Memory choices for Dell 12G Romley servers

Absence of 1333MHz at 3 DPC – for 16GB memory modules

Like IBM and HP, Dell too offers improved speeds and 1600MHz RDIMMs.

Dell also supports LRDIMMs.

However, Dell does not offer HyperCloud (yet).

This places Dell at a competitive disadvantage in the 3 DPC segment.

That is, those servers which are going to run at full memory loading (3 DIMMs per channel) are not going to be able to run at 1333MHz at 3 DPC using HyperCloud.

But the slower 1066MHz at 3 DPC using LRDIMMs.

In addition they will be experiencing the “high latency issues” discussed elsewhere here associated with LRDIMMs.

Absence of 1333MHz at 3 DPC and 2 DPC – for 32GB memory modules

When 32GB memory modules are required, this deficiency will get more glaring – as 32GB RDIMMs (4-rank) experience slowdown and the LRDIMMs vs. HyperCloud latency difference will figure not just at 3 DPC but at 2 DPC (since 32GB RDIMMs (4-rank) will not be in competition at 3 DPC, but also at 2 DPC and possibly 1 DPC – see IBM docs for speed slowdown for 4-rank memory).

Like IBM, which expects 32GB LRDIMMs to be “Available later in 2012”, Dell also has a similar timeline.

http://bladesmadesimple.com/2012/03/dells-poweredge-m620-blade-server-offering-up-to-768gb-ram/#more-1729
March 6, 2012
Dell’s PowerEdge M620 Blade Server Offering Up to 768GB RAM

In the spirit of full disclosure, the 32GB DIMMs, which are required to achieve the maximum capacity of 768GB RAM, will not be available until Q2 2012 (date not provided at this time.)

From the table one can see 4-rank experiencing severe slowdown at higher DPC (as in IBM docs):

RDIMM – dual-rank (2-rank) – at 1.5V
– 1 DPC at 1600MHz
– 2 DPC at 1600MHz
– 3 DPC at 1066MHz

RDIMM – quad-rank (4-rank) – at 1.5V
– 1 DPC at 1066MHz
– 2 DPC at 800MHz
– 3 DPC not supported (because 4 ranks x 3 DPC = 12 ranks which exceeds the 8 ranks per memory rank limit of current systems)

LRDIMM – at 1.5V
– 1 DPC at 1333MHz
– 2 DPC at 1333MHz
– 3 DPC at 1066MHz

Which places them at a competitive disadvantage to IBM and HP who deliver HyperCloud:

HCDIMM – at 1.5V
– 1 DPC at 1333MHz at 1.5V
– 2 DPC at 1333MHz at 1.5V
– 3 DPC at 1333MHz at 1.5V

UPDATE: added 05/31/2012

Here are more detailed numbers from Dell:

http://www.dell.com/downloads/global/products/pedge/poweredge_12th_generation_server_memory.pdf
Memory for Dell PowerEdge 12 th
Generation Servers

From the table one can see 4-rank experiencing severe slowdown at higher DPC (as in IBM docs).

And the effect gets worse at lower voltage (which is what will happen when you go to DDR4 with it’s lower voltages).

LRDIMMs not able to deliver 1333MHz at 3 DPC (as in IBM docs).

Table 3 – PowerEdge memory speeds by type and loading (on pg. 10)

RDIMM – dual-rank (2-rank) – at 1.5V (1600MHz RDIMM)
– 1 DPC at 1600MHz
– 2 DPC at 1600MHz
– 3 DPC at 1066MHz
.
RDIMM – dual-rank (2-rank) – at 1.5V (1333MHz RDIMM)
– 1 DPC at 1333MHz
– 2 DPC at 1333MHz
– 3 DPC at 1066MHz
.
RDIMM – dual-rank (2-rank) – at 1.35V (1333MHz RDIMM)
– 1 DPC at 1333MHz
– 2 DPC at 1333MHz
– 3 DPC not supported (at low voltage)
.
.
RDIMM – quad-rank (4-rank) – at 1.5V
– 1 DPC at 1066MHz
– 2 DPC at 800MHz
– 3 DPC not supported (because 4 ranks x 3 DPC = 12 ranks which exceeds the 8 ranks per memory rank limit of current systems)
.
RDIMM – quad-rank (4-rank) – at 1.35V
– 1 DPC at 800MHz
– 2 DPC at 800MHz
– 3 DPC not supported (because 4 ranks x 3 DPC = 12 ranks which exceeds the 8 ranks per memory rank limit of current systems)
.
.
LRDIMM – at 1.5V or 1.35V
– 1 DPC at 1333MHz
– 2 DPC at 1333MHz
– 3 DPC at 1066MHz

Advertisements

3 Comments

Filed under Uncategorized

3 responses to “Memory choices for Dell 12G Romley servers

  1. are you a netlist marketing employee using this free site for marketing ? shame on you.

    • Please read the About page.

      What is a “shame” is when a product is launched without securing appropriate legal cover for it (LRDIMM).

      I will be happy to retract any statement I have made which is incorrect or not based on fact.

    • Would you care to comment on the outcome of Netlist vs. Inphi in light of the ‘537 and ‘274 patent reexamination re-validations ?

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s