With the variety in names and so-called types of Pentium processors over the years, it can be a little bit confusing knowing the differences between them all. With that in mind, today’s SuperUser Q&A post has some answers to a curious reader’s question about numbered and non-numbered Pentium processors.
Today’s Question & Answer session comes to us courtesy of SuperUser—a subdivision of Stack Exchange, a community-driven grouping of Q&A web sites.
The Question
SuperUser reader user16973 wants to know what the difference is between numbered and non-numbered Pentium processors:
What is the difference between the two types of Pentium processors?
The Answer
SuperUser contributor Rich Homolka has the answer for us:
Have something to add to the explanation? Sound off in the comments. Want to read more answers from other tech-savvy Stack Exchange users? Check out the full discussion thread here.
In the early days of computing, IBM wanted multiple sources for their chips and Intel allowed AMD to make a limited number of 386 chips. When the 486 came out, clones were big enough that Intel did not need worry about IBM as much, but they also did not want to share the pie with AMD. They started calling their chips i486 and tried to get a trademark for i486. The courts laughed at them (going to trademark a letter?). So Intel tried to come up with a marketing name.
The trade-markable name Pentium was born from that change in marketing tactics (the root, Penta, meaning 5). This was their 586. There were other 586s, including Cyrix’s 5×86, which had (in some ways) a more advanced micro-architecture (the 5×86 broke down x86 instructions to RISC like micro-ops in much the same way chips do now).
That was the 586, so what name could they use for the next generation? Call the new 686 Sextium? Obviously bad. Perhaps Hexium? Not going to go there with Hex in the name.
So they went with the name Pentium Pro. Their first 686 was an extension of the marketing name for the 5th generation 586s. The next one after that? Well, Pentium II, then Pentium III. These are all 686 architectures.
Then, they went to Pentium 4. Why 4? Maybe they did not like choosing between IV or IIII.
This was a new generation, essentially their 786. They went all-in on the MHz race and made a new clock friendly architecture called Netburst. Very very deep pipelines, but it did not perform well. If those pipelines stalled (and not if, but when they stalled), you spent a lot of time trying to empty, then refill them. In CPU power for watts, it did not work as well as the Pentium M, which was a Pentium III based product. Intel kind of backtracked and did not follow the Netburst line much after that, though some other Pentium 4 features were added to the other chips.
Soon after, they started a new line of marketing names, like Centrino, Core, Core Duo, etc.
So, the original Pentium naming scheme stretches across three distinct generations of x86:
586: Pentium, Pentium MMX 686: Pentium Pro, Pentium II, Pentium III, Pentium M 786: Pentium 4
So, if you see something named Pentium, and it is in the single digit megabytes of RAM, and double digit megabytes of hard drive space, it may be an original Pentium.
Anything more recent than this is using Pentium as a pure marketing name. Since Pentium is trademarked, you are essentially calling it an Intel x86 computer. More recent chips are well past Pentium 4 in architecture (Pentium is only a brand now), connoting Intel Inside and giving no more info than that. The current uses of Pentium as a brand name seem to be on the lower end. Anything that is Core series or i3,5,7 series gets listed as that, anything left over may get Pentium.
