摘要:
A personal computer has two memory banks (12,14) respectively connected to two parity check units (16,18) operative to detect parity errors. Upon doing so, each unit (16,18) feeds a parity error signal to a separate latch (22,24). The latches (22,24) are connected to a logic circuit (26) which is in turn connected to an interrupt controller (34) that initiates an interrupt (36) when a parity error occurs. One latch (22) is further connected to a check bit (41) of a register (40) of an I/O port (38) and the check bit (41) is set by the one latch (22). An interrupt handler reads the register and provides messages indicating which memory bank (12,14) caused the parity error.
摘要:
A multiprocessor digital data processing system comprises a plurality of processing cells (18A to 18R, 34A to 34F, 38A, 38B) arranged in a hierarchy of rings (12A to 12F, 14A and 14B, 16). The system selectively allocates storage and moves exclusive data copies from cell to cell in response to access requests generated by the cells. Routing elements are employed to selectively broadcast data access requests, updates and transfers on the rings.
摘要:
Zum Registrieren von Adressen von einen hinsichtlich der Codierung fehlerhaften Speicherinhalt aufweisenden Speicherzellen einer über ein Busleitungssystem (DB, AB, SB) mit einer Zentralsteuereinheit (MPB) verbundenen Speicheranordnung (SBG) ist ein Register (Reg) vorgesehen, in dessen Registerzellen die bei der Durchführung eines Lesezyklus in der Speicheranordnung über das Busleitungs system übertragene Adresse der ausgewählten Speicherzelle einschreibbar ist. Jeder bei einem solchen Lesezyklus aus einer der Speicherzellen ausgelesener Speicherinhalt wird in einer Fehlererkennungsschaltung (FE) auf einen gegebenen falls vorhandenen Codierungsfehler überprüft. Bei Erkennen eines derartigen Codierungsfehlers gibt dann die Fehlerer kennungsschaltung ein entsprechendes Fehlersignal ab. Auf ein solches Fehlersignal hin sperrt eine Steuereinrichtung (G1, FF) das Register für die Übernahme einer weiteren über das Busleitungssystem übertragenen Adresse. Außerdem veranlaßt diese Steuereinrichtung die Zentralsteuereinheit, die in die Registerzellen des Registers zuletzt eingeschriebene Adresse als Adresse einer fehlerhaften Speicherzelle zu wer ten.
摘要:
The system has a flexible internal structure, protected from and effectively invisible to users, with multilevel control and stack mechanisms and the capability of performing multiple, concurrent operations, and providing a flexible, simplified interface to users.. The system comprises a plurality of separate, independent job processors (10114) and a memory (10112). Each processor includes a fetch unit (10120) and an execute unit (10122) and the fetch unit structures operands and instructions into objects. The fetch unit includes a register address generator generating unique and permanent identifier codes for the objects. The memory (10112) includes sections storing procedure objects, including a name table providing the operand addresses in the memory. The memory (10112) also includes protection tables for preventing a user obtaining access to objects private to others. The protection tables operate in association with a protection cache in the fetch unit (10120) and an active subject number register which stores a currently active number identifying the user, the procedure he is using and the type of operation instructed. The protection tables store an access control list establishing the access rights,of the subjects and the protection cache in the fetch unit (10120) controls access to the objects by comparing the currently 'active subject number with the requested object. The fetch unit includes a descriptor processor performing the opera- I tions required by the instructions and first and second microcode control means storing first and second sequences of microinstructions for controlling the descriptor processor, the first sequences being S-language instructions which have a uniform, fixed format in an intermediate level language.
摘要:
Method and apparatus for detecting and correcting both transient and single bit memory read errors while selectively logging only solid (that is, hardware-related) single bit memory read errors. Each of a plurality of memory modules directly transmits uncorrected memory data to a processor memory control while also providing for automatic local restoring of corrected data back into the memory address which produced the single bit error. The processor memory control provides its own error detection and correction which detects both multiple and single bit errors. Multiple bit errors are not corrected, but merely brought to the attention of the processor. Single bit errors are corrected, but only those which are found to most likely be solid errors are logged. A solid single bit error is recognized by detecting when two single bit errors having the same memory address occur consecutively.
摘要:
Disclosed is a main storage failure address control system in a data processing system which comprises a plurality of main storage units (MSU) including a hardware prefix area, a main storage control unit (MCU), a plurality of data processing units (CPU), and at least one data transfer apparatus, in which when a failure occurs at the read or write operation in the main storage unit, the failed main storage address is held in a failed main storage address register FSAR (41), and the address is then stored in the hardware prefix area; wherein the failed main storage address register FSAR (41) is located in the main storage control unit. In this system, the circuit constitution for reading the failed main storage address during access to the main storage unit and for storing the address into the hardware prefix area is simplified. Thus, increasing the efficiency of the processing of the system.
摘要:
The invention relates to a control method and apparatus for a plurality of memory units installed in a data processing system. In the control method a plurality of memory units (4, 5) perform simultaneous writing or reading operations, one of the memory units (4;5) being selected for normal use. In the event of an error occurring during a write mode operation, a memory unit (4;5) without error is immediately selected alternatively, and in the event of an error during a read mode operation the selection is made in response to the next clock pulse to permit a retry from a processor (1 ;2). The control apparatus comprises a plurality of memory units (4, 5), memory unit access means (12), a plurality of error holding circuits (17, 18), control means (23), status selection commanding means (13), and status selector means (14). The control method and apparatus works with enhanced reliability and performance.
摘要:
A memory address translation and related control system for performing the dual functions of converting virtual memory addresses generated by the CPU into real memory addresses in a highly efficient and versatile manner and for controlling certain memory functions such as journalling. The address translation function comprises two steps, the first comprising converting the virtual address into a second virtual address or an effective address and finally the step of converting the effective address into a real memory address. The first step utilizes a set of special registers addressable by a small field of the CPU generated virtual address which converts the virtual address into an expanded form. The second or effective address is then used as the subject of the second or address translation step. To greatly enhance the translation of frequently used virtual addresses, a special set of translation tables referred to herein as a Translation Look-Aside, Buffer (TLB) contain current effective to real address translations for use where frequently referenced addresses are requested. The TLBs are addressed using a subset of the effective address whereupon the contents of the addressed TLB is examined for a match with the effective address. If the addresses match a successful address translation is possible and the real address stored in the address field of the TLB is available for system use. If the desired effective address is not present in the TLB, the page frame tables stored in main memory are accessed and searched for the desired effective address and if found the associated real address is accessed. Further a special data field is provided in both the TLBs and the page frame tables in main memory wherein a bit is provided for each line in the referenced page at a given effective to real address translation which bits may be used to indicate when a line of data has been accessed or altered.
摘要:
A microprocessor is described. The microprocessor includes a software-based monitor for detecting TLB corruptions. The TLB corruptions contribute to undetected erroneous upset rate of the microprocessor. The software monitor detects errors in the TLB. The software-based monitor detects TLB corruptions in microprocessors where hardware protection mechanisms are not available. The software monitor mitigates single event effects due to atmospheric particles and improves the safety of high integrity computing products.