Support us on Patreon
PayPalIntel did a press event yesterday where they announced Intel Accelerated, a whole new roadmap and they're doing away with nanometer naming with something a bit more bland.
For some time now it has seemed like Intel has been struggling to shrink down, and I can't help feel that part of their new naming is to get away from others thinking that too. That said, the new naming better matches their rivals and it was at times confusing when we saw things like Intel "14nm++" it started to make much less sense overall.
Their new naming is as follows:
Intel 7 (previously 10nm Enhanced SuperFin)
Delivering an approximately 10% to 15% performance-per-watt increase over Intel 10nm SuperFin through FinFET transistor optimizations, including increased strain, more low-resistance materials, novel high-density patterning techniques, streamlined structures and better routing with a higher metal stack. Intel 7 will be featured in products such as Alder Lake for client in 2021 and Sapphire Rapids for the data center, which is expected to be in production in the first quarter of 2022.
Intel 4 (previously Intel 7nm)
Providing an approximately 20% performance-per-watt increase over Intel 7, Intel 4 is the first Intel FinFET node to fully embrace extreme ultraviolet lithography (EUV), which involves a highly complex optical system of lenses and mirrors that focuses a 13.5nm wavelength of light to print incredibly small features on silicon. This offers a vast improvement over prior technology that used light at a wavelength of 193nm. Intel 4 will be ready for production in the second half of 2022 for products shipping in 2023,
including Meteor Lake for client and Granite Rapids for the data center.
Intel 3
Continuing to reap the benefits of FinFET, Intel 3 is expected to deliver around an 18% performance-per-watt increase over Intel 4. This is a higher level of transistor performance improvement than typically derived from a standard full node. Intel 3 implements a denser, higher performance library; increased intrinsic drive current; an optimized interconnect metal stack with reduced via resistance; and increased use of EUV compared with Intel 4. Intel 3 will be ready to begin manufacturing products in the second half of 2023.
Intel 20A
Ushering in the angstrom era with two breakthrough technologies, PowerVia and RibbonFET. PowerVia is Intel’s unique, industry-first implementation of backside power delivery – eliminating the need for power routing on the front side of the wafer and providing optimized signal routing while reducing droop and lowering noise. RibbonFET, Intel’s implementation of a gate-all-around transistor, is the company’s first new transistor architecture since it pioneered FinFETs in 2011, delivering faster transistor switching speeds while achieving the same drive current as multiple fins in a smaller footprint. Intel 20A is expected to ramp in 2024.
2025 and Beyond
Beyond Intel 20A, Intel 18A is already in development for early 2025 with refinements to RibbonFET that will deliver another major jump in transistor performance. Intel is also working to define, build and deploy next-generation High NA EUV, and expects to receive the first production tool in the industry. Intel is partnering closely with ASML to assure the success of this industry breakthrough beyond the current generation of EUV.
If you missed it, back in March we had Intel announce a big manufacturing expansion so this is another step forward. With this they're going up against the likes of TSMC, aligning their naming makes more sense. It means little for us normal consumers, other than Intel clearly having plans in place to continue pushing forward with new and more advanced CPUs and so eventually we will see even better gaming performance.
“Building on Intel’s unquestioned leadership in advanced packaging, we are accelerating our innovation roadmap to ensure we are on a clear path to process performance leadership by 2025,” Intel CEO Pat Gelsinger said during the global “Intel Accelerated” webcast. “We are leveraging our unparalleled pipeline of innovation to deliver technology advances from the transistor up to the system level. Until the periodic table is exhausted, we will be relentless in our pursuit of Moore’s Law and our path to innovate with the magic of silicon.”
Article taken from GamingOnLinux.com.
"Real man have fabs" is a thing from the 90's. With more and more complicated processes, you're
better off leaving it to external partners. The risks nowadays seem to outweigh the advantages by far.
Last edited by sub on 27 July 2021 at 10:33 am UTC
Quoting: subIntel will have a hard time to reestablish trust in the reliability of their manufacturing processes.
"Real man have fabs" is a thing from the 90's. With more and more complicated processes, you're
better off leaving it to external partners. The risks nowadays seem to outweigh the advantages by far.
