TSMC and ARM Tape-Out First ARM Cortex-A57 Processor on 16 nm FinFET Technology

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
TSMC and ARM today announced the first tape-out of an ARM Cortex-A57 processor on FinFET process technology. The Cortex-A57 processor is ARM's highest performing processor, designed to further extend the capabilities of future mobile and enterprise computing, including compute intensive applications such as high-end computer, tablet and server products. This is the first milestone in the collaboration between ARM and TSMC to jointly optimize the 64-bit ARMv8 processor series on TSMC FinFET process technologies. The two companies cooperated in the implementation from RTL to tape-out in six months using ARM Artisan physical IP, TSMC memory macros, and EDA technologies enabled by TSMC's Open Innovation Platform (OIP) design ecosystem.

ARM and TSMC's collaboration produces optimized, power-efficient Cortex-A57 processors and libraries to support early customer implementations on 16 nm FinFET for high-performance, ARM technology-based SoCs.
"This first ARM Cortex-A57 processor implementation paves the way for our mutual customers to leverage the performance and power efficiency of 16nm FinFET technology," said Tom Cronk , executive vice president and general manager, Processor Division, ARM. "The joint effort of ARM, TSMC, and TSMC's OIP design ecosystem partners demonstrates the strong commitment to provide industry-leading technology for customer designs to benefit from our latest 64-bit ARMv8 architecture, big.LITTLE processing and ARM POP IP across a wide variety of market segments."

"Our multi-year, multi-node collaboration with ARM continues to deliver advanced technologies to enable market-leading SoCs across mobile, server, and enterprise infrastructure applications," said Dr. Cliff Hou , TSMC Vice President of R&D. "This achievement demonstrates that the next-generation ARMv8 processor is FinFET-ready for TSMC's advanced technology."

This announcement highlights the enhanced and intensified collaboration between ARM and TSMC. The test chip was implemented using a commercially available 16nm FinFET tool chain and design services provided by the OIP ecosystem and ARM Connected Community partners. This successful collaborative milestone is confirmation of the roles that TSMC's OIP and ARM's Connected Community play in promoting innovation for the semiconductor design industry.

Source
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
It'll take probably another 2~3yrs for these to hit the market but going ahead I see Intel being squeezed at the top end(server market) by ARM whilst the bottom end will be AMD's domain provided they stay afloat ! I see a huge squeeze on Intel's margins & even greater pressure on their ability to dictate terms(pricing mainly) to OEM's going forward, so what's your on this ?
 
Last edited:

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
It'll take probably another 2~3yrs for these to hit the market but going ahead I see Intel being squeezed at the top end(server market) by ARM whilst the bottom end will be AMD's domain provided they stay afloat ! I see a huge squeeze on Intel's margins & even greater pressure on their ability to dictate terms(pricing mainly) to OEM's going forward, so what's your on this ?

ARM? Topend? ARM performance is...very slow.

Also AMD is a goner in the serverspace. They got 4% or so left and its going down. Big tin servers are also slowly getting eaten by x86.

We had ARM servers for ages, they got nowhere.

2-3 years. Then we got Broadwell and Skylake CPUs. Not to mention Silvermont, Airmont and maybe a 3rd one.
 

Phynaz

Lifer
Mar 13, 2006
10,140
819
126
I'm anxiously awaiting more news on TSMC's 16nm process. Although as you said, it's a minimum of 2 years before this will see production.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
I would estimate 3 or 4 years away for 16nm. 20nm is not even close yet. But again, we all know they produced 28nm in 2010 too. *cough*
 
Last edited:
Mar 10, 2006
11,715
2,012
126
It'll take probably another 2~3yrs for these to hit the market but going ahead I see Intel being squeezed at the top end(server market) by ARM whilst the bottom end will be AMD's domain provided they stay afloat ! I see a huge squeeze on Intel's margins & even greater pressure on their ability to dictate terms(pricing mainly) to OEM's going forward, so what's your on this ?

Uh, no. Bottom end is what ARM is trying to take. Don't think for a minute that a 64 bit Cortex A15 could stand up to...what is it now, a Broadwell if not Skylake Xeon by the time it's out. Hell, don't expect it to compete with a Westmere.
 

Genx87

Lifer
Apr 8, 2002
41,091
513
126
It'll take probably another 2~3yrs for these to hit the market but going ahead I see Intel being squeezed at the top end(server market) by ARM whilst the bottom end will be AMD's domain provided they stay afloat ! I see a huge squeeze on Intel's margins & even greater pressure on their ability to dictate terms(pricing mainly) to OEM's going forward, so what's your on this ?

