Apparatus for creating a scalable graphics system with efficient memory and bandwidth usage

• US 5,999,183 A
• Filed: 07/10/1997
• Issued: 12/07/1999
• Est. Priority Date: 07/10/1997
• Status: Expired due to Term

• Current Assignee: Creative Technology Ltd.
• Original Assignee: Silicon Engineering, Inc. (Creative Technology Ltd.)
• Inventors: Brown, Philip, Kilgariff, Emmett
• Primary Examiner(s): Nguyen, Phu K.
• Assistant Examiner(s): Vo, Cliff N.
• Application Number:
  US08/891,280
• Time in Patent Office: 880 Days
• Field of Search: 345/418, 345/419, 345/513, 345/512, 345/508
• US Class Current: 345/418
• CPC Class Codes: G06T 15/00 3D [Three Dimensional] image rendering

Abstract

A scalable, three-dimensional (3D) graphics subsystem. The graphics subsystem includes a plurality of graphics modules each including a rendering module and a dedicated memory. In one embodiment, the rendering modules of the graphics modules are coupled together, possibly through a routing device, such that each rendering module views the memory space, formed by all dedicated memory, as one continuous shared memory.

Claims

1. A scalable graphics subsystem comprising:

a first graphics module including a first rendering module to create a display image, the first rendering module coupled to a first memory; and

a second graphics module including a second rendering module to create the display image, the second rendering module coupled to a second memory and in communication with the first rendering module, the second rendering module having access to information contained within the first memory.

2. The scalable graphics subsystem of claim 1, wherein the first rendering module is coupled to the second rendering module through a communication line.

3. The scalable graphics subsystem of claim 2, wherein the second rendering module including a memory controller having an expansion port coupled to the communication line, the memory controller enables the information to be obtained from the first memory and enables information to be loaded into the first memory.

4. The scalable graphics subsystem of claim 2, wherein the first rendering module is capable of accessing information contained in the second memory.

5. The scalable graphics subsystem of claim 4, wherein the first rendering module including a memory controller having an expansion port coupled to the communication line, the memory controller enables the information to be obtained from the second memory and enables information to be loaded into the second memory.

6. The scalable graphics subsystem of claim 5, wherein the expansion port supports serial data transmissions over the communication line.

7. The scalable graphics subsystem of claim 1 further comprising a routing device coupled to the first rendering module and the second rendering module, the routing device enables the second rendering module to be in communication with the first rendering module so that the second rendering module has access to the information contained within the first memory.

8. The scalable graphics subsystem of claim 7, wherein the routing device further enables the first rendering module to have access to information contained within the second memory.

9. The scalable graphics subsystem of claim 1 further comprising:

a first routing device coupled to the first rendering module; and

a second routing device coupled to the first routing device and the second rendering module, the second routing device enables the second rendering module to have access to the information contained within the first memory by supporting transmission of the information through the first and second routing devices and the first rendering module.

10. The scalable graphics subsystem of claim 1 further comprising:

a first routing device coupled to the first rendering module; and

a second routing device coupled to the first routing device and the second rendering module, the second routing device enables the first rendering module to have access to information contained within the second memory by supporting transmission of the information through the second routing device and the second rendering module.

11. A scalable graphics subsystem comprising:

a first graphics module including a first rendering module to create a display image and a first memory;

a second graphics module including a second rendering module to create the display image and a second memory; and

a first routing device coupled to the first graphics module and the second graphics module so that the first and second modules view memory space, formed by the first and second memories, as one continuous shared memory to enable the second rendering module to access a first set of display primitives contained in the first memory and the first rendering module to access a second set of display primitives contained in the second memory.

12. The scalable graphics subsystem of claim 11, wherein the second rendering module has access to a first set of display primitives contained in the first memory.

13. The scalable graphics subsystem of claim 12, wherein the first rendering module has access to a second set of display primitives contained in the second memory.

14. The scalable graphics subsystem of claim 13, wherein the first rendering module includes a first memory controller coupled to the first memory, the first memory controller includes an expansion port to allow the second set of display primitives to be routed into the first memory controller from the routing device.

15. The scalable graphics subsystem of claim 13, wherein the second rendering module includes a second memory controller coupled to the second memory, the second memory controller includes an expansion port to allow the first set of display primitives to be routed into the second memory controller from the routing device.

16. In a scalable graphics subsystem having at least a first graphics module and a second graphics module, a method comprising the steps of:

receiving a read request from a requesting agent by the first graphics module, the read request including a source identification, a request code and a device address;

decoding the read request to determine if the device address is associated with a local memory of the first graphics module;

mapping the device address into a device identification;

transmitting to a routing device information including the device identification, the request code, an address of the requesting agent, an assigned request number and a memory address;

determining whether a second graphics module identified by the device identification is coupled to the routing device;

accessing data contained at the memory address within a dedicated memory of the second graphics module if the second graphics module identified by the device identification is coupled to the routing device; and

returning the data to the requesting agent.

17. In a scalable graphics subsystem having at least a first graphics module and a second graphics module, a method comprising the steps of:

receiving a write request from a requesting agent by the first graphics module, the write request including data, a source identification, a request code and a device address;

decoding the write request to determine if the device address is associated with a local memory of the first graphics module;

mapping the device address into a device identification;

transmitting to a routing device information including the data, the device address, the request code, an address of the requesting agent, an assigned request number and a memory address;

determining whether a second graphics module identified by the device identification is coupled to the routing device;

writing the data into the memory address of a dedicated memory of the second graphics module if the second graphics module identified by the device identification is coupled to the routing device; and

returning an acknowledgment (ACK) to the requesting agent.