill into the characteristics of each sub-blazon, the larger the differences become. A device congenital on TSMC's 28LP process would have very different characteristics than a device built on 28HP, even though both are based on 28nm.

Over the final 20 years, information technology's become increasingly difficult to cleanly define a node. In the old days, node size and gate length were synonymous. As time has passed, the metrics for a new node accept grown more complex. Samsung, TSMC, and Intel all tend to brand their products as belonging to the same node (salvage for TSMC going with 16nm as opposed to 14nm), just that doesn't mean they are identical, as the nautical chart beneath demonstrates:

Intel-Features

Intel, TSMC, and Samsung feature sizes at 14nm.

Over the last few years, we've started to come across more and more than manufacturers taking this road. Samsung's 14nm technology is based on a respin of its original 20nm procedure, non the 20nm procedure it publicly reported when it outset discussed the applied science. It's debuted multiple variants of 14nm, while TSMC has both 16nm and 16FF+. Intel has respun 14nm into 14nm+, and some rumors propose the house will do a third respin (14nm++). TSMC likely isolated some additional improvements it could make to its 16nm node and decided to adopt a new naming convention.

Several years ago, I predicted we would begin to see more firms debuting their own methods of identifying process nodes as advances became more difficult and the speed of improvement fell. Samsung is positioning its 10nm node as a long-lived node, while TSMC believes its 10nm will be a short-lived process. Calling its new 16nm refresh "12nm" allows the company to appear to stay in well-nigh-lockstep with the rest of the industry, as opposed to falling behind information technology (even if that 'falling behind' is illusory and based in marketing classification, non fact). Intel's 10nm node will be smaller than Samsung's, but Intel generally marches to the beat of its own drum. But we're seeing a bit of jockeying for position and fifty-fifty dissimilar plans around specific nodes today that didn't used to be the case.

TSMC'due south 12nm process volition undoubtedly deliver some improvements over its 16FF+ node, but it's not going to be the same as a full-node compress, and the improvements may range from small to small. I'one thousand not too worried nigh how this could impact Volta, though. Nvidia has already demonstrated that it can evangelize a new GPU on the aforementioned process node with significant operation improvements, and Volta could turn out to be a major accelerate over Pascal, even if its 12nm node is more of a 16nm tweak.