How To Simulate 32 Bit Register

Chapter 8. Applications

8.2 xvi-BIT VERSUS 32-Chip HARDWARE

A cardinal decision about which stack processor to select for a particular application is the size of the processor's data elements: sixteen bits or 32 $.25. The determination betwixt 16- and 32-bit processors is driven by the factors of cost, size and performance.

8.2.1 16-Bit hardware often all-time

16-bit stack processors in general have lower costs than 32-bit processors. Their internal data paths are narrower, so they utilize fewer transistors and cost less to manufacture. They only need 16-scrap paths to external memory, so they take half as many memory bus information pins equally 32-fleck processors. System costs are also lower, since a minimum configuration 16-fleck processor only needs to have half the number of retention chips as a 32-scrap processor for a single bank of memory.

16-bit chips also take a reasonable corporeality of silicon surface area available for special features, such as hardware multipliers, on-chip program memory, and peripheral interfaces. The trend is for semicustom 16-bit stack processors such as the RTX 2000 to be complete systems-on-a-bit, including I/O peripherals and plan memory for embedded applications.

16-Bit processors should always exist evaluated for an application, then rejected in favor of 32-bit processors just if there is a articulate benefit for the change.

8.2.2 32-Flake hardware is sometimes required

Most traditional real fourth dimension control applications are well served by xvi-bit processors. They offering high processing speed in a minor organization at minimum toll. Of class, part of the reason that traditional applications are well served by 16-bit processors is that capable 32-flake processors take not been widely available for very long. Equally the more capable 32-fleck processors come into greater usage, new application areas volition be discovered to put them to good utilise.

32-Bit stack processors should be used instead of 16-fleck processors only in cases where the application requires high efficiency at one or more of the following: 32-bit integer calculations, access to large amounts of memory, or floating signal arithmetics.

32-Bit integer calculations are obviously well suited to a 32-bit processor. Occasions where 32-bit integers are required include graphics and manipulation of big data structures. While a 16-bit processor tin simulate 32-bit arithmetic using double-precision operands, 32-bit processors are much more efficient.

While sixteen-bit processors can use segment registers to admission more than 64K elements of retentivity, this technique becomes awkward and slow if it must be used ofttimes. A program that must continually change the segment annals to access data structures (especially single information structures that are bigger than 64K in size) can waste a considerable corporeality of fourth dimension computing segment values. Fifty-fifty worse, since the addresses that must be manipulated when computing information tape locations that are greater than 16 $.25 wide, accost computations are likewise slower considering of all the double-precision math involved. A 32-scrap processor tin offering a linear 32-bit address space with accompanying quick accost calculations on a 32-bit data path.

Floating indicate calculations also require a 32-bit processor for good efficiency. 16-Scrap processors spend a significant amount of time manipulating stack elements when dealing with floating signal numbers, whereas 32-bit processors are naturally suited to the size of the information elements. In that location are many instances in which scaled integer arithmetics is more appropriate than floating bespeak numbers to increase speed on some processors. In these cases a 16-flake processor may suffice. However, floating bespeak math must often be used to reduce the cost of programming a project, and to support lawmaking written in high level languages. Besides, with the advent of very fast floating point processing hardware, the traditional speed advantage of integer operations over floating point operations is decreasing.

The disadvantages of 32-bit processors are cost and system complication. 32-Bit processor chips tend to cost more because they have more than transistors and pins than do 16-scrap chips. They too require 32 bit wide plan memory and a generally larger printed circuit board than 16-bit processors. In that location is less room on-chip for extra features such equally hardware multipliers, only these items will appear as chip fabrication technology gets denser.

CONTENTS TOP CHAPTER PREV NEXT NEXT Section