GB1566951A - Processor system - Google Patents

Processor system Download PDF

Info

Publication number
GB1566951A
GB1566951A GB1357/77A GB135777A GB1566951A GB 1566951 A GB1566951 A GB 1566951A GB 1357/77 A GB1357/77 A GB 1357/77A GB 135777 A GB135777 A GB 135777A GB 1566951 A GB1566951 A GB 1566951A
Authority
GB
United Kingdom
Prior art keywords
processor
slave
executive
results
registers
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired
Application number
GB1357/77A
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
STC PLC
Original Assignee
Standard Telephone and Cables PLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Standard Telephone and Cables PLC filed Critical Standard Telephone and Cables PLC
Priority to GB1357/77A priority Critical patent/GB1566951A/en
Priority to ZA00777568A priority patent/ZA777568B/en
Publication of GB1566951A publication Critical patent/GB1566951A/en
Expired legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04QSELECTING
    • H04Q3/00Selecting arrangements
    • H04Q3/42Circuit arrangements for indirect selecting controlled by common circuits, e.g. register controller, marker
    • H04Q3/54Circuit arrangements for indirect selecting controlled by common circuits, e.g. register controller, marker in which the logic circuitry controlling the exchange is centralised
    • H04Q3/545Circuit arrangements for indirect selecting controlled by common circuits, e.g. register controller, marker in which the logic circuitry controlling the exchange is centralised using a stored programme
    • H04Q3/54541Circuit arrangements for indirect selecting controlled by common circuits, e.g. register controller, marker in which the logic circuitry controlling the exchange is centralised using a stored programme using multi-processor systems
    • H04Q3/5455Multi-processor, parallelism, distributed systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/08Error detection or correction by redundancy in data representation, e.g. by using checking codes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/28Error detection; Error correction; Monitoring by checking the correct order of processing

