Thursday, June 15th 2017

GLOBALFOUNDRIES on Track to Deliver Leading-Performance 7nm FinFET Technology

GLOBALFOUNDRIES today announced the availability of its 7nm Leading-Performance (7LP) FinFET semiconductor technology, delivering a 40 percent generational performance boost to meet the needs of applications such as premium mobile processors, cloud servers and networking infrastructure. Design kits are available now, and the first customer products based on 7LP are expected to launch in the first half of 2018, with volume production ramping in the second half of 2018.

In September 2016, GF announced plans to develop its own 7nm FinFET technology leveraging the company's unmatched heritage of manufacturing high-performance chips. Thanks to additional improvements at both the transistor and process levels, the 7LP technology is exceeding initial performance targets and expected to deliver greater than 40 percent more processing power and twice the area scaling than the previous 14nm FinFET technology. The technology is now ready for customer designs at the company's leading-edge Fab 8 facility in Saratoga County, N.Y.

"Our 7nm FinFET technology development is on track and we are seeing strong customer traction, with multiple product tapeouts planned in 2018," said Gregg Bartlett, senior vice president of the CMOS Business Unit at GF. "And, while driving to commercialize 7nm, we are actively developing next-generation technologies at 5nm and beyond to ensure our customers have access to a world-class roadmap at the leading edge."

GF also continues to invest in research and development for next-generation technology nodes. In close collaboration with its partners IBM and Samsung, the company announced a 7nm test chip in 2015, followed by the recent announcement of the industry's first demonstration of a functioning 5nm chip using silicon nanosheet transistors. GF is exploring a range of new transistor architectures to enable its customers to deliver the next era of connected intelligence.

GF's 7nm FinFET technology leverages the company's volume manufacturing experience with its 14nm FinFET technology, which began production in early 2016 at Fab 8. Since then, the company has delivered "first-time-right" designs for a broad range of customers.

To accelerate the 7LP production ramp, GF is investing in new process equipment capabilities, including the addition of the first two EUV lithography tools in the second half of this year. The initial production ramp of 7LP will be based on an optical lithography approach, with migration to EUV lithography when the technology is ready for volume manufacturing.

"We are very pleased with the leading-edge technology that GF is bringing with its advanced 7nm process technology. Our collaborative work with GF is focused on creating high-performance products that will drive more immersive and instinctive computing experiences," said Mark Papermaster, CTO and senior vice president of technology and engineering, AMD.
Add your own comment

16 Comments on GLOBALFOUNDRIES on Track to Deliver Leading-Performance 7nm FinFET Technology

#1
bubbly1724
GloFo would need to deliver on schedule since both Ryzen+ and Navi are scheduled for late 2018 with 7nm.
Posted on Reply
#2
raghu78
GF 7LP is shaping up to be a very competitive process node against Intel 10nm and TSMC 7nm. There is a high performance version optimized for 5 Ghz operation.

https://www.globalfoundries.com/sites/default/files/product-briefs/7lp-product-brief.pdf

7nm Zen 2 is likely to be designed using this very high performance process. So its looking quite good for Zen 2 to hit 5 Ghz and overclock beyond that for 24x7 operation. Zen 2 and Navi should launch sometime in Q1 2019. My calculations bring up a Contacted gate pitch of 56nm and Minimum Metal pitch of 40nm. 64% shrink for mobile chips which use a 6 track library. 55% shrink for High performance CPUs which use a 9 track library.

https://forums.anandtech.com/threads/globalfoundries-7lp-7nm-leading-performance-finfet-process-and-fx-7-asic-platform.2508687/#post-38937252

https://forums.anandtech.com/threads/globalfoundries-7lp-7nm-leading-performance-finfet-process-and-fx-7-asic-platform.2508687/
Posted on Reply
#3
Aenra
Dumb question, but assuming this is how it's going to turn out (2nd gen R7s being 7nm) in 2018, are we to expect any incompatibilities? Considering AM4, the 4 year support promise, etc. etc.?
Or will this be a new.. new R7 platform?

