As a general engineering hobbyist, I am learning more about the world of microcontrollers each and every day. Once thing I don't quite understand though is the significance of the bit version of a microcontroller.
I have been using the ATmega8 for several months, and it seems to work great for my purposes. I know how things like clock speed, memory, number of IO pins, types of communications buses, etc. differentiate one micrcontroller from another. But I don't quite understand the significance of, say, 8-bit vs. 16-bit vs. 32-bit. I do understand that a higher bit version allows the device to store larger numbers, but again, how does this impact my decision? If I am designing a product, under which hypothetical scenario would I decide that an 8-bit processor simply won't do, and that I need something higher.
Is there any reason to believe that a theoretical 32-bit variant of the ATmega8 (all other things equal) would be superior to an 8-bit version (if such a device was possible)?
I may be speaking nonsense, but I guess that's a result of my confusion.
Best Answer
It's not the width of number it can store, it's the width it can work with in a single operation. Customarily (but not necessarily) this also has a degree of correlation to the width of native memory addressing, and thus the amount of storage which can be easily mapped without ugly workarounds such as segmentation or bank switching.
Today's 32-bit cores are superior to 8-designs in most respects (flexibility, flat memory model, and of course performance), with the major exceptions being legacy systems, applications with extreme volume and price pressure (otherwise pricing tends to correlate better with on chip memory size than with core width), and side effects of process/density. The later can provide things like 5v operation, or possibly in some cases greater radiation hardness or a simplicity advantage if trying to prove the CPU design itself to be free of logic errors. One final process/age side effect of value to many hobbyists is that 8-bit cores in DIP packages are common, while 32-bit devices in such packages are rarer (though they do exist).