Computer graphics processing and selective visual display system – Computer graphics processing – Attributes
Reexamination Certificate
2001-03-01
2003-05-06
Luu, Matthew (Department: 2672)
Computer graphics processing and selective visual display system
Computer graphics processing
Attributes
C345S502000, C345S506000
Reexamination Certificate
active
06559854
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to an image creation device such as an entertainment device and, more particularly, to an efficient geometry processing technique when a computer graphics image is created.
1. Description of the Related Art
In computer graphics, an object to be displayed is modeled by a set of polygons. The vertexes of the polygons are expressed by homogeneous coordinates (x, y, z, w). The coordinates are converted according to the aspect coordinates, and the transparent transformation thereto or the like are performed according to a distance. For example, a distant object is converted to become small. The series of processings is called as a “geometry processing”. The vertex coordinates obtained as a result of the geometry processing is called as a display list (Display List: image display instruction).
The display list is sent to the drawing processing means. The drawing processing means draws a basic figure according to the display list in a frame memory. The drawing result is converted from a digital signal to an analog signal, and is displayed on a display unit.
Since the drawing result is updated according to a video rate every {fraction (1/60)}seconds, a moving image is displayed on a screen of the display unit. A series of drawing processings by the drawing processing means is called “rendering processing”.
Recently, the advancement of the semiconductor technology is remarkable. Since it has become possible to integrate a frame memory and the drawing processing means on an LSI and, therefor, improve the rendering processing, performance of the geometry processing has become relatively insufficient. As means for solving such a disadvantage, it is effective to connect a plurality of geometry engines (means for executing the geometry processing, and so forth) with the drawing processing means in parallel. In the drawing processing, there are a lot of parameters which should be preset, for instance, a clip area and a half transparent processing rate, etc. Thus, it becomes necessary to switch the parameters (“drawing context (Graphic Context)”, or simply “context”) used in an individual geometry engine.
On the other hand, two processings with different characters may exist together when a detailed breakdown of the geometry processing is observed. One of them is a pure coordinate conversion processing, and another is a behavior calculation processing. The former is a fixed geometry processing, and the latter is an unfixed geometry processing. For example, when a game program is analyzed, calculating a behavior of a character (“character” is not limited to man and may be applied to other objects, such as a motion of an enemy plane in a shooting game or a car in a racing game) in response to an external input, and actually calculating coordinate conversion and performing illumination processing have quite different time schedules, respectively. Although it is suffient when the former calculation is concluded on a video frame unit ({fraction (1/60)}seconds) basis, the latter calculation requires synchronization with a rendering pipeline on a polygon drawing unit basis, which is more detailed than the former calculation. Even if both of the calculations are similar, frequent context switching is required to deal with the different time axis in a single processing mode and, therefor, a serious disadvantage in the real time system arises.
Since there are processes that require the coordinate conversion processing while calculating and processes that require the coordinate conversion processing besides the behavior calculation processing as a behavior calculation processing, it is not necessarily simple. Therefore, a mechanism, which can send the result of the behavior calculation processing directly to the drawing processing means or use it for the coordinate conversion again, becomes desirable.
SUMMARY OF THE INVENTION
A main subject of the present invention is to provide an image creation device which can cancel the above-mentioned disadvantage.
To solve the above-mentioned disadvantage, an image creation device according to the present invention is characterized by comprising: a plurality of geometry processing means to create a drawing element list by performing geometry processings to express images, respectively, in parallel, said plurality of geometry processing means having at least one first geometry processing means to perform a typical geometry processing and at least one second geometry processing means to perform an atypical geometry processing with close-coupled and in cooperative with other geometry processing means; drawing means to perform a drawing processing based on said drawing element list; and control means to selectively adopt a first mode which parallelizes said at least one first geometry processing means and said at least one second geometry processing means for a processing of a following step and a second mode to lead a processing result of at least one second geometry processing means to an input of said at least one first geometry processing means.
In a first mode, at least two drawing element lists are created in parallel. In a second mode, a drawing element list, in which the processing result of one geometry processing means is reflected to the processing result of other geometry processing means, is created. Thereby, the result of, for example, an atypical geometry processing (coordinate conversion result) is directly led to the latter step processing in the first mode, and is supplied to the coordinate conversion again in the second mode. The efficiency improvement of the entire geometry processing can be achieved by using both of them property.
The control means has a function to dynamically switch one of the first mode and the second mode to the other one thereof. As the switch reference in this case, for example, there are modes to switch according to the entire amount of the geometry processing executed in the plurality of geometry processing means and to switch according to the change in the target of the geometry processing executed in the plurality of geometry processing means. As a latter example, for example, it may be considered when the processor, which performs the atypical geometry processing, performs the retrieval of the representative point of the image which consists of the set in the plurality of vertex, the first mode is adopted, and is switched to the second mode when the retrieval ends.
Thereby, an efficient processing according to the content of the geometry processing becomes possible.
Such an image processing device can be achieved by the computer single unit, the cooperation of the computer and the program, the cooperation of the computer, and the semiconductor device used thereto.
As is clear from the above-mentioned explanation, according to the present invention, since the result of the atypical geometry processing is directly led to the drawing processing means and can be shifted to the coordinate conversion on the way thereof, the geometry processing, which flexibly corresponds to a atypical element, becomes possible.
Since the efficiency improvement of the geometry processing can be achieved entirely and the context switch also decreases, an image creation device suitable by the real time system can be achieved.
Additional objects and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objects and advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out hereinafter.
REFERENCES:
patent: 5835096 (1998-11-01), Baldwin
patent: 6171186 (2001-01-01), Kurosawa et al.
Masaaki Oka et al., Designing and Programming The Emotion Engine -IEEE Micro, Nov.-Dec., 1999, pp. 20-28.
Masakazu Suzoki et al., A Microprocessor with A 128-Bit CPU, Ten Floating-Point MAC's Four Floating-Point Dividers, and An MPEG-2 Decoder-IEEE Journal of Solid-State Circuits, No
Oka Masaaki
Suzuoki Masakazu
Lerner David Littenberg Krumholz & Mentlik LLP
Luu Matthew
Sony Computer Entertainment Inc.
LandOfFree
Image creation device does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Image creation device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image creation device will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3066642