公开(公告)号：DE69624191T2

公开(公告)日：2003-06-12

申请号：DE69624191

申请日：1996-07-25

Applicant: COMPAQ COMPUTER CORP

Inventor： LUBBERS CLARK E ,  ELKINGTON SUSAN G

IPC: G06F11/10 ,  G11C29/00

Abstract: A method for atomically updating Error Detection Code (EDC) protected data in memory such that the EDC protection is maintained to the granularity of a single microprocessor machine instruction. The method is employed in a memory system having a volatile storage area and at least one nonvolatile storage area, each of the storage areas storing a copy of the protected data and two copies of its associated error detection code. The volatile and nonvolatile storage areas each have a first storage location for storing one of the copies of the associated error code and a second storage location for storing the other of the copies of the associated error code. In such a system, a chosen field with the data structure in the volatile copy is updated. Once the volatile copy is updated, a new error detection code is computed with the data in the volatile copy. The new error detection code is then written to the first storage location in each of the storage areas, volatile and nonvolatile, one at a time. Once the copies have been written with the new EDC, the chosen field of the data structure within the nonvolatile copy is updated. Lastly, the new error code is written to the second storage location in each of the updated storage areas.

公开(公告)号：DE69624191D1

公开(公告)日：2002-11-14

申请号：DE69624191

申请日：1996-07-25

Applicant: COMPAQ COMPUTER CORP

Inventor： LUBBERS CLARK E ,  ELKINGTON SUSAN G

IPC: G06F11/10 ,  G11C29/00

Abstract: A method for atomically updating Error Detection Code (EDC) protected data in memory such that the EDC protection is maintained to the granularity of a single microprocessor machine instruction. The method is employed in a memory system having a volatile storage area and at least one nonvolatile storage area, each of the storage areas storing a copy of the protected data and two copies of its associated error detection code. The volatile and nonvolatile storage areas each have a first storage location for storing one of the copies of the associated error code and a second storage location for storing the other of the copies of the associated error code. In such a system, a chosen field with the data structure in the volatile copy is updated. Once the volatile copy is updated, a new error detection code is computed with the data in the volatile copy. The new error detection code is then written to the first storage location in each of the storage areas, volatile and nonvolatile, one at a time. Once the copies have been written with the new EDC, the chosen field of the data structure within the nonvolatile copy is updated. Lastly, the new error code is written to the second storage location in each of the updated storage areas.