Table of Contents
Advertisement
Theory of Operation
2-17
Error Detection and Correction
The memory controller detects and corrects single-bit errors in data read from RAM. It also detects
double-bit errors. Each 32-bit word written to memory has a 7 -bit Hamming code attached to it.
When the data word is read, any single-bit or double-bit error is detected.
Any single-bit error that is detected is automatically corrected before the word is transferred to the
MPB. No additional time is required for the correction. At the same time that a single-bit error is
detected and corrected, the corrected data word is written into a healer location. Subsequent
accesses of that location are to the healer location rather than to the memory location.
A double-bit error is detected but not corrected. A double-bit error causes the system to halt,
preventing continuation of a program with bad data.
Healing is described in the following paragraphs.
Memory Healing
Each memory controller contains 32 words of CAM and 32 words of RAM which are used to
replace up to 32 failed memory words (Figure 2-8). The physical address of a failed word is put in
the healer CAM, the corrected data is placed in the corresponding healer RAM location, and bit 0 in
the CAM is set to enable the address to match. Subsequent accesses to this physical address are to
the healer RAM instead of the failed memory, causing the healer word to replace the failed word.
Healing in no way affects the timing of the memory operation. Except for the healer, no record of
healing is stored in memory.
All mapped addresses are sent to the healer CAM which compares each mapped address to all
addresses of failed locations. Healer CAM addresses of failed locations have bit 0 set.
When all 32 locations of the healer are full, no further healing or automatic changes to the healer
CAM occur on that memory controller. When all healer locations have been used, the healer
overflow bit in the MC status register is set.
When all healer locations are full, the operating system checks each healed location to determine if
the location is still faulty. If the location fault was caused by a momentary failure, the overflowed
CAM can be cleared and reused by the operating system.
Advertisement
Table of Contents