Hmmm I would not be so categorical. The reason why they fell behind was much more a shitty management than bad engineering or even business model (having their own fab). They also did change course in the opening of their fabs to others, which seem like a sane idea.
Having your own fab avoid being stuck in a shortage as an example... It can also allow you to have better integration, more iterative passes on your design. So it is nothing to laugh at either.
As for the quality of their nodes, in term of density, their superfin node fell somewhere between TSMC's 5 and 7. So the renaming might actually make complete sense, they simply align relative to the naming used by TSMC. It has been years that the "nm" at the end of the name did not mean anything anymore. And it tended to cause confusion. Confusion that some other founders did use to their advantage.
Now, Intel is still relatively late for TSMC's 3nm equivalent, but it seems they are finally on track to catch up.
More marketing bullshit. MTr/mm² (million of transistors per square mm) was actually a nice unit. Spitting out stuff vaguely related to a number of nanometers, I can see myself needing to continue to explain for decades to come that no, gate lengths are still about 20 nm and the nanometers you are sold are just a proxy for transistor count (thanks to more and more 3D integration).
Plus, this reads like 20 Amperes, not 20 Ångströms. The symbol is Å. Granted, it's harder to type on most keyboards than it it to handwrite.
OK, besides my gripe about marketingspeech, I'm glad to see they keep investing at the cutting edge. We need more competition!
Last edited by MayeulC on 27 July 2021 at 5:20 pm UTC
Oh noes, don't look at the number of cores, single thread performance, multicore performance, gaming performance, TDP, power usage, platform tech, benchmarks, pricing, availability or anything else where we don't have a clear advantage!
And now this... come on Intel, why you gotta be like this.
Quoting: MayeulCSorry for the rant:
More marketing bullshit. MTr/mm² (million of transistors per square mm) was actually a nice unit. Spitting out stuff vaguely related to a number of nanometers, I can see myself needing to continue to explain for decades to come that no, gate lengths are still about 20 nm and the nanometers you are sold are just a proxy for transistor count (thanks to more and more 3D integration).
Plus, this reads like 20 Amperes, not 20 Ångströms. The symbol is Å. Granted, it's harder to write than to type on most keyboards.
OK, besides my gripe about marketingspeech, I'm glad to see they keep investing at the cutting edge. We need more competition!
I agree that a different unit makes more sense. The nm and Å make sense if youre assumimg a 2D layout. Maybe we'll settle on something more general like # gates / logic volume, hopefully with a simple abbteviation. Also, I just want to point out that 2 nm == 20 Å.
Quoting: pageroundQuoting: MayeulCSorry for the rant:
More marketing bullshit. MTr/mm² (million of transistors per square mm) was actually a nice unit. Spitting out stuff vaguely related to a number of nanometers, I can see myself needing to continue to explain for decades to come that no, gate lengths are still about 20 nm and the nanometers you are sold are just a proxy for transistor count (thanks to more and more 3D integration).
Plus, this reads like 20 Amperes, not 20 Ångströms. The symbol is Å. Granted, it's harder to write than to type on most keyboards.
OK, besides my gripe about marketingspeech, I'm glad to see they keep investing at the cutting edge. We need more competition!
I agree that a different unit makes more sense. The nm and Å make sense if youre assumimg a 2D layout. Maybe we'll settle on something more general like # gates / logic volume, hopefully with a simple abbteviation. Also, I just want to point out that 2 nm == 20 Å.
It used to refer exclusively to gate length. While gate length was shrinking, you could just reduce every feature size, voltages, and call it a day: enjoy your free energy efficiency and frequency boost. This is the era of Dennard's scaling. Every one was happy with this idea, investments were planned to keep up the pace (Gordon Moore was more of an economist, "Moore's Law" is a businessplan).
Unfortunately, you can't just ignore physics. To better control transistor gates at small voltages, you need to make the gate less thick. But this has limits. So we stopped decreasing gate thickness and voltages, and power consumption shot up.
Now we need to make smarter devices: more transistor, more cores, smarter power usage. But we're not really making the gate length a lot smaller, due to a lot more issues.
Gate length remains relevant in 3D, but it won't change a lot anymore.
furaxhornyx Jul 28, 2021
(Sorry with the spelling, but is is indeed a pain to write properly on a keyboard)
... and then watch the others get confused.
See more from me