Out-of-the-Box Performance Evaluation

Silicon Motion claims read speeds of up to 895 MBps and write speeds in excess of 700 MBps in their marketing material for the SM2708. However, these speeds are heavily dependent on the NAND flash in the card. For the sampled reference design, Silicon Motion mentioned that they were seeing 895 MBps reads and around 420 MBps writes in terms of peak performance. Real-world speeds are bound to be much lower, depending on the particulars of the access trace.

CrystalDiskMark [Fresh]

CrystalDiskMark serves as a quick check to ensure that the card can meet the performance claims of the manufacturer. The workloads were processed for the SM2708 card in both SD Express and UHS-I modes.

CrystalDiskMark [Fresh] Benchmarks

In the out-of-the-box case, the read and write speeds in SD Express mode match Silicon Motion's numbers - coming in at 890 MBps and 418 MBps respectively. The bump in the random access IOPS in multi-threaded scenarios indicates that the SM2708 controller is pretty much a NVMe SSD controller with the legacy UHS-I controller functions addedin another form. The UHS-I numbers are around the 100 MBps mark, as expected. In any case, UHS-I operation is for backwards compatibility, and performance is not much of a concern in that mode.

Sequential Access - fio Workload

One key aspect to note with SD Express moving forward is that it is going to be pretty much impossible for the cards to maintain their peak speeds beyond the initial SLC cache region. In effect, the claimed speeds are going to be only for burst scenarios. For most applications, that really doesn't matter as long as the card is capable of sustaining the maximum possible rate at which the camera it is used in dumps data. We use fio workloads to emulate typical camera recording conditions. We first run the workload on a fresh card, and also after simulating extended usage (covered in a later section). Instantaneous bandwidth numbers are graphed.

fio Sequential Workload [Fresh]

The reference design has a SLC cache of around 5.5 GB up to which write speeds of up to 375 MBps can be sustained. Beyond that, we have a 75 MBps region, and further on, 30 MBps. Once the controller has been subject to this traffic, the reads start off around 200 MBps before moving higher and higher and ending up at around 700 MBps. On the other hand, the SLC caching effect is a bit more difficult to track in the UHS-I mode. Write speeds vary from as low as 10 MBps to peaks around 62 MBps. Reads are consistent at 72 MBps.

Next Gen SD Card Review: SM2708 Simulating Extended Usage
Comments Locked


View All Comments

  • nandnandnand - Thursday, September 9, 2021 - link

    I've asked this question myself. The volume of an SD card is about 10x that of a microSD card. You would expect it to be able to fit 4x, maybe 8x as much NAND. The largest capacity for both is still stuck at 1 TB.

    The first thing to do would be to go to 2 TB since it would be compatible with SDXC readers. After that, what is the market for SDUC? Some smartphones are dropping the microSD slot as the internal storage is now "good enough". Videographers may want an 8 TB full-size SD card, probably with SD Express speeds to deal with 4K/8K/360-degree video capture. Maybe the card needs to be made out of aluminum for cooling.
  • meacupla - Thursday, September 9, 2021 - link

    If I had to guess, there is a limitation at the controller and/or reader.

    I doubt there is a problem with file format type, as exFAT has existed for a while now, with very high compatibility, and even if the format type was limited to FAT32, the maximum size would be 2TB
  • schuckles - Friday, September 10, 2021 - link

    I think that pretty much all designs for SD cards attempt to support micro SD as well. So in the end the bigger size is more about consumer use case than increased capacity.
  • nandnandnand - Friday, September 10, 2021 - link

    All of the devices that support a full sized SD card should be compatible with a microSD adapter card, and pretty much all microSD cards I've seen come with an adapter (I have at least 14 of them now).

    There's no technical reason for SD cards to not be available in higher capacities, it comes down to the nature of the market. Maybe 10-100 times more devices are compatible with microSD because of smartphones. I wouldn't be surprised if a 2 TB microSD card gets announced before a 2 TB full-sized SD.
  • Nevod - Saturday, September 11, 2021 - link

    Yes, there's no reason to develop additional functionality for full-size SD as market is much smaller than for microSD.

    Hopefully, SD Express readers may appear on notebooks and become a decent performance option to increase storage. That may provide a push to increase full-size card capacity, if price would be competitive with m.2 and USB options.
  • nandnandnand - Saturday, September 11, 2021 - link

    I am hopeful. I've seen SD card readers on even OEM desktops I've looked at lately, and controllers like this are available:

  • Xajel - Thursday, September 9, 2021 - link

    I think one major test is left out here, performance per watt.

    I mean for a portable device, power is crucial here, if at that speed the card can save the exact same file much faster than a non-SD 7.1 card and eventually consumes less power then it's a win for the portable device. They can use it and get faster while consuming less power because it needs less time to save the data.

    But if if the Performance/Watt was low then it's a problem, And maybe they will use a custom firmware to actually limit the performance to save power and stay within the required temperature. And the smaller the device the more crucial is to stay within low power/temp. Like mobile devices.

    Using microSD Express might as well save Android from getting rid of the expandable storage due to lack of good performance on current microSDs (very low IO performance).
  • nandnandnand - Thursday, September 9, 2021 - link

    "Using microSD Express might as well save Android from getting rid of the expandable storage due to lack of good performance on current microSDs (very low IO performance)."

    That would be nice, but I think the major manufacturers just want to get rid of it so they can sell you a phone with 1 TB UFS for $200 more.
  • meacupla - Thursday, September 9, 2021 - link

    I am surprised the controller is still using 28nm
    doesn't that take up a lot of space?
  • beginner99 - Friday, September 10, 2021 - link

    "We are bullish..." Dude this isn't some hipster crypto forum...

Log in

Don't have an account? Sign up now