System and method for directing the flow of data and instructions into at least one functional unit
View Patent ↗A system and method are provided for directing the flow of data and instructions into at least one functional unit. In one embodiment of a system of components defining a plurality of nodes, a queue network manager (QNM) forming a part of each node, is provided. In this embodiment, the QNM comprises an interface to a network that supports intercommunication among the plurality of nodes, an interface configured to pass messages with a functional unit within the node, a random access memory (RAM) configured to store at least one of a message and a programmable instruction, and logic configured to control an operational aspect of a functional unit based on contents of the programmable instruction.
1. In a system of components defining a plurality of nodes, a queue network manager (QNM) forming a part of each node, the QNM comprising:
an interface to a network that supports intercommunication among the plurality of nodes;
an interface configured to pass messages with a functional unit within the node;
a random access memory (RAM) configured to store at least one of a message and a programmable instruction; and
logic configured to evaluate contents of the programmable instruction and configure the functional unit to control an operational aspect of the functional unit based on the evaluated contents of the programmable instruction.
2. The QNM of claim 1 , wherein the logic configured to control an operational aspect of a functional unit comprises an execution unit within the QNM that is configured to evaluate the programmable instruction stored in the RAM.
3. The QNM of claim 1 , further including at least one execution unit, each execution unit configured to perform a functional operation.
4. The QNM of claim 3 , wherein the programmable instruction is operable to control an operation of at least one execution unit.
5. The QNM of claim 1 , further including logic to receive a programmable instruction from a remote node and store the programmable instruction in the RAM.
6. The QNM of claim 1 , wherein the functional unit is a message-producing functional unit.
7. The QNM of claim 1 , wherein the functional unit is a message-consuming functional unit.
8. The QNM of claim 1 , wherein the system is a computer graphics system.
9. The system of claim 1 , wherein the at least one message contains an instruction for the at least one functional unit.
10. The system of claim 1 , wherein the at least one functional unit is one selected from the group consisting of a texture mapping component, a geometry accelerator, a shader, a z/blend component, a rasterizer, a tiler, and a cache controller.
11. In a system of components defining a plurality of nodes, a method for directing the flow of data and instructions into at least one functional unit, the method comprising:
receiving a programmable instruction from a remote node through a first interface;
storing the programmable instruction in a random access memory (RAM); and
using contents of the programmable instruction to configure the operation of the functional unit.
12. The method of claim 11 , further comprising receiving a message from remote node and storing the received message in the RAM.
13. The method of claim 12 , further comprising exchanging messages with at least one functional unit through a second interface.