Supermicro M11SDV-4C-LN4F Power Consumption
We used our pair of Extech TrueRMS Power Analyzer 380803 units to take measurements at different points of the Supermicro M11SDV-4C-LN4F use on 120V power in the embedded lab. Embedded platforms tend to spend more time at the edge in offices rather than in higher power data centers, hence why we do our testing at a lower voltage. Here are the figures:
- Power off BMC only: 4.4W
- OS Idle: 26.7W
- 100% Load: 59.2
- Maximum Observed: 65.8W
These are solid results. The Supermicro M11SDV-4C-LN4F performs well and at a lower power level than many of the Intel Xeon D-2100 performance competitive solutions. In the embedded market, low power is key.
Final Words
In terms of raw performance, the Supermicro M11SDV-4C-LN4F is a great option. If you are coming from the Intel Xeon D-1500 (or lower end Xeon D-1600) series, you will notice a solid uptick in performance with the AMD EPYC 3151 SoC. While Intel’s solutions based on Broadwell-DE are now over four years old, AMD’s is based on a newer architecture. Compared to the Intel Xeon D-2100 series, AMD is offering competitive CPU performance and memory capacity at lower power consumption. There is a compelling space for this platform.
We maintain that there is a segment of the market that needs to diversify from Intel for at least a portion of their portfolio. In the past, that meant going to an Arm server involving porting code. The Supermicro M11SDV-4C-LN4F is a drop-in replacement. Supermicro ensured even the form factors matched as much as possible using a familiar mITX size and rear I/O. When new security vulnerabilities like Foreshadow/ L1TF are found in an architecture well into its lifecycle, having another vendor that is or may not be vulnerable is important for business continuity.
As with the other Supermicro M11SDV offerings, we still wish that Supermicro had found a way to add the AMD EPYC 3000 series quad 10GbE networking onboard. One could argue that there is little to no extra room on the motherboard to put 10GbE cages and that a 10Gbase-T PHY would use too much power and space as well. We understand the design direction, even if we still wish there was a possibility. Our readers have been consistently responding the same in our M11SDV series.
Sharing many of the same I/O placements as Supermicro’s other embedded offerings making integration as alternatives to the company’s other Intel offerings as easy as changing the motherboard part. We think that the company has a large captive market for this product.
Now that street pricing puts this board under $500, and that includes the CPU, there is another aspect to explore. For CPU performance AMD is taking a clear value leadership role in the market giving one the same performance at a significant discount over a Xeon D-2123IT based platform. Offering customers a second chip option at potentially a higher margin will certainly entice OEMs using these platforms.
For the small lab deployment, our suggestion is to get this platform over the Supermicro M11SDV-4CT-LN4F as the extra performance is nice and the price delta is small. For appliance manufacturers, we still see the “4CT” version s a good option. Overall, we were very impressed with this motherboard.
From what I’ve seen, these 3000 series embedded chips from AMD offer 32 PCIe lanes, so I’m somewhat surprised they are keeping these on tiny platforms for the initial launch. I’d think that increased storage flexibility would be a big selling point of a SKU like this, so having additional PCIe slots and/or M.2 would be really nice.
@Andrew: Agree entirely. This article doesn’t plot it directly, but AFAIK Intel still wins performance/watt. AMD’s big advantage is lots more I/O — which such small boards cannot accommodate.
Ya’ll are joking. Right Frank? They’ve even given the data for direct comparison https://www.servethehome.com/supermicro-x11sdv-4c-tln2f-review-with-intel-xeon-d-2123it/3/
Look at the 4c/8t Intel Xeon D-2123IT power consumption compared to the EPYC 3151 here. They’re both using SM boards and the power isn’t close while performance is. That Xeon D-2123IT has 2x the memory bandwidth so that’s fair, but it’s using a lot more power.
I’m hoping maybe the 2nd iteration of Epyc 3xxx boards is a little more ambitious, and takes advantage of 10GbE, more SATA and maybe a FlexATX option with extra PciE slot(s).
what VRMs does this have?
When they add a second pcie slot I will be interested. Then I can add sas control, and 10g or 40g card. One slot is two few. I am enjoying faster networking and want option for 8 platters.
supermicro has a reputation for not supporting standard off the shelf hardware
i’ve seen this board’s compatibility list. its next to impossible to have supermicro green light hardware that’s received thousands of positive reviews just because supermicro isn’t selling it, which makes working with their support team very difficult. i hope that someday soon when you guys write reviews of products, the first consideration is accessibility of support and compatibility
a note on compatibility:
i’d like to build an epyc 3251 server with my own case and power supply
however, supermicro does not include a kit that will allow me to interface their headers to a face plate
supermicro also does not provide adapters to interface standard atx to the power ports and smb headers
so even thought this is a server class board that anyone would like to work with, the review is biased in the sense that we may not use it stand alone. it must come with supermicro enclosures
On the PSU part, they are not using the ATX power so you just need to utilize the CPU power connector on a standard PSU and have a jumper solution (they are around $6 available all over) for the PSU.
On the headers, they are fairly standard pins. It is pretty hard, especially in the server industry, to fault a vendor for not having a pin-compatible solution for every chassis out there. Most server vendors you are lucky to have 1-2 chassis options and many more connectors are customized. We have used these in non-SM chassis without issue though.