Eight bits of Single Error Correct and Dual Error Detect (SECDED) Error Correction Code can be calculated with every burst of write data. This is stored in the HBM and can be checked during read operations.
In the event of an ECC error, it is logged, and optionally an interrupt is triggered. Reads that are correctable are corrected with no impact to performance. You can configure the HBM Controller to write back corrected values to the HBM, with an impact to efficiency.
Note:
- You cannot use ECC and Data Mask concurrently.
- If ECC is not used, you cannot use the ECC memory space to store extra data.