They will try to break into the low end server market. Something where processing power isnt needed but low power is desired. For instance a file or front end web server.
 
Mar 10, 2006
11,715
2,012
126
They will try to break into the low end server market. Something where processing power isnt needed but low power is desired. For instance a file or front end web server.

While ARM just taped out the A57 core, Intel has been sampling its "Avoton" micro-server SoC since at least October, if not earlier.
 

lagokc

Senior member
Mar 27, 2013
808
1
41
In other possibly panglossian manufacturing news -

http://fudzilla.com/home/item/30939-tsmc-20nm-fab-14-coming-on-line-soon

"TSMC apparently thinks we’ve been stuck at 28nm for way too long and it seems on track to open its first 20nm foundry later this month."

http://fudzilla.com/home/item/30941-globalfoundries-might-be-a-threat

"Globalfoundries has laid out a roadmap for 2014 that includes 3D FinFET transistors at the 14nm process which makes it a contender in 2014."


Is anyone else a bit skeptical of Global Foundries ability to be ready for 14nm in 2014? Not that I wouldn't love that, but it seems optimistic.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
In other possibly panglossian manufacturing news -

http://fudzilla.com/home/item/30939-tsmc-20nm-fab-14-coming-on-line-soon

"TSMC apparently thinks we’ve been stuck at 28nm for way too long and it seems on track to open its first 20nm foundry later this month."

http://fudzilla.com/home/item/30941-globalfoundries-might-be-a-threat

"Globalfoundries has laid out a roadmap for 2014 that includes 3D FinFET transistors at the 14nm process which makes it a contender in 2014."


Is anyone else a bit skeptical of Global Foundries ability to be ready for 14nm in 2014? Not that I wouldn't love that, but it seems optimistic.

There is endless roadmaps you can find to show neither TSMC or GloFo actually delivers what they promise on the fancy slides. 28nm for example for TSMC was a good 2 years late. GloFo doesnt even ship 28nm yet, even tho their roadmaps showed 2010.
 
Mar 10, 2006
11,715
2,012
126
In other possibly panglossian manufacturing news -

http://fudzilla.com/home/item/30939-tsmc-20nm-fab-14-coming-on-line-soon

"TSMC apparently thinks we’ve been stuck at 28nm for way too long and it seems on track to open its first 20nm foundry later this month."

http://fudzilla.com/home/item/30941-globalfoundries-might-be-a-threat

"Globalfoundries has laid out a roadmap for 2014 that includes 3D FinFET transistors at the 14nm process which makes it a contender in 2014."


Is anyone else a bit skeptical of Global Foundries ability to be ready for 14nm in 2014? Not that I wouldn't love that, but it seems optimistic.

Global Foundries has barely shipped 28nm, if at all given the comments on TSMC's call that it had ~100% 28nm market share. So, how can GloFo go from not shipping any 28nm, to skipping right over 20nm to get to its FinFET?

It's a load of BS, and the people who keep buying GloFo's lies year after year keep getting burned. Is it any wonder that the guys who own GloFo can't wait for the IPO so that they can cash out of this disaster?
 

Phynaz

Lifer
Mar 13, 2006
10,140
819
126
In other possibly panglossian manufacturing news -

http://fudzilla.com/home/item/30939-tsmc-20nm-fab-14-coming-on-line-soon

"TSMC apparently thinks we’ve been stuck at 28nm for way too long and it seems on track to open its first 20nm foundry later this month."

http://fudzilla.com/home/item/30941-globalfoundries-might-be-a-threat

"Globalfoundries has laid out a roadmap for 2014 that includes 3D FinFET transistors at the 14nm process which makes it a contender in 2014."


Is anyone else a bit skeptical of Global Foundries ability to be ready for 14nm in 2014? Not that I wouldn't love that, but it seems optimistic.

Best to ignore Fudzilla.
 

SocketF

Senior member
Jun 2, 2006
236
0
71
Is anyone else a bit skeptical of Global Foundries ability to be ready for 14nm in 2014? Not that I wouldn't love that, but it seems optimistic.
Yes everybody. 20nm is said to be due in 2013 ... lets wait and see ;-)

There is endless roadmaps you can find to show neither TSMC or GloFo actually delivers what they promise on the fancy slides. 28nm for example for TSMC was a good 2 years late. GloFo doesnt even ship 28nm yet, even tho their roadmaps showed 2010.
No they are shipping now, there is a chinese tablet with an ARM dualcore fabbed at GF@28nm. I think I (or somebody else) posted it already somewhere else here in this forum. So we can say now, that they were ~3 years late with 28nm.
 

