Hardware options installation 30
Memory configurations
To optimize server blade availability, the server blade supports the following AMP modes:
• Advanced ECC—provides the greatest memory capacity for a given DIMM size, while providing up to
4-bit error correction. This mode is the default option for this server blade.
• Lockstep—provides enhanced protection over Advanced ECC mode while continuing to make all
installed memory available to the operating system. The server blade can continue to function if a single-
or mulit-bit memory failure within a single DRAM device occurs.
• Online spare memory—provides protection against failing or degraded DIMMs. Certain memory is
reserved as spare, and automatic failover to spare memory occurs when the system detects a DIMM that
is degrading and receiving a high rate of correctable memory errors. This allows DIMMs that have a
higher probability of receiving an uncorrectable memory error (which would result in system downtime)
to be removed from operation.
• Mirrored Memory—provides maximum protection against failed DIMMs. Uncorrectable errors in one
channel are corrected by the mirror channel.
Advanced Memory Protection options are configured in RBSU. If the requested AMP mode is not supported
by the installed DIMM configuration, the server blade boots in Advanced ECC mode. For more information,
see "HP ROM-Based Setup Utility (on page 55)."
For the latest memory configuration information, see the QuickSpecs on the HP website
(http://www.hp.com).
RDIMM maximum memory configurations
The server blade supports a maximum of 96 GB of memory with one processor (6 x 16 GB), or 192 GB of
memory with two processors (12 x 16 GB).
UDIMM maximum memory configurations
The server blade supports a maximum of 24 GB of memory with one processor and 48 GB of memory with
two processors using 4-GB dual-rank UDIMMs.
Advanced ECC memory configuration
Advanced ECC memory is the default memory protection mode for this server blade. Standard ECC can
correct single-bit memory errors and detect multi-bit memory errors. When multi-bit errors are detected using
Standard ECC, the error is signaled to the server blade and causes the server blade to halt.
Advanced ECC protects the server blade against some multi-bit memory errors. Advanced ECC can correct
both single-bit memory errors and 4-bit memory errors if all failed bits are on the same DRAM device on the
DIMM.
Advanced ECC provides additional protection over Standard ECC because it is possible to correct certain
memory errors that would otherwise be uncorrected and result in a server blade failure. The server blade
provides notification that correctable error events have exceeded a pre-defined threshold rate.
