Abstract:
Routine processing for routine data, non-routine processing for routine data and general non-routine processing are to be processed efficiently. To this end, a main CPU has a CPU core having a parallel computational mechanism, a command cache and a data cache as ordinary cache units, and a scratch-pad memory SPR which is an internal high-speed memory capable of performing direct memory accessing (DMA) suited for routine processing. A floating decimal point vector processor (VPE) has an internal high-speed memory (VU-MEM) capable of DMA processing and is tightly connected to the main CPU to form a co-processor. The VPE has a high-speed internal memory (VU-MEM) capable of DMA processing. The DMA controller (DMAC) controls DMA transfer between the main memory and the SPR, between the main memory and the (VU-MEM) and between the (VU-MEM) and the SPR.
Abstract:
A surface computer includes an address generator for generating an address for adjusting surface region data concerning at least a storage region and a concurrent computer, provided at a subsequent stage of the address generator, having a plurality of unit computers.
Abstract:
An apparatus for displaying an object such as a billboard in a virtual world is provided. An input history of a user's operation for moving a character in the virtual world is obtained. The movement track of the character in the virtual world is also obtained. The position and direction of the billboard are changed according to the input history and the movement track so that the billboard is visible to the user. For instance, on a street where the user is expected to move at a high speed, the direction of the billboard is changed so that its display surface can face the front of the character and the billboard is displayed in a position far away from the user's viewing position.
Abstract:
A prefetch command control apparatus is provided. A protocol slot generation unit, when receiving from a CPU a prefetch command in which a utilization time of data to be prefetched is specified, generates a protocol slot based on the utilization time and registers it in a schedule list storage unit. When receiving a regular access command, the protocol slot generation unit registers a protocol slot in a regular protocol queue storage unit. A cost evaluation unit evaluates an issuance cost of the prefetch command based on a cache retention time of data to be prefetched and evaluates an issuance cost of the regular access command based on a resource occupation cost. A protocol issuance unit decides which command shall be issued, the prefetch command or regular access command, based on the evaluation result of these issuance costs.
Abstract:
The present invention relates to the architecture and use of a computer system optimized for the efficient modeling of graphics. The computer system has a primary processor and a graphics processor. The primary processor has two vector processor units within it, one which is closely connected to central processor unit. Simultaneously performing complex modeling calculations on the first vector processor and CPU, and geometry transformation calculations on the second vector processor, allows for efficient modeling of graphics. Furthermore, the graphics processor is optimized to rapidly switch between data flows from the two vector processors. In addition, the graphics processor is able to render many pixels simultaneously, and has a local memory on the graphics processor chip that acts as a frame buffer, texture buffer, and z buffer. This allows a high fill rate to the frame buffer.
Abstract:
An image processing apparatus for performing rendering processing of three-dimensional objects is provided. An object storage unit stores the three-dimensional data of the object and the array data of B-box which encloses the spatial region which the object occupies. A grouping unit reads in the B-box array from the object storage unit, does grouping of multiple B-boxes into groups based on the object characteristics and level of detail information. A rendering processing unit derives a brick in which there are B-boxes belonging to the same group and generates image data by doing rendering processing independently by brick to be stored in an image storage unit. A consolidation unit consolidates the image data per brick stored in the image storage unit and generates the final output image data to be displayed.
Abstract:
A communication device communicates information via a virtual world configured by a server machine to client terminal devices operating characters in the virtual world. It is therefore possible to transmit various information to and to receive various information from the virtual world, even from a place remote from the client terminal devices, which enables a linking between the virtual world and the real world to be realized.
Abstract:
A rectangular-parallelopiped space (box space) expresses the moving images by use of a virtual space. A plurality of frames contained in the moving images appear continuously along time axis. The box space is cut through by a desired surface, and an image projected on this cut surface is projected onto a plane parallel in the direction of time axis. Images sequentially projected onto the plane are outputted as new moving images.