(can envision the package, but not necessarily the pins)
Posted on Reply
#4
Melvis
Good news, this is what I like to hear and this is when I will be jumping to a new AMD platform When Zen 2 comes out :) or even Threadripper 2.0
Posted on Reply
#5
prtskg
Aenra said:
Dumb question, but assuming this is how it's going to turn out (2nd gen R7s being 7nm) in 2018, are we to expect any incompatibilities? Considering AM4, the 4 year support promise, etc. etc.?
Or will this be a new.. new R7 platform?

(can envision the package, but not necessarily the pins)
As far as I know, 2018 zen is on 14nm. AM4 will be compatible with new zen platforms, even those on 7nm.
Posted on Reply
#6
jigar2speed
For the first time in history, AMD would be competing with 7nm Chip against 10nm Chip from Intel, however 10nm from Intel should be equal to 7nm from Globalfoundries.

Got to love competition
Posted on Reply
#7
raghu78
jigar2speed said:
For the first time in history, AMD would be competing with 7nm Chip against 10nm Chip from Intel, however 10nm from Intel should be equal to 7nm from Globalfoundries.

Got to love competition
Intel 10nm should be slightly higher density than GF 7LP. GF 7LP Transistor performance and power efficiency will be very with Intel 10nm. The direct comparison of products built on the processes would be Icelake on 10+ vs Zen 2 on 7LP in 2019.
Posted on Reply
#8
Steevo
How long until we are 3-D printing processors...
Posted on Reply
#9
Prince Valiant
Steevo said:
How long until we are 3-D printing processors...
A few decades :P?

I wonder how tiny and efficient old stuff like a Voodoo 5 could be made on a node of this size XD.
Posted on Reply
#10
Grings
Prince Valiant said:
A few decades :p?

I wonder how tiny and efficient old stuff like a Voodoo 5 could be made on a node of this size XD.
well the voodoo 5 used approx 14 million transistors, a current day titan xp has 12 billion...
Posted on Reply
#11
trparky
Hey Intel, better look out... AMD is coming to get you. Imagine, by this time next year AMD Ryzen will be clocked as high as 5 GHz and then we will have the Intel killer that we have all been wanting for so long. Ryzen at 7nm and 5 GHz will scale so well that it will kick Intel's ass all the way to the moon and back. Guaranteed!
Posted on Reply
#12
Aenra
raghu78 said:
Intel 10nm should be slightly higher density than GF 7LP. GF 7LP Transistor performance and power efficiency will be very with Intel 10nm. The direct comparison of products built on the processes would be Icelake on 10+ vs Zen 2 on 7LP in 2019.
If you could expand that into an explanation that morons like me can grasp, i'd be grateful :)
Posted on Reply
#13
jigar2speed
raghu78 said:
Intel 10nm should be slightly higher density than GF 7LP. GF 7LP Transistor performance and power efficiency will be very with Intel 10nm. The direct comparison of products built on the processes would be Icelake on 10+ vs Zen 2 on 7LP in 2019.
I actually read somewhere that AMD is already beating Intel at 14nm in density, can't remember where.
Posted on Reply
#14
raghu78
Aenra said:
If you could expand that into an explanation that morons like me can grasp, i'd be grateful :)
I meant GF 7nm process known as GF 7LP should be very competitive with Intel second gen 10nm process known as 10+ in terms of transistor density, performance and efficiency . This would help AMD design competitive Zen 2 CPU which can hit 5 Ghz clocks. If you want more explanation I could send a PM to you.
Posted on Reply
#16
Aenra
raghu78 said:
If you want more explanation I could send a PM to you.
ooh, if you can spare the time, by all means do! Always happy to learn :)

And thanks for replying ^^
Posted on Reply
Add your own comment