Category: 

What Is the Difference Between Vector and Scalar Processors?

Article Details
  • Written By: Matthew F.
  • Edited By: C. Wilborn
  • Last Modified Date: 05 October 2014
  • Copyright Protected:
    2003-2014
    Conjecture Corporation
  • Print this Article
Free Widgets for your Site/Blog
In the US, men comprise 81% of lighting strike victims.  more...

October 22 ,  1962 :  US President John F. Kennedy ordered an air and naval blockade in Cuba.  more...

The part of a computer that allows it to function, carrying out the instructions of various programs, is the central processing unit (CPU). The CPU, also called a processor, receives a program's instructions; decodes those instructions, breaking them into individual parts; executes those instructions; and reports the results, writing them back into memory. The format for that processor comes in one of two primary types: vector and scalar. The difference between the two is that scalar processors operate on only one data point at a time, while vector processors operate on an array of data.

Scalar processors are the most basic type of processor. These process one item at a time, typically integers or floating point numbers, which are numbers too large or small to be represented by integers. As each instruction is handled sequentially, basic scalar processing can take up some time. Most modern computers use a type of scalar processor.

In contrast, vector processors operate on an array of data points. This means that rather than handling each item individually, multiple items that all have the same instruction can be handled at once. This can save time over scalar processing, but also adds complexity to a system, which can slow other functions. Vector processing works best when there is a large amount of data to be processed, groups of which can be handled by one instruction.

Ad

Vector and scalar processors also differ in their startup times. A vector processor often requires a prolonged startup of the computer because of the multiple tasks being performed. Scalar processors start a computer in a much shorter amount of time, since only single tasks are being executed.

The superscalar processor takes elements of each type and combines them for even faster processing. Using instruction-level parallelism, superscalar processing can perform multiple operations at the same time. This allows for the CPU to perform much faster than a basic scalar processor, without the additional complexity and other limitations of the vector processor. There can be problems with this type of processor, however, as it must determine which tasks can be performed in parallel and which are dependent on other tasks being completed first.

Vector and scalar processors are still used on a daily basis. Some video game consoles, for example, use a combination of both vector and scalar processors. Vector processing is seen to have promise when dealing with multimedia tasks in which one instruction can address the large amount of data required for video and audio.

Ad

More from Wisegeek

You might also Like

Discuss this Article

hamje32
Post 3

@miriam98 - Vector processing would handle some of your problems, but personally I think that it’s overkill. If you only use vector processing for a few functions, and the rest of your software does fine with scalar processing, then you have a lot of unused computer power.

I think that it comes down to a cost-benefit analysis on the part of the computer manufacturers. They can probably pack more power into their machines than they currently have, but who will use it?

If most people won’t need it, then it affects the marketability of the product line. When I think of vector processors and such, I think of physicists working at CERN or some other laboratory needing that power, but not the average computer user.

MrMoody
Post 2

@miriam98 - The thing that people have to realize about a CPU processor is that it simply cannot do all things well, in my opinion.

You mentioned extreme gaming and video cards. There’s a reason that gamers buy dedicated video cards with their own memory. It allows the game to offload its processing tasks onto the video card instead of always making demands on the CPU.

So looking for an all-powerful CPU that does everything is not the answer, the way I see it. The answer is that all of the data and memory intensive applications need to be offloaded on separate devices, while allowing the CPU to simply focus on running the operating system and the software that is running in RAM.

If just you keep looking for a faster computer processor to make your computer blazing fast, you’ll hit the wall eventually.

miriam98
Post 1

I’ve been waiting for a long time for a computer processor that will rise to the demands of video editing and extreme gaming.

Up until now the only way to meet those demands was to buy graphics boards with dedicated processors and tons of dedicated graphics memory, or keep buying a new computer every two years with a faster processor and more RAM. Either way, I find myself always taxing my system at some point.

Just the other day, however, I heard that Intel has unleashed what it considers its fastest processor, and they claim that it boosts video editing and gaming speed by 40%. That’s something I have to see in order to believe.

I don’t know if they use scalar processors; I hope not, because scalar technology, while good for some things, is bad for other processes – at least that’s what I take away from the article.

Post your comments

Post Anonymously

Login

username
password
forgot password?

Register

username
password
confirm
email