I see so much of this stuff going on in ads for computers but I just don’t understand why one is better than another and why.
In: 4
The 4nm etc is (in a simplified way) a measurement of how big the transistors or “wires” are in the processor. So back at 80nm (nanometers) we’re looking at 20 times the size wires compared to the new 4nm.
So why is that good? After all, with electric service you need bigger wires to carry more power! But in a computer the benefit is two pronged. It actually takes less power, basically because there’s 20x less material to energize.
The biggest upside, though, is that they can fit more transistors. If you’ve got 1/20th the size transistors, you can fit nearly 20x as many transistors. More processing power.
It’s the same for CPUs and GPUs. A GPU is basically a CPU with a ton of tiny cores. You know you see things like 16 core processors right? Well GPUs can have thousands, they’re just a lot more limited at what they can do. A CPU can do anything, graphics cards are much more limited.
4nm or 6nm process refers to the method that is used to make the silicon chip. It is (ELI5) a measure of the size of the smallest devices made on the chip. A smaller number is more advanced because, as the number gets smaller, more devices can be made on a similar sized chip and this makes it faster and generally more efficient.
A CPU is the brains of a computer. It is a chip that does all the general purpose computing in a computer, laptop or tablet etc.
A GPU is a specialized chip designed for graphics processing. The chip is optimized for certain calculations that are used to make graphic images. A GPU will work in conjunction with a CPU.
GPU is Graphics Processing Unit. Also known as a “video card”. CPU is Central Processing Unit and is the main “brain” of the entire computer. You’d never compare those two components against each other. They work with each other and compliment each other.
NM is nanometer. A 4NM process makes the chipset thinner than a 6NM process. On paper, a thinner/smaller chip will require less power and be able to be packed in to a smaller device. Thinner does not necessarily mean better. But getting things smaller is almost always good in the computing world.
4nm process means smaller transistors than 6nm process. Smaller transistors means you can fit more transistors in the same space, which can mean faster processors or better performance. The actual number (4nm) is mostly just a marketing term than an actual measurement, but smaller is better.
The CPU is the brain of your computer, it’s responsible for everything your computer does.
The GPU is a helper processor. It stands for “Graphics Processing Unit”, and historically it was responsible for rendering video on your computer. However, these days it can actually be used for dozens of things other than video, too. In a nutshell, a GPU has hundreds of little mini CPUs that are more limited and not quite as general-purpose, but you can leverage all of them working in parallel.
A better GPU definitely helps with graphics – like playing games at high-resolution with a high frame rate. It can also help with crypto mining, photoshop filters, video encoding, and many other specialized tasks.
A better CPU helps with your overall computer speed – how fast a program opens, how fast a webpage loads, etc.
Okay, so for the first question.
Imagine you had a warehouse, and in that you were putting machines that do one specific thing, let’s say, make a pencil. If your warehouse is 1000 square feet, and your pencil machine takes up 10 square feet, it would follow that you can naturally fit 100 pencil machines. Now say you reduce the size of the pencil machine to 5 square feet, half the original size. It would naturally follow that you can fit twice as many machines in the same space.
For computer parts essentially scale that down to extremely small areas. Part manufacturers are trying to put as many “Machines” (transistors) in a small area, and reducing the scale of each individual “machine” means you can fit more
For the second question.
A CPU and a GPU are essentially machines that are specialized to do one specific thing.
Back to the pencil machine analogy, if you have a pencil machine, you may be able to make a pen using it, but it’s not what it’s designed to do, so it will be less efficient. Maybe it takes three times as long to make a pen with a pencil machine. So what do you do? You get a warehouse with pen machines in addition to your pencil machines. Now you can make pens much faster, and your pencil machines are able to do work that they’re more specialized for.
In terms of CPU VS GPU. Essentially CPUs are meant to calculate one “large” operation, say 123456789 x 987654321, whereas a GPU is meant to calculate a lot of smaller operations, for example it might calculate 2×2 5000 different times.
This is a massive simplification of hardware architecture overall, but in principle that’s how they’re meant to work.
4nm/6nm for a typical consumer is just there for marketing fluff. There are advantages for a smaller number, but you as a consumer don’t get to choose the same CPU or GPU made by different processes. As a consumer, you would be better informed by understanding the performance of the CPU/GPU itself rather than the process it was made with.
CPU is the central processing unit and GPU is the graphics processing unit. Every computer has a CPU and GPU, although sometimes the CPU and GPU are combined. If you’re mostly playing games or video editing, you’re more interested in a better GPU. If you’re doing heavy excel work, the CPU is more important. You can find reviews and benchmarks on the CPU and GPU, which are generally a decent indicator of performance of a device you’re buying.
Nowadays it’s just marketing. Smaller number = better, but you can’t compare the nm number from one company to that of another, because the actual number is meaningless now outside of marketing.
It used to refer to the smallest part of a transistor or the wires or circuits, but this is no longer the case and hasn’t been for a long time.
You can check out [this YouTube video](https://youtu.be/1kQUXpZpLXI) where they compared TSMC 7nm to Intel 14nm under an electron microscope and … the different parts are more or less the same size.
Reading the answers, I also ask: why are GPU cards also getting so much bigger and less efficient?
What you are reading is a measurement of distance – 4nm refers to four nano meters, or 0.000000004 meters.
In terms of computers, this refers to the size of the transistors on the chip – this is a critical component of a computer, with billions being required to make up a modern processor. The smaller the transistor, the more you can fit on to the same size of chip, and the closer together they can be placed.
All other things being simplified and equal, the more transistors you have, the better the performance can be.
Latest Answers