Patent US4949243A successfully refreshed from Google Patents.
US4949243A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Data processing system intended for the execution of programs in the form of search trees, so-called or parallel execution
Assignee: SWEDISH INSTITUTE OF COMPUTER SCIENCE
•
Filing: 1987-02-24
•
Granted: 1990-08-14
•
Expires: 2007-02-24
Abstract
Abstract A computer system primarily intended to execute programs, the execution of which can be described in the form of so-called search trees, such as so-called OR Parallel execution, comprising a number of computers or processors and memories. According to the invention, each of the processors (PEO-PE7) can be connected to memory modules (MMO-MM15) via a network (12). The network is capable to connect each processor simultaneously to the write input of a group of memory modules divided for the respective processor, so that the processor in question simultaneously shall be able to write information into the connected group of memory modules, and is capable to connect said processor to the read output of only one memory module in said group. A control member (20) is provided to scan the operation status of the processors (PEO-PE7) and memory modules (MMO-MM15) and is arranged at a pre-determined occasion, such as when a first processor arrives at a division or branching point in said search tree in the executing program, to control said network (12) to connect a second processor, which does not execute, to the read output and write input of one of the memory modules, to the write input of which the first processor had been connected and, thus, fed-in data at the execution all the way to the division or branching point.
Inventors
- 👤 Khayri A. Mohamed Ali
- 👤 Lennart E. Fahlen
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 09:48
CPC Classifications
G; G06; G06F; G06F15/00; G06F15/16; G06F15/163; G06F15/173; G06F15/17356; G06F15/17368; G06F15/17375
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
240 words
A computer system intended primarily for executing programs, the execution of which can be described in the form of search trees, also called OR Parallel execution, comprising a number of separate processors and memory modules with write inputs, wherein each of said separate processors (PE1-PEn; PE; PE0-PE7; PEM) is adapted to be connected to memory modules (MM1-MMn; MM; MM0-MM15; PEM) via a network (1; 5-7,8; 12; 38-41), which network is adapted to connect each of said separate processors simultaneously to a group of write inputs (W;Wr) of memory modules designated for the respective processor, so that a processor simultaneously is adapted to write information into the connected group of memory modules, and is adapted to connect said processor to only one read output (R;Rd) of a memory module present in said group, and that a control member (2;10;20;43) is provided to scan the operation status of the processors (PE1-PEn; PE; PE0-PE7; PEM) and memory modules (MM1-MMn; MM; MM0-MM15; PEM), which control member (2;10;20;43) is arranged at a predetermined occasion, such as when a first processor reaches a branching point in said search tree in the executing program, to control said network (1;5-7,8;12;38-41) to connect another processor, which does not execute, to read output (R;Rd) and write input (W;Wr) of one of the memory modules, to the write input of which the first processor had been connected and, thus, fed-in data at the execution all the way to the branching point.
Claim 2
Dependent Claim
240 words
A computer system intended primarily for executing programs, the execution of which can be described in the form of search trees, also called OR Parallel execution, comprising a number of separate processors and memory modules with write inputs, wherein each of said separate processors (PE1-PEn; PE; PE0-PE7; PEM) is adapted to be connected to memory modules (MM1-MMn; MM; MM0-MM15; PEM) via a network (1; 5-7,8; 12; 38-41), which network is adapted to connect each of said separate processors simultaneously to a group of write inputs (W;Wr) of memory modules designated for the respective processor, so that a processor simultaneously is adapted to write information into the connected group of memory modules, and is adapted to connect said processor to only one read output (R;Rd) of a memory module present in said group, and that a control member (2;10;20;43) is provided to scan the operation status of the processors (PE1-PEn; PE; PE0-PE7; PEM) and memory modules (MM1-MMn; MM; MM0-MM15; PEM), which control member (2;10;20;43) is arranged at a predetermined occasion, such as when a first processor reaches a branching point in said search tree in the executing program, to control said network (1;5-7,8;12;38-41) to connect another processor, which does not execute, to read output (R;Rd) and write input (W;Wr) of one of the memory modules, to the write input of which the first processor had been connected and, thus, fed-in data at the execution all the way to the branching point.
Claim 3
Dependent Claim
71 words
A computer system as defined in claim 1, characterized in that the control member (2;10;20;43) is arranged to control said network (1;5-7,8;12;38-41) to connect the second processor to at least one additional one of the write inputs (W;Wr) of an additional one of said last mentioned memory modules, provided that two memory modules are accessible, so as to write into the same data during the subsequent execution of said second processor.
Claim 4
Dependent Claim
54 words
A computer system as defined in claim 1 characterized in that said control member comprises at least one processor (2;10;20;43) and is connected to each of said separate processors (PE1-PEn; PE; PE0-PE7; PEM), and each of said memory modules (MM1-MMn; MM; MM0-MM15; PEM), and is connected to control inputs (22-27; 46-48) of said network.
Claim 5
Dependent Claim
65 words
A computer system as defined in claim 1, wherein each of said number of separate processors (PE1-PEn; PE; PE0-PE7), comprises a local memory containing a copy of the actual program code, and that separate said memory modules (MM1-MMn; MM; MM0-MM15) comprise a greater number than the number of said separate processors, and the separate processors and said memory modules are connected to said network (1;5-8;12).
Claim 6
Dependent Claim
41 words
A computer system as defined in claim 1, characterized in that it comprises a number of processor elements (PEM), each of which comprises a processor (29) and a memory module (30), which processor elements (PEM) are connected to said network (38-41).
Claim 7
Dependent Claim
112 words
A computer system as defined in claim 1, characterized in that it comprises two or more so-called clusters comprising a number of processors (PE), a number of memory modules (MM) and said network (5-7), which network (5-7) is arranged to connect different processors (PE) and different memory modules (MM) in a cluster one with the other, that said clusters are interconnected via a common network (8) connected to the network (5-7) associated with each cluster, and that the common network (8) and the network (5-7) in each cluster is adapted to connect a processor (PE) in a cluster to the write input of one or several memory modules (MM) in other clusters.
Claim 8
Dependent Claim
65 words
A computer system as defined in claim 1, characterized in that said network (1;5-8;12;38-41) comprises a coupling circuit (13;38-41) comprising a number of selectors (SELECT;MPX), which via said control inputs (22-27;46-48) of the circuit are controlled by said control member (20;43) to couple-up different processors (PE0-PE7;PEM) with the write input and, respectively, different processors with the read output of respective different memory modules (MM0-MM15; PEM).
Claim 9
Dependent Claim
103 words
A computer system as defined in claim 7, characterized in that the circuit (13;38-41) is provided with a number of shift registers (S.R), into which the control member (20;43) is arranged to serially store a number of information bits, which describe the intended coupling-up of the circuit (13;38-41) between different processors (PE0-PE7;PEM) and different memory modules (MM0-MM15;PEM), and is provided with a number of data registers (D.R), to which the control member is arranged to control the transfer of information from the shift registers (S.R.), so that the transfer takes place in parallel, which data registers (D.R.) are connected to said selectors (SELECT;MPX).
Claim 10
Dependent Claim
16 words
A computer system as defined in claim 4 wherein each local memory also contains an interpreter.
References Cited (Backward Citations)
US4368514A
Cited
US4414624A
Cited
US4493030A
Cited
US4691280A
Cited
US4546432A
Cited
US4608631A
Cited
US4757442A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1993-08-13 | 1994-02-12 | 1994-08-14 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1997-08-13 | 1998-02-12 | 1998-08-14 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2001-08-13 | 2002-02-12 | 2002-08-14 | $7700.00 | Window Closed / Lapsed |