Here's why the 20nm chipsets of today are the beasts that they are: nanometers explained

Here's why the 20nm chipsets of today are the beasts that they are: nanometers explained
When it comes to new processor announcements, their manufacturers are always keen to point out that they are made on a smaller "nanometer process" or "process size" than a year ago, hence they are n-times more powerful and energy-efficient. All is well, but if you are the curious type, you might be wondering what a process size is, does it eat carrots, and how does it relate to the speed with which your smartphone runs games or drains its battery. 

Besides, isn't it somewhat counter-intuitive that processors actually become smaller, yet they are more powerful, but less power hungry? After all, we're conditioned to believe that bigger also means stronger, and stronger means more power is required. 

Don't worry, it's not that confusing in practice. We'll try explaining the idea of process size right now.

What's a nanometer?


In essence, a microprocessor is not much more than a bunch of layers made of different materials. Stacking them in particular ways yields us the tiny electronic components used by the processor to crunch numbers – such as transistors, resistors, and capacitors. These don't look like the ones in that broken tube TV uncle Joe threw in the bin eons ago. They are microscopic, and laid out on a grid of squares that act as On and Off switches. The distance between those processor components is measured in nanometers, which represents one billionth of a meter. The less that distance is, the more stuff you can fit on the chip.

Is that all there's to it?


No, because there are more ways in which decreasing the distance between components results in more efficient chips. Shrinking the microprocessor results in lower capacitance between the transistor terminals, which increases their switching frequency. And since the dynamic power a transistor consumes when switching electronic signals is directly proportional to capacitance, the transistors end up faster and less power-hungry!


Sweet, right? It gets better. Those smaller transistors need less voltage to turn on, so they are driven by lower voltages. And dynamic power loss is proportional to the square of the voltage. When you diminish the voltage needed to drive current through the transistors, you magically - no, mathematically - end up cutting power consumption. And the final factor that makes semiconductor makers push smaller process sizes is cost. The smaller a component is, the more of it you can fit in the wafers on which semiconductors are manufactured. Although smaller process sizes need more expensive equipment, the cost of investment is offset by the per-wafer cost.

But why does shrinking the process size take the industry two years on average?


Alas, nature has its ways to balance things in its favor, instead of ours. That's why those small, powerful, and efficient transistors from the paragraph above are more prone to leaking current. If you make semiconductors for a living, that's quite the wall to beat your head against. Voltage leaks happen in squares that are in an Off state, and result in the chip consuming power while it's doing nothing. In an ideal world, all those squares in the layer mask grid would be completely stable, but little electricity buggers like fluctuations, gradients, and diffusion get more troublesome as electronics become smaller.



So how small can these components ultimately get?


From the table below, you can see that the most popular and powerful mobile processors right now seem to be hanging at 20nm or 28nm. But the smallest process in commercial deployment is 14nm, established by Intel and used for its desktop and notebook CPUs. The company is targeting a 5nm process for chips in 2020, and in 2028, the industry expects to reach a 1nm process. This might end up as the limit of the current manufacturing technology we're using, and at that point, the industry will have to consider other developments and materials. Since we already had a transistor as tiny as a single atom in 2012, it's safe to say chip makers will find a way to continue bettering their craft.

ProcessorProcess size (nm)
Qualcomm Snapdragon 81020
Qualcomm Snapdragon 80528
Apple A820
NVIDIA Tegra K128
Samsung Exynos 7 Octa20
MediaTek MT679528

FEATURED VIDEO

42 Comments

1. Settings

Posts: 2943; Member since: Jul 02, 2014

Every processor stated above is fast and efficient in power saving. The difference can be viewed by benchmarks, but in everyday use we cant see the difference unless you have a great deal on small details.

2. ArtSim98

Posts: 3535; Member since: Dec 21, 2012

I WANT 18 CORES RUNNING AT 18.8GHz IN 0.0001 NM PROCESS AND WATERCOOLER ALL ON MY PHONE OH YEAH!!! /s

3. luis.d

Posts: 354; Member since: Dec 04, 2013

YEAH!!!

4. jopancy

Posts: 78; Member since: Apr 25, 2012

Oh yeah!! That would be in the year 2194. Awesome!!

7. roldefol

Posts: 4744; Member since: Jan 28, 2011

Dude! A single atom of silicon is 0.2 nm. YOU CANNOT CHANGE THE LAWS OF PHYSICS. Quantum computing? Now you're playing with power!

8. chengsae

Posts: 64; Member since: Dec 10, 2013

you do mean (fm) femtometer, you can only get less Hz with more cores. sorry to break your balls. lol. i dont mean to be a jerk. hahaha

10. sgodsell

Posts: 7430; Member since: Mar 16, 2013

I would love 18 cores running at 18 ghz, but I love my nuts as well. I don't want them fried. :-)

14. jaytai0106

Posts: 1888; Member since: Mar 30, 2011

Yeah... Unplug charger from your phone, turn the screen on to check the time and reply a text massage, lock the phone, put in your pocket.... then you are on fire all the sudden...

