Vector processing system
View Patent ↗A vector processing system for executing vector instructions, each instruction defining multiple pairs of values, an operation to be executed on each of said value pairs and a scalar modifier, the vector processing system comprising a plurality of parallel processing units, each arranged to receive one of said pairs of values and to implement the defined operation on said value pair to generate a respective result; and a scalar result unit for receiving the results of the parallel processing units and for using said results in a manner defined by the scalar modifier to generate a single output value for said instruction.
1. An integrated circuit comprising:
a decode circuit for receiving a plurality of instructions wherein a first instruction comprises a first operation and a second instruction comprising a second operation;
a processing unit for executing the first operation on a pair of input values and generating an output result, wherein the output result is stored in a register file;
a plurality of pixel processors, wherein each pixel processor is arranged to receive one or more values from the register file and implement the second operation on said one or more values to generate a respective result, and wherein each of the plurality of pixel processors is identified by an index; and
a post-processor for receiving the results of the plurality of pixel processors and for using said results in a manner defined by a modifier to return the index of one of the pixel processors.
2. The integrated circuit according to claim 1 , wherein the post-processor is operable to select the result from one of said plurality of pixel processors.
3. The integrated circuit according to claim 1 , wherein the post-processor is operable to sum the results from said plurality of pixel processors.
4. The integrated circuit according to claim 1 , wherein the post-processor is operable to return the index of the pixel processors that generated the minimum result.
5. The integrated circuit according to claim 1 , wherein the post-processor is operable to return the index of the pixel processors that generated the maximum result.
6. The integrated circuit according to claim 1 , wherein the post-processor is operable to return the minimum result.
7. The integrated circuit according to claim 1 , wherein the post-processor is operable to return the maximum result.
8. The integrated circuit according to claim 1 , wherein each pixel processor in the plurality of pixel processors is selectable by at least one flag.
9. The integrated circuit according to claim 8 , wherein the post-processor processes the results only of selected ones of the pixel processors.
10. The integrated circuit according to claim 1 , wherein the integrated circuit further comprises a memory for holding packed operands, each operand comprising multiple values.
11. The integrated circuit according to claim 1 , wherein the first instruction is a scalar instruction.
12. The integrated circuit according to claim 1 , wherein the second instruction is a vector instruction.
13. The integrated circuit according to claim 1 , wherein the results of the plurality of pixel processors are stored in a vector file.
14. The integrated circuit according to claim 13 , wherein the contents of the register file are available to the vector file.
15. The integrated circuit according to claim 1 , wherein the index returned by the post-processor is available to the register file.
16. The integrated circuit according to claim 1 , wherein the processing unit is an arithmetic processing unit.