US5029080A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for composing a set of instructions for executing a data flow program defined by structured data
Assignee: Hitachi Ltd
•
Filing: 1988-04-14
•
Granted: 1991-07-02
•
Expires: 2008-04-14
Abstract
Abstract A method of composing a set of instructions for directly executing a data-flow type program by using a Petri net diagram direction to structured data of at least one of, or a combination of, Cartesian product, direct union and sequence, and a structured data driven type processor system for executing a program containing such instructions. In composing a set of instructions, desired data paths, i.e., links, are provided in accordance with the Petri net diagram, and the links are defined by a data type which defines the data to be processed. A work node connected to the link at the input side of the work node is defined which work node takes data from the link at the input side of the work node, performs a desired calculation to take the calculation result out to the link at the output side of the work node. A data type defining data on the link at the output side is restricted by a calculation function of the work node. Instructions associated with data structure include a decomposition instruction for decomposing structured data into constituent elements and a composition instruction for composing data of Cartesian product, direct union or sequence from constituents elements. The decomposition and composition instructions are added to instruction languages of the structured data driven type system.
Inventors
- 👤 Shigeru Otsuki
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 22:37
CPC Classifications
G; G06; G06F; G06F9/00; G06F9/06; G06F9/44; G06F9/448; G06F9/4494
Claims Analysis
Total Claims: 4
Claim 1
Independent Claim
287 words
A structured data processor system comprising: a plurality of processors for executing instruction; an instructions buffer for holding instructions in executing a data-flow program; execution control means for judging whether instructions, from said instruction buffer to be executed by said plurality of processors, are executable and sending said instructions to said plurality of processors if judged to be executable; means for interconnecting said execution control means, said instruction buffer and said plurality of processors; wherein instructions having a complete set of operand data can be executed in parallel in said plurality of processors; and wherein said instruction buffer includes an area for storing information on a decomposition instruction and a composition instruction to be executed by said plurality of processors, wherein when said decomposition instruction is executed by said plurality of processors, structured data being inputted to said plurality of processors is decomposed into constituent elements, said structured data being of at least one of Cartesian product data, direct union data and sequence data, or data convertible into such structured data, and wherein when said composition instruction is executed by said plurality of processors, constituent elements being inputted to said plurality of processors is composed into structured data being of at least one of Cartesian product data, direct union data or sequence data; a link buffer for storing link information on links included in a data-flow program diagram and having operands of said instruction; and link buffer control means connected to said link buffer for performing an exclusive control of said link information; wherein said link buffer control means cooperates with said execution control means to send said link information of said link buffer to said plurality of processors in accordance with instructions from said instruction buffer.
Claim 2
Dependent Claim
287 words
A structured data processor system comprising: a plurality of processors for executing instruction; an instructions buffer for holding instructions in executing a data-flow program; execution control means for judging whether instructions, from said instruction buffer to be executed by said plurality of processors, are executable and sending said instructions to said plurality of processors if judged to be executable; means for interconnecting said execution control means, said instruction buffer and said plurality of processors; wherein instructions having a complete set of operand data can be executed in parallel in said plurality of processors; and wherein said instruction buffer includes an area for storing information on a decomposition instruction and a composition instruction to be executed by said plurality of processors, wherein when said decomposition instruction is executed by said plurality of processors, structured data being inputted to said plurality of processors is decomposed into constituent elements, said structured data being of at least one of Cartesian product data, direct union data and sequence data, or data convertible into such structured data, and wherein when said composition instruction is executed by said plurality of processors, constituent elements being inputted to said plurality of processors is composed into structured data being of at least one of Cartesian product data, direct union data or sequence data; a link buffer for storing link information on links included in a data-flow program diagram and having operands of said instruction; and link buffer control means connected to said link buffer for performing an exclusive control of said link information; wherein said link buffer control means cooperates with said execution control means to send said link information of said link buffer to said plurality of processors in accordance with instructions from said instruction buffer.
Claim 3
Dependent Claim
55 words
A system according to claim 1, wherein said link buffer includes an area for storing link information of a data-flow program and an area for storing information on a data structure corresponding to said stored link information, and said instruction buffer stores information having an instruction format of said data-flow program as an instruction packet.
Claim 4
Dependent Claim
30 words
A system according to claim 2, wherein said instruction packet includes an instruction code defining a work node, and link information for input and output sides of said work node.
References Cited (Backward Citations)
US4315315A
Cited
US3962706A
Cited
US4145733A
Cited
US4149240A
Cited
US4319321A
Cited
US4455619A
Cited
US4644461A
Cited
US4814978A
Cited
US4866663A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1994-07-01 | 1994-12-31 | 1995-07-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1998-07-01 | 1998-12-31 | 1999-07-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2002-07-01 | 2002-12-31 | 2003-07-02 | $7700.00 | Window Closed / Lapsed |