A vector processing system for executing vector instructions, each instruction defining multiple value pairs, an operation to be executed and a modifier, the vector processing system comprising a plurality of parallel processing units, each arranged to receive one of said pairs of values and, when s
A vector processing system for executing vector instructions, each instruction defining multiple value pairs, an operation to be executed and a modifier, the vector processing system comprising a plurality of parallel processing units, each arranged to receive one of said pairs of values and, when selected, to implement an operation on said value pair to generate a result, each processing unit comprising at least one flag and being selectable in dependence on a condition defined by said at least one flag, wherein the modifier defines the condition under which the parallel processing unit is individually selected.
대표청구항▼
The invention claimed is: 1. A vector processing system comprising: a circuit for receiving an instruction defining multiple value pairs, an operation to be executed and a modifier; a plurality of parallel processing units, each arranged to receive one of said value pairs and, when selected, to imp
The invention claimed is: 1. A vector processing system comprising: a circuit for receiving an instruction defining multiple value pairs, an operation to be executed and a modifier; a plurality of parallel processing units, each arranged to receive one of said value pairs and, when selected, to implement the operation on said value pair to generate a result, each processing unit in the plurality of parallel processing units comprising at least one flag and being selectable in dependence on a condition defined by said at least one flag and the modifier; and a scalar processing unit for receiving the results from more than one selected processing unit to generate a scalar result. 2. The vector processing system according to claim 1, wherein said at least one flag is a carry flag. 3. The vector processing system according to claim 1, wherein said at least one flag is a negative flag. 4. The vector processing system according to claim 1, wherein said at least one flag is a zero flag. 5. The vector processing system according to claim 1, wherein a parallel processing unit in the plurality of parallel processing units comprises a plurality of flags, the condition being defined by the state of said plurality of flags. 6. The vector processing system according to claim 1, wherein the modifier in the instruction is a set flag modifier for updating the at least one flag in the plurality of parallel processing units. 7. The vector processing system according to claim 1, wherein the system further comprises a vector register file holding packed operands, each operand comprising multiple values. 8. The vector processing system according to claim 1, wherein a parallel processing unit in the plurality of parallel processing units comprises an accumulator that is selectively operable to accumulate the result of the parallel processing unit. 9. The vector processing system according to claim 8, wherein the modifier of the instruction is an accumulate modifier that causes the accumulator to accumulate the results of successive operations of the parallel processing unit. 10. A method of vector processing, the method comprising: supplying to a first parallel processing unit a first pair of values on which an operation is to be implemented to generate a first result, wherein the first parallel processing unit is one of a plurality of parallel processing units; reading a modifier supplied with an instruction, the modifier defining a condition under which the first parallel processing unit is selected; comparing a state of at least one flag in the first parallel processing unit with the defined condition to determine whether or not the first parallel processing unit is selected; and if the first parallel processing unit is selected, executing the operation to generate the first result; supplying to a second parallel processing unit a second pair of values on which the operation is to be implemented to generate a second result, wherein the second parallel processing unit is another of the plurality of parallel processing units; reading the modifier supplied with the instruction, the modifier defining a condition under which the second parallel processing unit is selected; comparing a state of at least one flag in the second parallel processing unit with the defined condition to determine whether or not the second parallel processing unit is selected; and if the second parallel processing unit is selected, executing the operation to generate the second result, and processing the first result and the second result in a scalar result unit to produce a scalar result. 11. An integrated circuit for vector processing, wherein the integrated circuit comprises: a memory having stored thereon a computer program comprising an instruction stream including a vector instructions, the vector instruction defining multiple value pairs, an operation to be executed on each value pair, and a modifier; and a processor which comprises a plurality of parallel processing units, wherein each parallel processing unit is arranged to receive one of said value pairs and to selectively implement said operation, and wherein cooperation between the computer program and the processor being such that a parallel processing unit is selected to operate on the basis of a condition defined by at least one flag in the processor, and wherein the condition is set by the modifier in the vector instruction, and wherein more than one results from the plurality of parallel processing units is processed to generate a scalar result. 12. The integrated circuit according to claim 11, wherein said at least one flag is a carry flag. 13. The integrated circuit according to claim 11, wherein said at least one flag is a negative flag. 14. The integrated circuit according to claim 11, wherein said at least one flag is a zero flag. 15. The integrated circuit according to claim 11, wherein each parallel processing unit in the plurality of parallel processing units comprises a plurality of flags, the condition being defined by the state of said plurality of flags. 16. The integrated circuit according to claim 11, wherein the modifier in the vector instruction is a set flag modifier for updating the at least one flag in the plurality of parallel processing units. 17. The integrated circuit according to claim 11, wherein the memory further stores a vector register file holding packed operands, each operand comprising multiple values. 18. The integrated circuit according to claim 11, wherein each parallel processing unit in the plurality of parallel processing units comprises an accumulator that is selectively operable to accumulate the result of the parallel processing unit. 19. The integrated circuit according to claim 11, wherein the modifier of the vector instruction is an accumulate modifier that causes the accumulator to accumulate the results of successive operations of the parallel processing unit.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (5)
Pitsianis, Nikos P.; Pechanek, Gerald G.; Rodriguez, Ricardo E., Efficient complex multiplication and fast fourier transform (FFT) implementation on the manarray architecture.
Thomas L. Drabenstott ; Gerald G. Pechanek ; Edwin F. Barry ; Charles W. Kurak, Jr., Methods and apparatus to support conditional execution in a VLIW-based array processor with subword execution.
Sprague David L. (10 Jacobs Creek Rd. Trenton NJ 08628) Harney Kevin (30 Reeve Pl. Brooklyn NY 11218) Kowashi Eiichi (6234 Kaitlyn Ct. Lawrenceville NJ 08648) Keith Michael (14 Quail Dr. Holland PA 1, Simd with selective idling of individual processors based on stored conditional flags, and with consensus among all flag.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.