External Memory Interface Handbook Volume 3: Reference Material: For UniPHY-based Device Families

ID 683841
Date 3/06/2023
Public
Document Table of Contents

3.4.4. ECC

The hard controller supports both error-correcting code (ECC) calculated by the controller and by the user. Controller ECC code employs standard Hamming logic which can detect and correct single-bit errors and detect double-bit errors. The controller ECC is available for 16-bit and 32-bit widths, each requiring an additional 8 bits of memory, resulting in an actual memory width of 24-bits and 40-bits, respectively.

In user ECC mode, all bits are treated as data bits, and are written to and read from memory. User ECC can implement nonstandard memory widths such as 24-bit or 40-bit, where ECC is not required.

Controller ECC

Controller ECC provides the following features:

Byte Writes—The memory controller performs a read/modify/write operation to keep ECC valid when a subset of the bits of a word is being written. If an entire word is being written (but less than a full burst) and the DM pins are connected, no read is necessary and only that word is updated. If controller ECC is disabled, byte-writes have no performance impact.

ECC Write Backs—When a read operation detects a correctable error, the memory location is scheduled for a read/modify/write operation to correct the single-bit error.

User ECC—User ECC is 24-bits or 40-bits wide; with user ECC, the controller performs no ECC checking. The controller employs memory word addressing with byte enables, and can handle arbitrary memory widths. User ECC does not disable byte writes; hence, you must ensure that any byte writes do not result in corrupted ECC.