Synthetic Benchmarks - ATTO and CrystalDiskMark

Benchmarks such as ATTO and CrystalDiskMark help provide a quick look at the performance of the direct-attached storage device. The results translate to the instantaneous performance numbers that consumers can expect for specific workloads, but do not account for changes in behavior when the unit is subject to long-term conditioning and/or thermal throttling. Yet another use of these synthetic benchmarks is the ability to gather information regarding support for specific storage device features that affect performance.

Silicon Motion claims read and write speeds of 2100 and 2000 MBps respectively for specific access traces. The ATTO benchmarks provided below deliver close results. ATTO benchmarking is restricted to a single configuration in terms of queue depth, and is only representative of a small sub-set of real-world workloads. It does allow the visualization of change in transfer rates as the I/O size changes, with optimal performance being reached around 512 KB for writes and 4MB for reads with a queue depth of 4.

ATTO Benchmarks
TOP: BOTTOM:

CrystalDiskMark. for example, uses four different access traces for reads and writes over a configurable region size. Two of the traces are sequential accesses, while two are 4K random accesses. Internally, CrystalDiskMark uses the Microsoft DiskSpd storage testing tool. The 'Seq128K Q32T1' sequential traces use 128K block size with a queue depth of 32 from a single thread, while the '4K Q32T16' one does random 4K accesses with the same queue configuration, but from multiple threads. The 'Seq1M' traces use a 1MiB block size. The plain 'Rnd4K' one uses only a single queue and single thread . Comparing the '4K Q32T16' and '4K Q1T1' numbers can quickly tell us whether the storage device supports NCQ (native command queuing) / UASP (USB-attached SCSI protocol). If the numbers for the two access traces are in the same ballpark, NCQ / UASP is not supported. This assumes that the host port / drivers on the PC support UASP.

CrystalDiskMark Benchmarks
TOP: BOTTOM:

For sequential accesses, the read speeds of the SM2320 reference design match / surpass the bridge-based solutions, while the write speeds are slightly behind (around 1800 MBps against 2100 MBps). In the random access workloads, the DRAM-less nature of the UFD controller result in performance loss for high-queue depth operations. At low queue depths, the write performance of the UFD controller matches the bridge-based solutions with high-end NVMe SSDs.

Introduction AnandTech DAS Suite - Benchmarking for Performance Consistency
Comments Locked

18 Comments

View All Comments

  • Bik - Thursday, September 16, 2021 - link

    these would be good to use in laptop with limited power budget
  • meacupla - Thursday, September 16, 2021 - link

    It would be nice to see an NVMe SSD that has even more power efficiency than a P31, for sure.
  • Samus - Friday, September 17, 2021 - link

    What I find amazing is how fast and power efficient this thing is for having a USB-C connector. Getting that performance out of that many conductors is just amazing.
  • bernstein - Thursday, September 16, 2021 - link

    IMHO (re)using (old) m2 nvme/sata ssd's in a external case (usb-bridge) is in almost all cases the cheaper/more flexible solution. sure it's a tiny bit bigger, more-expensive & less power-efficient... but for single external drive these are almost always negelgible.
  • meacupla - Thursday, September 16, 2021 - link

    IDK about that.
    This XS2000 only has 500GB, 1TB and 2TB models, and I would think most people will be upgrading TO that size, rather than upgrading FROM that size.
    When you add in the cost of an USB 3.2 Gen 2x2 external case, things end up not being cheap.

    I am looking at the prices from my local retailer, and the price for the 500GB and 1TB model XS2000 is, in fact, better than buying separately.
    For the 2TB model, buying separately is cheaper.
    For the 500GB and 1TB model, it's only cheaper if I opt for an NVMe enclosure that is not capable of USB3.2 Gen 2x2
  • Drkrieger01 - Thursday, September 16, 2021 - link

    I imagine we'll start seeing the return of some decent ultra highs speed USB sticks with these controllers now available
  • Wereweeb - Thursday, September 16, 2021 - link

    "The lack of any thermal solution (note that we are evaluating a bare PCB here) means that we can't make any comments on the recorded temperature." It's worrying that they sent you a bare PCB, instead of the product that costumers will buy, when they know y'all are likely to do the most throughout analysis of the device.

    I'd imagine that it's hard to fuck up with such an elegant and simple design, but you never know - Kingston is the one who managed to innovate in the creation of LED-fried NAND.
  • DigitalFreak - Thursday, September 16, 2021 - link

    Do laptops outside of TigerLake even have USB 3.2 2x2 support? Let alone desktops.
  • timecop1818 - Friday, September 17, 2021 - link

    I don't think even tiger lake has native USB 2x2 without adding a bridge chip
  • DigitalFreak - Friday, September 17, 2021 - link

    I was thinking Thunderbolt 4 / USB 4 is backwards compatible with 2x2.

Log in

Don't have an account? Sign up now