What is the exact "N" value of the bit processor ?, explanation for freescale arch

Question

While reading one Freescale processor manual, I was stuck somewhere, which indicates that it is a 32-bit processor.

Can I find out the exact meaning and logic of this?

Update:

Whether it indicates its ALU width or the width of its address or its register width, or all of them together are N-bits each.

Update:

I hope you heard about Freescale processors. I just stumbled upon their website, which describes one of their latest Starcore processors, known as the SC3850, as a 16-bit processor. As far as I know, it has 32-bit program counters, including ALU and 40-bit register width and address bus width of 2x64 bits. The SC3850 can also handle SIMD (2) instructions, which have 32 bits or 64 bits.

For more information go to this link.

Answer 1

One of the main reasons you will need a processor register width is performance. Typically, doubling the number of bits doubles the speed at which the processor can move data and compute. This is why we do not all use 8-bit processors.

Another main reason is address space. A 16-bit counter limits you to 64k of address space, and a 32-bit counter limits you to 4 gigabytes. The new 64-bit processors allow, if all address lines are present, to support 17,179,869,184 gigabytes of memory.

Answer 2

Please see the Wikipedia entry for 32-bit processors , from the entry:

In computer architecture, 32-bit integers, memory addresses, or other data units are those that are no more than 32 bits (4 octets). In addition, the 32-bit CPU and ALU architecture are those based on registers, address buses, or data buses of this size. 32-bit is also a term, the creation of computers in which 32-bit processors were considered Standard.

Read and understand the article - then the answer to N will be obvious.

Answer 3

Firstly, I do not have a definitive answer, but I would suggest that 8, which is a power of 2, is an important factor. The presence of power 2 also means that certain optimizations can be performed by dividing 8 bits into groups, which also means that lookup tables can be used for certain operations. 8 bits in the past were also the ideal size when dealing with regular old ascii characters. I can imagine that using 5-bit bytes and encoding an ascii character string across memory would be a pain.