AMD Radeon 400 Series Launching Summer of 2022 - Features 2X Performance Per Watt With 14nm FinFET

AMD's next generation "Arctic Islands" family of Radeon 400 series is 1 that many gamers have been eagerly awaiting for so long, as information technology represents the first major generational jump in performance and efficiency since the introduction of the HD 7000 series in January of 2022. This is because it'southward the very first generation of Radeon graphics chips to characteristic next generation FinFETs, rather than the aging 28nm process that spans everything from the 300 serial, Fury series and Nvidia'south 900 serial .

The Arctic Islands family of GPUs has been subject to numerous leaks in the past, unfortunately none of which had any information nigh when they were actually going to exist released. At that place hasn't been whatsoever reliable data about Arctic Islands' release timeframe, that is until today. Nosotros have confirmed that the company is planning to innovate its side by side generation 14nm / 16nm family of graphics cards throughout the summer of 2022 and into the back to schoolhouse season. The launch is even so too far out to make out whatever specific details and we have withal to ostend what the new serial will actually be called, so nosotros're going to use "400 series" every bit placeholder until then.

This goes hand-in-hand with what he had exclusively reported final month about AMD successfully completing the design of several "Arctic Islands" R 400 serial GPUs which take been taped out and are on track to begin mass product. TSMC'due south 16FF+ process is already in volume production at mature yields, with additional chapters and mass product expected past adjacent year as both Nvidia and AMD ramp-upwards their adjacent generation 16nm products. All in all the visitor expects to triple its 16nm capacity by the end of next year.

AMD Radeon 400 Series Chill Islands - 2d Generation Stacked Memory "HBM2" & 2X The Performance Per Watt

AMD'southward President and CEO Lisa Su confirmed this past October the company's plans to update the entire graphics line-upwards over "the coming quarters" with a new set of products that have "2X the performance per watt" of the current Radeon R9 Fury and 300 series of graphics cards. And every bit mentioned earlier nosotros've managed to confirm exactly when AMD is planning to launch its new family of GPUs, across Lisa Su's broad statement at concluding quarter'due south earnings teleconference, and it'll be in the summer of next year.

Lisa Su – Avant-garde Micro Devices, Inc. – President, CEO – Q3 2022 Earnings Teleconference

We are likewise focused on delivering our next-generation GPUs in 2022 designed to meliorate functioning per watt by 2X compared to our current offerings, based on design architectural enhancements, likewise every bit advanced FinFET process technology.

AMD Radeon 400 Series, Arctic Islands

Despite the existence of three+ different iterations of GCN, namely GCN one.0 ( HD 7000 series ) , GCN 1.1 ( R9 290 serial) , GCN one.ii ( R9 285 and 380) and Fiji ( R9 Fury X, R9 Fury and R9 Nano) which is based on an updated GCN one.2 blueprint; according to AMD's Master Applied science Officer Marking Papermaster AMD just recognizes having introduced 2 primary generations of GCN and then far. With the next major iteration to come up out next year in the form of the "Arctic Islands" family of graphics chips.

Arctic Islands will feature three major improvements over AMD'south current current R 300 serial and Fury series line-up. These include second generation HBM, next generation "Arctic Islands" GCN architecture as well every bit a more advanced 14/16nm FinFET manufacturing process. The three of which hateful that for the first time since 2022 we're going to get a truly adjacent generation family of GPUs, with performance and power efficiency levels that vastly exceed what nosotros run into today from the 28nm 300 serial and Fury serial.

At 1 Terabyte/southward of retentiveness bandwidth HBM ii.0 offers double the bandwidth of HBM 1.0 found in the R9 Fury Ten which features a 4096bit memory interface, 4GB of VRAM and a full of 512GB/due south of bandwidth. The flagship GPU in the Arctic Islands family has been numerously purported as "Greenland". Which is fix to be AMD'south most powerful and most avant-garde graphics chip to appointment. Greenland is rumored to feature up to eighteen billion transistors and 32GB of second generation HBM with 1TB/s of memory bandwidth. Making it the largest ever graphics engine conceived by the visitor, at approximately twice the transistor count of AMD'south current flagship code named "Republic of the fiji islands" powering the Fury series of Radeon graphics cards.

