Up in ARMs: TSMC recruited to produce the next generation of 20nm 64-bit mobile chips

Up in ARMs: TSMC recruited to produce the next generation of 20nm 64-bit mobile chips
British mobile chip designer ARM and the world's largest foundry for those TSMC have deepened their partnership to work on ARMs next generation silicon. The task is a die shrink to 20nm, from the current 28nm (Snapdragon S4) or 32nm (Exynos). 

Not only that, but those chips are supposed to be 64-bit, and utilize a TSMC's FinFET technology, which is similar to the current 22nm 3D transistors that Intel is using in its brand spanking new Ivy Bridge architecture.

All those improvements promise a huge performance boost with less space taken, and at lower power consumption envelopes. Furthermore, the FinFET production tech will allow shortened time to markets, not like now, when ARM announced its Cortex-A15 architecture almost two years ago, and we are yet to see a single retail gadget with those chips. As per Cliff Hou, VP of TSMC Research & Development:

Advancing the clock frequencies while keeping the same frugal power consumption ARM chips are known for, are the key factors for the widespread adoption of the RISC architecture even beyond the mobile realm. After 20nm chips, ARM and TSMC are continuing the partnership all the way down to 15nm.

FEATURED VIDEO

11 Comments

1. mercorp

Posts: 1045; Member since: Jan 28, 2012

Samsung must be fuming now.

2. hung2900

Posts: 966; Member since: Mar 02, 2012

That is a hard macro SoC of ARM, and TSMC is the fab that producing it. TSMC has been doing it for quite a long time (Cortex A9 and Cortex A15 hard macro). It does not affect very much on the licencees like Samsung or nVIDIA.

7. shelley.bevacqua

Posts: 80; Member since: Aug 27, 2011

You are funny ! But probably correct.

8. SuperAndroidEvo

Posts: 4888; Member since: Apr 15, 2011

Hey that is how tech moves. Samsung will rebound & make some great processors for next year’s phones & tablets. In this business tech just moves at the speed of light.

9. cepcamba

Posts: 717; Member since: Feb 27, 2012

Samsung produces chips for their own products, and sells some on the side. Nah, they won't be affected much. I'm guessing the 28nm of Samsung will be at par with the 20nm of these guys.

3. darac

Posts: 2156; Member since: Oct 17, 2011

Awesome news for ARM. Stick to PC's, Intel

4. pokharkarsaga

Posts: 547; Member since: Feb 23, 2012

new innovation welcome to the smartphone and tablet world....

5. Birds

Posts: 1172; Member since: Nov 21, 2011

OMG, I just sat here and stared at the screen, and I realized that I think I figured out how SoC's work. Correct me if I'm wrong but like a 65nm chipset compared to a 20 nm chipset clocked at one gigahertz is going to be less efficient because although they are different sizes, the 20nm chipset will have a proportionally higher clock speed. But since it is smaller, it would draw on less speed. Lets say if they were the same size, the 20nm, chipset would actually be clocked at more than 3 gigahertz, if the clock speed was keapt the same in the 20nm chipset as it blows up to the size of the 65 nm one. I feel like I'm wrong some one tell me if I'm right or not. And what architecture ate the Krait CPUs? Would they be the equivalent of A9s, A15s or something kinda inbetween?

6. ardent1

Posts: 2000; Member since: Apr 16, 2011

If you take a step back and think about the amount of energy an electron has to move for bigger chips versus smaller chips, it's easy to that the same electron doesn't travel as far, has less resistance, etc. in the smaller chips. I am generalizing here but you get the picture.

10. cepcamba

Posts: 717; Member since: Feb 27, 2012

Commendable simple explanation :)

11. schecter7

Posts: 99; Member since: Apr 20, 2012

Power consumption is roughly proportional to node cap * voltage ^2 * frequency. I'm talking about only dynamic power that gets used as transistors keep switching. Die shrink scales cap down - so it allows for a scaled up freq. for around same power budget. Of course, there are leakage/static power (say about 30% of the total power) that actually goes up with die shrink. So freq. really doesn't scale up that much. Or power savings is not as much - still significant. Then there is pipleline depth - which tends to increase for higher throughput leading to higher clock freq. So yeah - you probably get the idea. Krait is A15 equivalent implementation of Qualcomm - both are based on the same instruction set (that the SW sees). Unlike most others, Qualcomm designs its own core architecture. Think about AMD & Intel for example - they both implement X86 instruction set but the underlying HW architectures are significantly different. Until we run a krait and A15 (designed by ARM itself) next to each other, it's hard to say which one's better - at least at this point.

Latest Stories

This copy is for your personal, non-commercial use only. You can order presentation-ready copies for distribution to your colleagues, clients or customers at https://www.parsintl.com/phonearena or use the Reprints & Permissions tool that appears at the bottom of each web page. Visit https://www.parsintl.com/ for samples and additional information.