Electrical computers and digital processing systems: processing – Instruction alignment
Reexamination Certificate
1995-06-07
2002-01-22
Nguyen, Hiep T. (Department: 2187)
Electrical computers and digital processing systems: processing
Instruction alignment
C711S100000, C703S027000
Reexamination Certificate
active
06341345
ABSTRACT:
FIELD OF THE INVENTION
The present invention pertains generally to the field of data processing, and more particularly to the field of endian oriented computer systems.
BACKGROUND OF THE INVENTION
The earliest digital computers built in the late 1940's had simple designs and components. Despite numerous advances in technology over the years, most modern day computers still use the same basic components to perform the same fundamental tasks of storing and manipulating information.
Two of these basic components are computer memory and a processor. Computer memory stores information being used by the computer, and works in much the same way as the memory of a person. For example, just as people can remember ideas about different topics and events, the memory of a computer system can be used to store words, numbers, pictures, and other forms of information.
A computer processor is the active component of the computer system. The processor operates on the information stored in the computer system's memory to carry out the task assigned to the computer system. The tasks being processed by the computer system are also sometimes called jobs, programs, or processes.
A computer processor running a job reads and processes information stored in computer memory in much the same way a person reads and processes the words printed on the page of a book. Therefore, just as the arrangement of words on a page is important to human readers, the arrangement of information in the computer system's memory is important to the computer system. For example, words in English are written from left to right and words in Hebrew are written from right to left. People who read only English are able to understand English words that are written from left to right and people who read only Hebrew are able to understand Hebrew words that are written from right to left. The fact that English words are written on a page from left to right does not mean that it is better to arrange words in this manner instead of arranging them from right to left. English words are written from left to right simply because English readers expect words to be written from left to right. In this sense, the arrangement of information in the memory of a computer system is not different than the arrangement of words on a page. One way of arranging the information is not better than any other way of arranging the information. However, computer systems are also just like people in the sense that if the information is not arranged in a way that the computer system expects, the information cannot be understood by the computer system.
Of course, the fact that one way of arranging computer system information is not better than any other way of arranging the information has “opened the door” for different approaches to organizing information in computer system memory. It is no surprise, then, that computer system designers would at some point develop different schemes for organizing at least some forms of computer system information. One such divergence occurred some time ago for two particular forms of computer system information (called floating point information and binary integer information). At present, there are two common schemes for arranging these types of computer system information. The two schemes were dubbed “little endian” and “big endian” after the warring tribes from the famous book
Gulliver's Travels
written by Jonathan Swift. While the terms are colorful, they have no significance to computer systems beyond denoting how these types of information are arranged on a particular computer system.
In the late 1970's and early 1980's, INTEL CORPORATION introduced processors which became the standard for IBM PC and compatible personal computers. These computer systems used the so-called little endian arrangement. During this same time, other computer systems were designed using the so-called big endian arrangement. These later computer systems included processors manufactured by MOTOROLA Corporation and used in computer systems manufactured by APPLE Corporation.
In the past, the way computer systems organized information (in big or little endian format) within their memory was not a significant problem because it was not considered advantageous to arrange information in more than one way on a single computer system.
Today, however, the tremendous growth of computers used in businesses and homes has given rise to a serious need for compatibility between the different types of computer systems. For example, persons who use IBM PC or compatible computers cannot generally share computer programs and information with persons who use APPLE Macintosh computers, and vice versa. Large corporations that use both types of computers find it difficult to distribute information among employees. Small businesses often find that they cannot easily share information with suppliers or buyers who do not have the same type of computers. Consequently, computer software developers are often forced to devote additional time and resources to develop multiple versions of the same software so as to support different types of computer systems. In short, the inability to arrange certain types of information in more than one way on a single computer system has in large part resulted in delayed products, lost productivity, reduced efficiency, and increased capital expenditures.
Some existing computer systems do attempt to deal with the endian problem, but only in a limited fashion. These computer systems have what can be referred to as bi-endian capability. Essentially, bi-endian capability means that the same computer system can be made to execute either big endian tasks or little endian tasks, but not both types of tasks together. In other words, when the computer system is first started, the computer system is told whether it will be running big endian or little endian tasks (i.e., the computer system can be made to run in either big endian mode or little endian mode). Switching an existing bi-endian computer system's endian mode (i.e., big endian mode to little endian mode or vise versa) requires special purpose software that executes very early in the computer's initialization cycle (i.e., very close to start-up). Thereafter, all tasks will execute in the specified endian. For practical purposes, then, bi-endian computer systems are really equivalent to regular, “mono-endian,” computer systems once they have completed their boot process.
While these bi-endian computer systems do provide additional flexibility by providing the ability to run either big endian or little endian tasks, they do not solve the problem associated with the need to allow tasks having different information format expectations (i.e., big versus little endian) to co-exist and execute, task for task, on a single computer system.
Without a computer system that can simultaneously run programs from both endian environments and share information between those programs, the incompatibility problems of today will continue to plague the computer industry.
SUMMARY OF THE INVENTION
It is a principal object of this invention to provide an enhanced computer system that allows tasks having different information format expectations (i.e., big versus little endian) to co-exist and execute, task for task, on a single computer system without the need for specialized hardware while nonetheless allowing tasks of one endian to access data formatted in the alternate endian.
It is another object of this invention to provide an enhanced computer system that allows tasks having different information format expectations (i.e., big versus little endian) to co-exist and execute, task for task, on a single computer system without the need for specialized hardware while nonetheless allowing such tasks to access data formatted in the alternate endian in a way that does not require the accessing tasks to understand and manage the internal data representations of the computer system processor.
A novel apparatus and method that allows tasks having different information format ex
Auslander Marc Alan
Loen Larry Wayne
Nguyen Hiep T.
Roth Steven W.
LandOfFree
Mixed-endian computer system that provides cross-endian data... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Mixed-endian computer system that provides cross-endian data..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mixed-endian computer system that provides cross-endian data... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2863959