Dynamic cache row fail accumulation due to catastrophic failure

摘要

A technique is provided for accumulating failures. A failure of a first row is detected in a group of array macros, the first row having first row address values. A mask has mask bits corresponding to each of the first row address values. The mask bits are initially in active status. A failure of a second row, having second row address values, is detected. When none of the first row address values matches the second row address values, and when mask bits are all in the active status, the array macros are determined to be bad. When at least one of the first row address values matches the second row address values, mask bits that correspond to at least one of the first row address values that match are kept in active status, and mask bits that correspond to non-matching first address values are set to inactive status.

主权项

1. A computer system, comprising:
a controller and a group of array macros, the system configured to perform a method comprising: detecting, by the controller, a failure of a first row in the group of array macros, the first row having first row address values; configuring a mask to have associated mask bits individually corresponding to each of the first row address values, wherein the associated mask bits are initially all in an active status; detecting, by the controller, a failure of a second row in the group of array macros, the second row having second row address values; comparing the first row address values to the second row address values; if none of the first row address values match the second row address values in the comparing and if the associated mask bits are all in the active status, determining, by the controller, the group of array macros is bad; if at least one of the first row address values match the second row address values in the comparing, keeping in the active status the associated mask bits that individually correspond to the at least one of the first row address values that match, and setting to inactive status the associated mask bits that individually correspond to non-matching first address values during the comparing, wherein, for new accesses to the group of array macros, new row address values of new rows in the group of array macros are only compared to the first row address values having the associated mask bits in the active status; accumulating the new rows as row failures, in response to the new row address values matching the first row address values having the associated mask bits in the active status; in response to detecting the failure of the second row and before failures are detected in a group of adjacent rows, preemptively setting the group of adjacent rows as failures in the group of array macros if the group of adjacent rows each have adjacent row address values matching the first row address values corresponding to the associated mask bits in the active status.