Unisys Corporation

Jerome G Carlin

Mitchell A Bauman

Larry L Byers

Gary R Robeck

Roger Lee Gilbertson

Lloyd E Thorsbakken

Michael R Overley

R Lee Gilbertson

A system and method for managing memory data within a data processing system is disclosed. A main memory is provided to store data signals. When the main memory receives a request to read data signals, the main memory determines whether an updated copy of the requested data signals may be stored within some other storage device within the system. If so, the main memory issues a snoop request to this other storage device to cause any updated copy of the requested data to be returned to the main memory. In addition, the main memory reads the requested data signals from its data store. This data will be used to satisfy the read request if an updated copy of the data signals is not returned to the main memory in response to the snoop request. Otherwise, the updated copy is provided to fulfill the request.

System and method for accelerating read requests within a multiprocessor system

An improved fault detection system and method for detecting the occurrence of faults within the addressing logic of a storage device is provided. Data stored to a selected address within a storage device includes a copy of the selected address. During a subsequent read operation, the copy of the address is read from memory and compared to the read address used to perform the memory access. If the addresses are not the same, a potential addressing fault occurred within the control logic of the storage device. The fault detection system is particularly adaptable for use with storage devices having a relatively small number of addressable locations, each containing a relatively large number of bits. According to one embodiment of the invention, the storage device is a General Register Array (GRA) utilized as a queue.

System and method for detecting faults in storage device addressing logic

An improved memory request storage and allocation system using parallel queues to retain different categories of memory requests until they can be acted on by the main memory. Memory requests in the parallel queues are allowed to access the main memory according to a queue priority scheme. The queue priority scheme is based on an adjustable ratio, which determines the rate at which memory requests from one queue are allowed to access the main memory versus memory requests from other queues. Registers for bypassing the adjustable ratio eliminate delays by prohibiting the queue priority circuitry from attempting to retrieve a non-existent memory request from a queue. Conflict detection circuitry maintains proper instruction order in the parallel queue architecture by ensuring that subsequent memory requests, which have the same address as a memory request already in the queue, are placed in the same queue in the order that they were entered into the queue.

Memory queue with adjustable priority and conflict detection

Growing community of inventors

Saint Paul, MN, United States of America

Jerome G Carlin