28. joey_sfb

Posts: 6794; Member since: Mar 29, 2012

ArtSim98, they will just plug the chip into your brain and it will be cool by your brain juice. Possible future.

5. darkoman4

Posts: 183; Member since: May 30, 2014

At what size this technology gets into the realm of quantum mechanics where things get weird, unpredictable but probable.

6. ABDULGHAFOOR

Posts: 106; Member since: May 04, 2012

Informative article, Thanks Phonearena

21. garlic456

Posts: 251; Member since: Dec 24, 2012

It is Luis D. , who wrote this article. :)

9. xondk

Posts: 1904; Member since: Mar 25, 2014

And it only gets smaller and smaller, and that still amazes me, though I do wonder if they can go below nano scale in terms of making functioning transistors and such.

11. AnukulVcool unregistered

The Girl is holding Cell processor of ps3. it was a beautiful processor to look at but notorously hard to work on.

12. roldefol

Posts: 4744; Member since: Jan 28, 2011

Kind of like the PS3. Powerful, pretty, but way more complicated than it needed to be.

13. QuadFace

Posts: 179; Member since: Aug 19, 2013

What about the processing cores, Dual Core Tri Core and Quad-core?

15. roldefol

Posts: 4744; Member since: Jan 28, 2011

It is pretty insane that in just a few years mobile processors have caught up with PCs. Dual core, then quad, now 64 bit 8-core with quad core GPUs.

24. strudelz100

Posts: 646; Member since: Aug 20, 2014

Mobile computing is NOT the same as PC. Adding cores and clock speed is the opposite of what is most effective in mobile because BOTH produces extra heat Low clock speed, small NM and advanced custom designs are whats needed in mobile because a PHONE IS NOT PLUGGED INTO THE WALL. Excess heat is your battery life literally vanishing into thin air.

25. roldefol

Posts: 4744; Member since: Jan 28, 2011

Exactly. That makes those advancements in mobile SoC that much more impressive.

31. strudelz100

Posts: 646; Member since: Aug 20, 2014

What's impressive is getting as much performance as an 8 core design out of Apple, and Nvidia's 2 core design. Adding more cores or cranking up the speed is not impressive because the excess heat is wasted battery life.

40. RiceKnight

Posts: 5; Member since: Aug 30, 2012

Why would you come on to a site and start posting stuff that's completely untrue =_=; Get your facts straight mate. More cores reduces heat and allows for a smoother experience on multi threaded applications. More cores allows for lower voltage levels and clocks.

26. brrunopt

Posts: 742; Member since: Aug 15, 2013

They have cought up in number, not performance..

16. ArmAndHammer2015

Posts: 20; Member since: Nov 25, 2014

I love articles like this! Really great information and easy to follow! Keep up the good work Luis D.

17. romeo1

Posts: 816; Member since: Jan 06, 2012

Great article. Now im interested in why hertz don't matter in actual speed. As i used to have a 3ghz pentium 4ht and the amd 64 3000+ at 2ghz kicked its ass anyday.

23. strudelz100

Posts: 646; Member since: Aug 20, 2014

It's because all cores are not created equal. Some cores are designed to be large, and have pipes that can carry a lot of data at once, and draw more power per Mhz. Other cores are smaller and can't carry as much, but have lower power draw. Take a few of those small cores and pump the clock speed though and you get similar performance, but with the pesky issue of excess heat, and diminishing returns per-core. Basically, Mobile computing is completely different than PC because the battery power is finite. Excess heat literally is your battery being wasted. Android devices have made up for wasteful core adding and clock speed racing, using old Snapdragon processors by doubling device battery size in 3 years.

37. romeo1

Posts: 816; Member since: Jan 06, 2012

Thnx that was really helpful

35. NotBiased

Posts: 8; Member since: Nov 20, 2014

Yeah, my iPhone 5S with dual core 1.3GHz scores more than my laptop in geekbench, which has dual core 2.2GHz Intel Pentium T4400.

38. romeo1

Posts: 816; Member since: Jan 06, 2012

I'm not sure but i think geekbench is testing the performance of the device not only the processor itself. If geekbench would test the processor itself the t4400probably would win

41. LifeSucks

Posts: 54; Member since: Jan 15, 2015

As the guy above said, all cores are not created equal. When comparing processors you also have to see a factor called IPC or Instructions per Clock. A CPU core with high IPC need not be clocked higher to perform great. For example here are the IPC of Cortex A7: 1.9 DMIps/MHz Cortex A15: 3.5 to 4.0 DMIps/MHz (Dhrystone Million Instructions per second) Cortex A53: 2.3 DMIps/MHz Cortex A57: 4.1 to 4.8 DMIps/MHz So the reason the newer Cortex's are faster than older ones is because of increase in IPC (and not "64-bit" as some people believe).

18. XaErO

Posts: 353; Member since: Sep 25, 2012

Great article !!

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.