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

Samsung Fab Line

Samsung announced today it has begun mass product of system-on-a-chip (SoCs) based on its 10nm procedure node. The company is claiming a technological first over rivals like TSMC and Intel, and believes devices with its 10nm technology could ship early on in 2022, though the business firm states that availability volition generally improve throughout the twelvemonth.

Co-ordinate to Samsung, its 10nm LPE (Low Power Early on) process node will offer "up to 30-percent increment in area efficiency with 27-percent higher performance or 40-percent lower power consumption." That "or" is important in this context, because information technology represents the caste to which manufacturers now have to brand narrow trade-offs between functioning and power consumption. Consider this, from Samsung'southward own page on its 45nm technology:

"The 45nm engineering doubles gate density of the 65nm process with the meaning depression power and low manufacturing cost that is 50% linear shrink in addition to xv% speed enhancements and 35% active power reduction."

Or this, from the company's page on its 32nm process node. "32nm HKMG process boasts up 30% higher speed, thirty% less power, 30% scaling with twice of SRAM density over 45nm engineering, making it ideal for high performance mobile applications."

In the erstwhile days, manufacturers were able to serve up gate density improvements, ability consumption gains, and higher clock speeds at the same time. Nowadays, you lot go to pick 1-2 of those features to emphasize and, if you're lucky, you don't have to reduce the third to compensate. This is one reason why manufacturers have introduced the concept of hybrid nodes, and of long-lived versus short-lived nodes — it doesn't make sense for all companies to button for each and every accelerate in the semiconductor market. Some firms go on pushing into every new node for SoCs (Apple, Samsung Exynos, Qualcomm). Other components, similar GPUs, are hopping betwixt nodes, targeting the ones that make the most sense. Neither AMD nor Nvidia have said anything about whether they will adopt 10nm; the products that we know of scheduled for early 2022 are nevertheless built on 14nm hardware.

Industry predictions, features diverge

In the past, when node shrinks were more uniform, there was broad agreement in the industry about the features and characteristics of any given node. This is no longer the case. Samsung is positioning its 10nm node equally a long-lived node and a successor to 28nm, while TSMC intends to focus on 7nm every bit its adjacent major deployment, with relatively express rollout on 10nm. GlobalFoundries is also skipping 10nm, with a focus on pushing straight for 7nm. Each foundry has different applied science and follows different pattern rules, which is 1 reason why you can't easily port designs from one foundry to another. Simply also makes it more than difficult to cleanly compare their respective solutions.

Samsung intends to start rolling out 10nm LPP next twelvemonth, as the follow-up to 10nm LPE, just as its modern 14nm LPP is a follow-up to the 14nm LPE that debuted in 2022. Intel isn't expected to have 10nm ready until mid-2017, but its die shrinks have traditionally been smaller than its competitors. Whether this makes Intel's process technology "better" is a complicated question that depends on your indicate of view. Historically, Intel has had difficulty competing against the merchant foundries within relevant price brackets. One might fairly say that exterior of its contra-revenue shipments, Intel chips accept tighter manufacturing tolerances and smaller characteristic sizes in some cases, merely too tend to cost significantly more.

The ane thing nosotros can predict about the future of semiconductor manufacturing, bold that GF, Intel, Samsung, and TSMC pull off their corresponding roadmaps, is that node names will encapsulate fifty-fifty less relative information — and nosotros'll take to dig deeper into design rules and specifications to accurately capture the differences between these technologies. The companies are all pursuing different strategies to their 10nm and 7nm targets, and until we see some apples-to-apples comparisons information technology's difficult to predict who will take an edge on any given procedure node.