Idontcare

Elite Member
Oct 10, 1999
21,110
59
91
No they are shipping now, there is a chinese tablet with an ARM dualcore fabbed at GF@28nm.

So a no-name chinese design house managed to upstage AMD in getting 28nm functional silicon out of GloFo? o_O Really?
 

SocketF

Senior member
Jun 2, 2006
236
0
71
So a no-name chinese design house managed to upstage AMD in getting 28nm functional silicon out of GloFo? o_O Really?
Yes, AMD canceled their 28nm bulk chips last year, the yields were too bad, I once posted the yields in the FDSOI thread and you helped me with decoding it.

Seems I havent posted it here before, well then here's the link to the ARM SoC from GF:

SoC launched in January at CES:
http://armdevices.net/2013/01/09/rockchip-rk3188-28nm-hkmg-quad-core-arm-cortex-a9-launched/

Tablet launched / availability in March:
http://armdevices.net/2013/03/10/pipo-max-m9-rk3188-28nm-hkmg-quad-core-arm-cortex-a9-tablet/

Seems pretty nice ~$200 (Chinese prices, add taxes and shipping costs) for a 28nm quadcore tablet are ok ;-)

Edit: Too late.
 

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
So a no-name chinese design house managed to upstage AMD in getting 28nm functional silicon out of GloFo? o_O Really?

What was the size and complexity of the chip being produced by the Chinese company?? What quantities is it shipping in??
 
Last edited:

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
ARM? Topend? ARM performance is...very slow.

Also AMD is a goner in the serverspace. They got 4% or so left and its going down. Big tin servers are also slowly getting eaten by x86.

We had ARM servers for ages, they got nowhere.

2-3 years. Then we got Broadwell and Skylake CPUs. Not to mention Silvermont, Airmont and maybe a 3rd one.
By top end I meant the server/HPC market that makes up majority of Intel's revenues & profits, IIRC one of the recent AT articles showed that calxeda(ARM) delivers greatly on the power/efficiency front & seeing as how sensitive the enterprise is in that regard I don't why the likes of AMD, Samsung, Qualcomm even Nvidia can't make a dent to Intel's dominance provided they're in it for the long haul !
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
Uh, no. Bottom end is what ARM is trying to take. Don't think for a minute that a 64 bit Cortex A15 could stand up to...what is it now, a Broadwell if not Skylake Xeon by the time it's out. Hell, don't expect it to compete with a Westmere.
Again, if this is any indication as to where ARM is headed, I see no reason why Intel shouldn't be worried just like their unsuccessful scramble in the mobile space thus far has shown us, the only difference being that they're the incumbents in this case !
 

Ajay

Lifer
Jan 8, 2001
16,094
8,112
136
So a no-name chinese design house managed to upstage AMD in getting 28nm functional silicon out of GloFo? o_O Really?

Probably Risk production, too much downside and probably too few wafer starts for AMD right now.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
By top end I meant the server/HPC market that makes up majority of Intel's revenues & profits, IIRC one of the recent AT articles showed that calxeda(ARM) delivers greatly on the power/efficiency front & seeing as how sensitive the enterprise is in that regard I don't why the likes of AMD, Samsung, Qualcomm even Nvidia can't make a dent to Intel's dominance provided they're in it for the long haul !

ARM servers is nothing new, they have been there for a long time. And gotten nowhere.
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
ARM servers is nothing new, they have been there for a long time. And gotten nowhere.
That's what they said about their mobile offerings as well & yet here we are at a stage where the cortex A15 & something like a Snapdragon 800 is the best in ultra/low power segment even though Intel is half a node ahead of'em, granted they don't have atom at 22nm but still !

Just to add ~ 64bit extensions will give them something what they didn't have earlier i.e. the ability to add massive amounts of memory & who knows 64bit ARM might deliver greater benefits as compared to the jump from x86 to x86-64 !
 
Last edited:

Torn Mind

Lifer
Nov 25, 2012
12,050
2,764
136
Anytime you have a ratio, you can increase it by increasing the numerator value(i.e performance) or decreasing the denominator value, i.e watts. I would suspect that Intel has a hold on server because they can handle heavier workloads.
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
163
106
Anytime you have a ratio, you can increase it by increasing the numerator value(i.e performance) or decreasing the denominator value, i.e watts. I would suspect that Intel has a hold on server because they can handle heavier workloads.
But the thing is performance doesn't scale up with increasing power so the upside is limited, that's why we see the tapering off in their performance graph from SNB to IVB & now Haswell, however with energy efficiency in mind you can incrementally up the performance till it reaches a certain level. Now with severs you can add lots of cores to increase the performance & SoC's deliver even greater efficiency so there certainly is alot more headroom than what most would like to believe !