With ARM chips now ubiquitous in high-performance laptops and edge servers, it’s legitimate to ask whether these new devices are worth your next purchase. It’s time to get an understanding of the technical differences between ARM processors and the more muscular x86-64 predecessors that previously ran the chip market unimpeded.
What Does x86-64 Mean Anyway?
Intel processors found in desktop and laptop computers are sometimes referred to as “x86” processors. The 64-bit architecture that all modern computers use today now sits on top of the x86 model, which is now referred to as “x86-64”.
This all sounds a little bit confusing, but it helps explain why there are two different Program Files folders on Windows.
To make things simple, all 32-bit applications go in the x86 folder and the 64-bit ones go in the other folder. This has been a convention since Microsoft released its 64-bit version of Windows XP in 2001.
To simplify things a little bit, we’ll refer to “x86-64” as “x86,” as there are enough similarities between 32-bit and 64-bit chips to group them together.
The label “x86” comes from the granddaddy of modern processing, a microprocessor created by Intel named the 8086. This 16-bit chip operated under an instruction set still used in large part by modern processors today to perform advanced computing tasks.
Everything from your text editor to advanced video rendering software still has the capability to operate under an architecture that was born in 1978!
Since the release of the 8086 microprocessor, Intel continued using the naming convention for future models such as the 80286 and 80386 until it broke with tradition by releasing the Pentium series. Nonetheless, we still pay homage to those old chips by categorizing all subsequent processors that use its instruction set as “x86”.
Even the more modern 64-bit processors that AMD first released in the Opteron series in the 2000s are given the same designation, as the overwhelming majority of 64-bit processors in desktop systems and servers continue to stand on the pillar of the now-humble 8086.
Instruction Sets
All of a processor’s functionality is based around what’s called an instruction set. This is a hard-wired set of rudimentary operations that a chip can perform. Each instruction tells the chip to do things like basic math and move data around. At the bottom of every bit of code in every program that you run on your machine is a layer that talks to the processor. This layer also uses its own code known as assembly language, which translates one step further down into the base instructions that are often referred to as machine code or machine language.
This is where we get to the core difference between ARM and x86 chips.
x86 chips use complex instruction set computing (CISC), whereas ARM chips use reduced instruction set computing (RISC). Whereas CISC chips try to put more “work” into one instruction while sacrificing clock cycles to accomplish this task, RISC chips have (as the name implies) a much smaller instruction set that breaks everything down into simpler steps that can be executed in one single clock cycle.
CISC vs. RISC
If a CISC chip needs to multiply two numbers, it might run a single command: MULT 2, 3. This single command will cover loading numbers from memory, multiply them together, and store the result in the correct memory location. An RISC chip performing the same operation would require many more steps. First, a LOAD instruction to move the numbers from the registrars to the execution unit. Then, a PROD instruction to multiply the numbers. Finally, a STOR instruction to place the result in the correct register.
While the CISC chip might seem more efficient because its commands appear simpler, keep in mind a few important differences:
- First, CISC chips execute commands over multiple clock cycles, while each instruction in a RISC chip is executed over a single clock cycle. Because of this, our hypothetical
MULTcommand might run in the same amount of cycles as the set of RISC instructions that perform the same task. - Second, all of CISC’s instructions and logic need to be stored in transistors. RISC chips can use fewer transistors because they need to store fewer instructions.
- Third, the lower number of transistors required by RISC allows for lower power usage.
There are some advantages to CISC. First, the computer doesn’t need to do much work to convert from a human-level programming language like C to processor-level assembly language. In fact, the MULT command mentioned above is very similar to the C command foo = foo * bar.
RISC chips ask the compiler to do a lot more work to get code down into assembly language. CISC chips can also perform their operations directly on system memory while RISC chips have to pull data from memory onto the processor registers before working with it.
In a head-to-head performance contest between the two, as far as consumers are concerned, there’s no clear winner. However, RISC has one more ace up its sleeve to really get an edge on CISC.
Power Consumption
Between CISC and RISC, there is absolutely no contest when it comes to power usage. RISC categorically takes the crown here. A reduced instruction set provides a reduced wafer footprint, making the chip smaller and therefore less power-hungry.
Smaller chips with fewer microscopic components also have less electrical resistance to deal with and don’t require as much wattage to run. The best case study for this is the proven technology of the smartphone, a “computer-lite” device that wields an immense amount of performance for its relatively small size yet manages to subsist in many cases for over 24 hours on a comparatively small battery.
That being said, this doesn’t mean that all computers will start using ARM chips to reduce power consumption. In the desktop market, where the system typically depends on a direct connection to a wall socket as opposed to a battery, power efficiency isn’t such an enormous priority. CISC chips still perform amazingly in these situations and there’s no sign of this changing anytime soon, really.
Should I Get an ARM or x86 System?
With Microsoft also releases their Windows 11 for the ARM architecture and Apple switching their Mac to use ARM chips, you might be interested to get an ARM PC too. However, it breaks everything down to one very simple question: Are you trying to squeeze every bit of performance per watt-hour of power supplied by your battery? Or are you more inclined to push as much raw performance through your device to the detriment of battery life?
For the majority of use cases someone would be buying a system for, the decision is that simple. In the end, just make sure you don’t forget to bring your charging cable with you!
Image credit: Engineer man in sterile suit is holding Microchip by DepositPhotos
Our latest tutorials delivered straight to your inbox