Description

(54) IMPROVEMENTS IN OR RELATING TO PROCESSOR SYSTEM (71) We, STANDARD TELE PHONES AND CABLES LIMITED, a British Company of 190 Strand, London W.C.2. England, do hereby declare the invention, for which we pray that a patent may be granted to us, and the method by which it is to be performed, to be particularly described in and by the following statement: This invention relates to a multi-processor system of the type in which a so-called executive processor controls a set of socalled slave computers each of which is allotted a programme for it to execute.
In such a system it is necessary for the executive processor to be aware of the serviceability conditions of the slave processors which it controls. Information as to these conditions may be obtained partly from the results of the tasks allotted to the slave computers and partly from routining, but not all failures of the slave processors are rapidly and readily discernible by the executive processor from the effects of failures.
An object of the present invention is to assist the executive processor's rapid determination of a large part of the possible malfunctions of the slave processors.
According to the present invention there is provided a multi-processor system which includes an executive digital processor and a plurality of slave digital processors, in which data processing tasks are allotted to the slave processors by the executive processor for the slave processors to execute those tasks, in which during the execution of a said task a sequence of summation operations is performed on words read fom a memory which contains the programme for the slave processor executing that task, and in which the results of said sequence summation operations are checked by the executive processor at predetermined intervals, the correctness or otherwise of the operations of the slave processor being assessed on the basis of the results of said checks.
An embodiment of the invention will now be described with reference to the highly schematic block schematic drawing accompanying the Provisional Specification.
In the arrangement described herein, the slave processors perform their functions in a simple cyclic manner, and each of the slave processors acts as a major part of a signalling terminal in a multi-exchange telecommunication system. The programme cycles around a closed loop of instructions, the loop having branchings which are followed or not, dependent on the conditions found on the signalling highway or highways under control. The operational conditions of the signalling terminal may also influence the manner in which the program cycles.
In every cycle of the programme a different control word for the programme for the slave processor 1 is read from the read only memory programme store 2 and is added to the contents of a pair of sum registers. Each such word is a 16 bit, i.e. two byte, word and the upper and lower bytes of this word are added respectively to different ones of the sum registers. In the execution of these additions each upper byte is shifted to the lower byte position before it is added to its sum register.
The two sum registers are set to zero at the beginning of the scan of all of the control words in the store such as 2 which contains the programme and its associated fixed data. The address of the word read from the read-only store 2 which is read, split into its bytes, and added to the sum registers is incremented by one after each such addition. This procedure continues until the contents of the last word location of the store 2 have been accessed and added to the sum registers.
When the last word has been read and added to the sum registers, the contents of those sum registers are transferred to two results registers in a storage area 3 which is a random access memory usable either by the slave processor 1 or the executive processor (not shown). This storage area 3 is accessible for either read or write via selectors 4, 5, as required.
The "worst case" acceptable time taken to complete one of these sum check sequences on the memory 2 by the slave processor 1 is known, and the excutive processor accesses the results register in the storage area 3 at intervals greater than the abovementioned worst case time.
If the contents of the results registers when thus checked by the executive processor are not as expected then that slave processor is not functioning correctly and the executive processor takes the necessary action. This could be the disablement of the failed slave processor, plus the transfer of its tasks to a different processor or processors, plus the giving of an alarm to the maintenance staff.
If the results are correct on the above check, the executive processor resets the results registers to zero, and then checks to see if the resetting has in fact been correctly performed.
In an example described above the executive processor checks each slave processor's results registers once per second.
WHAT WE CLAIM IS: 1. A multi-processor system which includes an executive digital processor and a plurality of slave digital processors, in which data processing tasks are allotted to the slave processors by the executive processor for the slave processors to execute those tasks, in which during the execution of a said task a sequence of summation operations is performed on words read from a memory which contains the programme for the slave processor executing that task, and in which the results of said sequency of summation operations are checked by the executive processor at predetermined intervals, the correctness or otherwise of the operations of the slave processor being assessed on the basis of the results of said checks.
2. A system as claimed in claim 1. in which each said slave processor executes the task allotted to it in a cyclic manner by the execution of a closed loop of instructions, with or without branchings, and in which on each cycle of the loop a control word for the slave processor is read from a read-only memory, said sequence of summation operations being effected on said control words.
3. A system as claimed in claim 2, in which each said control word is split into an upper portion and a lower portion for said summation, in which the upper portions of successive ones of said control words are summated in a first sum register and the lower portions of successive ones of said control words are summated in a second sum register, in which the two sums thus produced are transferred respectively to first and second result registers, in which the time taken for a complete summation sequence of control words in one of said slave processors is known, and in which remedial action is taken in respect of a slave processor if the said time exceeds a pre-set maximum acceptable value.
4. A multi-processor system substantially as described with reference to the drawing accompanying the provisional specification.
Reference has been directed in pursuance of section 9, subsection (1) of the Patents Act 1949, to patent No. 1324250
**WARNING** end of DESC field may overlap start of CLMS **.

Claims (4)

**WARNING** start of CLMS field may overlap end of DESC **. added to the sum registers, the contents of those sum registers are transferred to two results registers in a storage area 3 which is a random access memory usable either by the slave processor 1 or the executive processor (not shown). This storage area 3 is accessible for either read or write via selectors 4, 5, as required. The "worst case" acceptable time taken to complete one of these sum check sequences on the memory 2 by the slave processor 1 is known, and the excutive processor accesses the results register in the storage area 3 at intervals greater than the abovementioned worst case time. If the contents of the results registers when thus checked by the executive processor are not as expected then that slave processor is not functioning correctly and the executive processor takes the necessary action. This could be the disablement of the failed slave processor, plus the transfer of its tasks to a different processor or processors, plus the giving of an alarm to the maintenance staff. If the results are correct on the above check, the executive processor resets the results registers to zero, and then checks to see if the resetting has in fact been correctly performed. In an example described above the executive processor checks each slave processor's results registers once per second. WHAT WE CLAIM IS:
1. A multi-processor system which includes an executive digital processor and a plurality of slave digital processors, in which data processing tasks are allotted to the slave processors by the executive processor for the slave processors to execute those tasks, in which during the execution of a said task a sequence of summation operations is performed on words read from a memory which contains the programme for the slave processor executing that task, and in which the results of said sequency of summation operations are checked by the executive processor at predetermined intervals, the correctness or otherwise of the operations of the slave processor being assessed on the basis of the results of said checks.
2. A system as claimed in claim 1. in which each said slave processor executes the task allotted to it in a cyclic manner by the execution of a closed loop of instructions, with or without branchings, and in which on each cycle of the loop a control word for the slave processor is read from a read-only memory, said sequence of summation operations being effected on said control words.
3. A system as claimed in claim 2, in which each said control word is split into an upper portion and a lower portion for said summation, in which the upper portions of successive ones of said control words are summated in a first sum register and the lower portions of successive ones of said control words are summated in a second sum register, in which the two sums thus produced are transferred respectively to first and second result registers, in which the time taken for a complete summation sequence of control words in one of said slave processors is known, and in which remedial action is taken in respect of a slave processor if the said time exceeds a pre-set maximum acceptable value.
4. A multi-processor system substantially as described with reference to the drawing accompanying the provisional specification.
Reference has been directed in pursuance of section 9, subsection (1) of the Patents Act 1949, to patent No. 1324250
GB1357/77A 1977-12-20 1977-12-20 Processor system Expired GB1566951A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GB1357/77A GB1566951A (en) 1977-12-20 1977-12-20 Processor system
ZA00777568A ZA777568B (en) 1977-12-20 1977-12-20 Improvements in or relating to processor system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB1357/77A GB1566951A (en) 1977-12-20 1977-12-20 Processor system

