Many times Tech companies use Process Node as their marketing strategies, But increased Process Nodes in a processor really affects the performance and battery efficiency of a processor, and should we trust this tech-giants marketing? In this session Let’s find out what is Process Node and the mechanism behind its workings.
“The word processor is a better tool than a quill pen because you can do so much more with it, but on the other hand, what you have to say and how you say it is the ultimate determination.” ~ Walter Murch
Process Node Definition:
Process Node is a process of making a circuit in which we compress the transistor of the chip (processor) to make it even better in terms of performance and battery efficiency by utilizing the same space.
What is Process Nodes:
Process Node is also called a Technology Node, typically speaking process node is a CPU marketing strategy, it is used to signify how better the processor is in terms of better performance and better energy efficiency.
The thing is that with increasing demand for better performance and battery life, many companies are trying to create better and efficient processors, but the issue is that the size of the devices are getting smaller like laptops, smartphones, tablets, etc.
Because the devices in which the processor is situated is getting smaller and slimmer, hence we cannot make bigger processor to cope-up with that situation, it simply means if we want better performance we have to increase the size of the processor but today’s devices are getting slimmer and slimmer, how how to manage this thing?
The only problem to the solution is by decreasing the size of the transistor, yes by decreasing the size of the transistor we can increase the performance and well as battery efficiency of a certain device.
Here’s the term comes Process Node, which generally referred to a number of different features of a transistor that includes gate length and, half-pitch.
Process Node is measured in Nanometers (nm), and it is assumed that the smaller one is better, basically speaking process nodes is a measurement of transistors, more the process nodes (transistors) better the performance will be.
So simply we can say a node is a point in a circuit or network, and it connects through a certain process, hence called a “process node”.
Process Node simply defines, Semiconductor manufacturing process or semiconductor fabrication process, in which certain specific circuit is created in specific steps (steps used to create an integrated circuit).
Finally, we can say that Process Node is a process of making a circuit in which we compress the transistor of the chip (processor) to make it even better in terms of performance and battery efficiency by utilizing the same space.
How Process Nodes Works and Its History:
The tech headlines and you’ll see plenty of stories about how chipmakers are racing to cram more and more tiny transistors onto their processors and why not, the more transistors means better performance and better battery efficiency.
This is because the electrons don’t have to travel as far through each transistor so they can switch on and off and therefore process information more quickly.
But do process nodes really tell the whole story about the performance and battery upskilling? Let’s findout.
For Professional advisory, We reached out to Jason gorse and Bruce Feinberg from Intel and we’d like to thank them for their contributions, the process node was originally a measure of how long the gate in the transistor was this is the part that actually controls the flow of electrons from the source to the drain.
This was considered an accurate enough proxy for transistor size up until about 1997 when the 350-nanometer process was popular the reason this is important is that when you double the number of transistors on a chip it’s fair to expect roughly double the performance at a given die size.
And for a long time these doublings happened, if you will take place at such predictable intervals that Moore’s law came to be stating that the number of transistors on a chip would double about every two years this gave the chip makers an easy cadence to follow for naming each process node.
Because they could expect each one to be smaller by a factor of about 0.7 why point seven you might ask well the transistors are roughly square in shape and if you multiply 0.7 by 0.7 you get 0.49 or roughly 1/2.
So for example when the industry went from 1900 to the 700-nanometer process node this marked a rough doubling of the number of transistors that they could fit in a given area.
Even though the name of the process only reduced by a factor of 0.7 things is in 1997 while manufacturers were able to start shrinking the gate length by more than a factor of 0.7 other parts of the transistor weren’t shrinking as quickly anymore.
So gate length was no longer a good proxy for the overall transistor density in the entire chip and therefore the performance rather than changing the naming scheme outright though.
We started to see a process node defined by the size of a group of transistors called a cell this was done to give people an estimate of the equivalent level of processing power accounting for components that weren’t shrinking as quickly.
So the first node we saw under this new naming system was the 250-nanometer process performance was about double the previous node as you would expect from the name.
But the gate length was actually around 190 nanometers which is much smaller it’s just that there was other stuff that prevented the transistors from being packed more tightly.
Until around 2012 and the 22-nanometer process when a whole new type of transistor was introduced FinFET chip makers found that at these sizes the gates were so small that you could have electrons leaking through them due to quantum tunneling this could cause undesirable behavior.
so engineers needed a way to make their chips more powerful without shrinking the gates even further the solution was to take the channel the electrons go through and raise it up like a shark fin hence the name FinFET.