HBM2

The Arctic Islands graphics architecture will power everything from next generation mobile and desktop GPUs to APUs and semi-custom chips. There'south likewise strong evidence to suggest that Nindendo'south next generation gaming device "Nintendo NX" – which is coming side by side year – will exist powered by an AMD semi-custom SOC. Making it a very probable candidate to feature AMD's 3rd generation "Chill Islands" GCN architecture.

AMD Radeon 400 Series Arctic Islands To Feature 14nm / 16nm FinFET Process

AMD'southward chief engineering officer, Mark Papermaster, appear last calendar month that AMD will in fact exist leveraging Globalfoundries' 14LPP process for CPU, APU and GPU products. Which was a very interesting development to say the least as It was confirmed back in Baronial that AMD is also in fact ane of TSMC's clients for the 16nm node. The very same process that Nvidia had officially confirmed earlier in the year that information technology volition exist using for its next generation Pascal GPUs in 2022.

Marking Papermaster, senior vice president and chief technology officer at AMD :

FinFET technology is expected to play a critical foundational function across multiple AMD product lines, starting in 2022, GLOBALFOUNDRIES has worked tirelessly to reach this fundamental milestone on its 14LPP process. We look forrad to GLOBALFOUNDRIES' continued progress towards full production readiness and await to leverage the advanced 14LPP process technology beyond a wide ready of our CPU, APU, and GPU products. - Press Release

From a historical point view, every i of AMD's graphics production launches on a side by side generation manufacturing process in the current and past two decades was delivered on a TSMC process node. Now that we have official confirmation that AMD will be edifice FinFET GPUs at both TSMC and Globalfoundries next yr information technology's going to be a fascinating spectacle to see which GPUs would debut on which procedure and why AMD decided to get against its tradition and partner with both foundries for its next generation Arctic Islands GPUs.

14LPE is the early access "low power" version of the common Samsung/Globalfoudnries 14nm FinFET process, while 14LPP is the 2d generation, high performance variant that is set to succeed 14LPE. Despite its name, 14LPP should evangelize ameliorate performance besides as lower ability consumption, the only caveat being its later on availability.
Globalfoundries Samsung 14nm FinFET 14LPE 14LPP
14nm FinFET will offer GPU blueprint engineers about double transistors to play with in the same expanse as the current 28nm process. 14nm FinFET too has significantly faster switching speeds, which will translate to significantly higher clock speeds compared to electric current 28nm based GPUs. This is all in improver to the desperate power savings enabled by the smaller feature sizes and the motion from planar to FinFET gates.

14nm FinFET Engineering

Globalfoundries.com
14LPE – Early time-to-market place version with area and power benefits for mobility applications
14LPP – Enhanced version with higher performance and lower power; a total platform offering with MPW, IP enablement and wide application coverage

TSMC'southward 16nm FinFET process node offers equally impressive figures with double the transistor density of current 28nm engineering as well as faster switching speeds and finally significantly lower power consumption.

TSMC.com
TSMC's 16FF+ (FinFET Plus) technology tin provide above 65 percent college speed, effectually two times the density, or seventy per centum less power than its 28HPM technology. Comparing with 20SoC technology, 16FF+ provides extra 40% college speed and 60% power saving. By leveraging the experience of 20SoC technology, TSMC 16FF+ shares the aforementioned metallic backend process in order to quickly improve yield and demonstrate procedure maturity for time-to-market value.

It will exist interesting to meet how things play out side by side year with Nvidia's Pascal GPUs which will also exist produced on TSMC's 16nm FinFET process and feature second generation High Bandwidth Memory. How much exactly Pascal and Arctic Islands GPUs are going to toll will depend almost entirely on the production yields and volumes of the leading edge FinFET node next year. But and so far this is shaping up to exist one of the biggest operation and power efficiency boosts we're going to see from a new generation of graphics cards in a long while.

Wccftech	Year	Procedure	Flagship GPU	Production	Memory	Bandwidth
Southern Islands	2012	28nm	Tahiti	HD 7970	3GB GDDR5	264GB/s
Volcanic Islands	2013	28nm	Hawaii	R9 290X	4GB GDDR5	320GB/s
Pirate/Caribbean area Islands	2015	28nm	Republic of the fiji islands	R9 Fury X	4GB HBM1	512GB/s
Arctic Islands	2016	14/16nm	Greenland	?	16GB HBM2	1TB/s