Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Why ARM processor is more power efficient compared to Intel processor

Status
Not open for further replies.

biju4u90

Full Member level 3
Joined
Dec 10, 2014
Messages
172
Helped
3
Reputation
6
Reaction score
3
Trophy points
18
Activity points
1,437
ARM processors dominate over Intel processors in mobile phone markets because of it's power efficiency compared to Intel. How does ARM processor achieve lower power consumption compared to Intel for same operation? For example, consider the case of multiplication between two numbers. How does the power consumption vary between ARM and Intel processors for this same operation?
 

The market niche originally intended to reach by ARM developers was not the desktop segment (where Intel holds some leadership) but rather the embedded segment and the low power consumption requirement is a limiting factor for increasing speed and processing power. Perhaps in the future both architectures will undergo changes/adjustments in order to compete with each other, but so far this has been their customer's profile.
 

But how does ARM architecture become more efficient in terms of power reduction?
 

Hi,

I'm not an expert in this....
But if I remember right, then they focussed on decoding the current instruction and disabled all sections that are not used by this instructiin.
Thus they avoided unnecessary signal transitions within the silicon.

I assume there are a lot of informations about this topic in the internet.
Did you do some internet search?

Klaus
 

I assume there are a lot of informations about this topic in the internet.
Did you do some internet search?

What I understood from the internet is that, since ARM architecture is based on RISC model, the complexity of hardware is less compared to that of Intel which follows CISC. The simple hardware reduces power consumption.

But my doubt is that, in RISC architecture, when the hardware complexity is reduced, the complexity of the compiler/device that gives input to hardware can increase too, right? It's like a complex instruction is split into pieces by the compiler and is given to the hardware as single cycle instructions. So when we consider the power consumption of an operation (say, multiplication) why doesn't the power consumption become similar in Intel (which uses larger instruction in hardware) and ARM (which uses multiple smaller instructions in hardware)?
 

Hi,

RISC, CISC:
* In the past RISC prcessors had low transistor count, and thus only maybe 32 instructions. Thus parsing an instruction was not that complex and was fast. But for example a "multiplication" needed a lot of instructions.
* Nowadays even RISC processors may have several hundreds of instructions. Even RISC processors now have a "multiplication" instruction.
Thus the difference is not that big than in the past.

ARM power consumption vs x86 power consumption: I just did an internet search about this topic. There are more than enough hits. --> Read through them.

Klaus
 

Status
Not open for further replies.

Similar threads

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top