By increasing the surface area of the channel and allowing lots more electrons to pass through of course this also meant that transistors were now 3-dimensional instead of planar making it much harder to accurately measure their size.
Now the industry has still continued to use that 0.7 factor to describe a generation of improvement like going from 14 to 10 to 7 nanometer processes.
But the truth of the matter is that these numbers don’t actually measure the real size of the transistor anymore and they can even vary wildly between different manufacturers.
Intel for example attempts to measure a process node by taking the weighted average of the two most common standard cell sizes.
A more important consideration though is transistor density that’s how many can be packed into the same space without decreasing the size of the actual transistor.
All in addition to density chip makers are using other techniques like improved materials to boost performance this can include everything from squeezing the crystal structure of the channel to make the electrons go through faster, to low resistance traces between transistors to gate materials with a high dielectric constant for better control of electron flow.
Of course this process can require some trial and error Intel’s well-publicized difficulties with their 10-nanometer process were due in large part to them trying to overscale.
In other words, pack more than double the number of transistors into the same space which required them to try out lots of new technologies inside the chip all at one time which caused delays and manufacturing problems.
But as our technology continues to improve chip makers look poised to keep Moore’s law, even if it’s a little slower alive to some extent as well as keep silicon the base material for our processors for a long time to come before.
We have to really start considering more exotic solutions like carbon nanotubes in the meantime I hope you enjoyed this deeper dive into processor sizes just remember that the process node isn’t the be-all and end-all.
When you’re shopping for a CPU anyway it’s always more important to pay attention to the real-world performance that you’ll see in games and applications that you actually use it’s making of things to actually use.
How Process Node is responsible for Better Performance and Better Energy Efficiency:
Is it not amazing to you that a decade ago when the Pentium 4 processor extreme edition 3.46 gigahertz first launched it debuted around $1000 with the rest of the top tier products falling around 600, 400 and 275 dollars and that now in 2014 pricing is still very similar.
Microprocessor manufacturing facilities also known as FABs continue to increase in the cost of the processors we use in our devices be they laptops tablets phones or even a hundred other things.
you wouldn’t think of perform better consume less power and are available at when we adjust for inflation the same or lower prices year after year I mean they’re still basically layered metal circuits on a peer silicon wafer
That had transistors formed in it so simple right actually no even though many of the raw materials being used are similar the actual device fabrication process has changed dramatically every two years or so.
Truly speaking it’s almost like clockwork intel has debuted a new way to test the laws of physics and begin mass production of processors running smaller and smaller transistors every time they shrink things down another notch we say they’ve moved to a new process node.
When this happens there are a couple of things that usually occur as per the following.
- Transistors switch faster (this translates to potentially higher clock speeds and performance)
- Less current is required for the transistor (which translates into reduced power consumption)
- Decreased Physical area (taken as per transistor goes down significantly allowing either what is fundamentally the same processor to be manufactured with less raw material)
- Lower cost (a better processor to be manufactured with the same raw material at a similar cost)
What is fundamentally the same processor to be manufactured with less raw material and therefore lower cost or a better processor to be manufactured with the same raw material at a similar cost as well.
So that’s all the fuss being made right now about Intel’s Core M processor codename Broadwell why the first CPU to be produced using Intel’s latest 14 nanometer manufacturing process.
Now architectural II it’s not a huge change compared to has well the last generation one which is based on Intel’s 22 nanometers.
Manufacturing process but shrinking the size of the transistors allows the quorum to do some pretty amazing stuff including deliver dual-core turbo boost capable.
CPUs with beefy onboard graphics that have a TDP of four to four and a half Watts low enough for use in two and ones and other ultra-thin mobile devices in the future with felt requiring a cooling fan not to mention better performance better battery life etc.
And there’s more as Intel’s capacity at 40 nanometer ramps up we will see this technology deployed in the desktop and server until it’s everywhere and then it’s time to start the whole process all over again and that is how we keep getting better processors at the same or even lower prices.
“I’ve tried word processors, but I think I’m too old a dog to use one.” ~ Dee Brown
Does increased Process Nodes affects performance and battery efficiency?
Technically speaking, YES!
An increased amount of Process Nodes does increase the performance and battery efficiency because the number of transistors is increased but the size of the processor (chip) remains the same. Higher the number of transistors better the performance and battery quality.