Publications (1)

Publication Number Publication Date
GB1566951A true GB1566951A (en) 1980-05-08

Family

ID=9720617

Family Applications (1)

Application Number Title Priority Date Filing Date
GB1357/77A Expired GB1566951A (en) 1977-12-20 1977-12-20 Processor system

Country Status (2)

Country Link
GB (1) GB1566951A (en)
ZA (1) ZA777568B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005031575A2 (en) * 2003-09-26 2005-04-07 Ati Technologies, Inc. Method and apparatus for monitoring and resetting a co-processor
US7702955B2 (en) 2005-12-28 2010-04-20 De Almeida Adrian S Method and apparatus for detecting a fault condition and restoration thereafter using user context information

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005031575A2 (en) * 2003-09-26 2005-04-07 Ati Technologies, Inc. Method and apparatus for monitoring and resetting a co-processor
WO2005031575A3 (en) * 2003-09-26 2005-05-19 Ati Technologies Inc Method and apparatus for monitoring and resetting a co-processor
US8250412B2 (en) 2003-09-26 2012-08-21 Ati Technologies Ulc Method and apparatus for monitoring and resetting a co-processor
US7702955B2 (en) 2005-12-28 2010-04-20 De Almeida Adrian S Method and apparatus for detecting a fault condition and restoration thereafter using user context information

Also Published As

Publication number Publication date
ZA777568B (en) 1978-10-25

Similar Documents

Publication Publication Date Title
US4635193A (en) Data processor having selective breakpoint capability with minimal overhead
US4080650A (en) Facilitating return from an on-line debugging program to a target program breakpoint
US3781810A (en) Scheme for saving and restoring register contents in a data processor
US4371754A (en) Automatic fault recovery system for a multiple processor telecommunications switching control
US4524415A (en) Virtual machine data processor
US3599176A (en) Microprogrammed data processing system utilizing improved storage addressing means
CA1240065A (en) Error detection and correction system
US7752427B2 (en) Stack underflow debug with sticky base
US4486828A (en) Data processing system providing data security through coded identification of accessing terminals
US4719565A (en) Interrupt and trap handling in microprogram sequencer
US3573736A (en) Interruption and interlock arrangement
KR100543268B1 (en) Security coprocessor for enhancing computer system security
US4074229A (en) Method for monitoring the sequential order of successive code signal groups
GB1081814A (en) Data handling system
US9176821B2 (en) Watchpoint support system for functional simulator
US5491799A (en) Communication interface for uniform communication among hardware and software units of a computer system
CN103955649A (en) Method for safely starting terminal equipment
US4063081A (en) Computer apparatus
GB1566951A (en) Processor system
US3593297A (en) Diagnostic system for trapping circuitry
US3629851A (en) Scanner control circuit for a program-controlled communication switching system
CN111737656B (en) Application program-oriented privileged hardware resource access method and electronic equipment
CN112035379B (en) Method and device for using storage space, storage medium and electronic device
US5455940A (en) Method for abnormal restart of a multiprocessor computer of a telecommunication switching system
GB2373891A (en) Monitoring unaligned memory accesses

Legal Events

Date Code Title Description
PS Patent sealed
PCNP Patent ceased through non-payment of renewal fee