USB 3.2 Gen 2x2 State of the Ecosystem Review: Where Does 20Gbps USB Stand in 2020?
by Ganesh T S on October 5, 2020 10:30 AM EST- Posted in
- Storage
- SSDs
- Western Digital
- SanDisk
- ASMedia
- USB 3.2 Gen 2x2
AnandTech DAS Suite - Benchmarking for Performance Consistency
Our testing methodology for DAS units takes into consideration the usual use-case for such devices. The most common usage scenario is transfer of large amounts of photos and videos to and from the unit. Other usage scenarios include the use of the DAS as a download or install location for games and importing files directly off the DAS into a multimedia editing program such as Adobe Photoshop. Some users may even opt to boot an OS off an external storage device.
The AnandTech DAS Suite tackles the first use-case. The evaluation involves processing three different workloads:
- Photos: 15.6 GB collection of 4320 photos (RAW as well as JPEGs) in 61 sub-folders
- Videos: 16.1 GB collection of 244 videos (MP4 as well as MOVs) in 6 sub-folders
- BR: 10.7 GB Blu-ray folder structure of the IDT Benchmark Blu-ray
Each workload's data set is first placed in a 25GB RAM drive, and a robocopy command is issued to transfer it to the DAS under test (formatted in NTFS). Upon completion of the transfer (write test), the contents from the DAS are read back into the RAM drive (read test). This process is repeated three times for each workload. Read and write speeds, as well as the time taken to complete each pass are recorded. Bandwidth for each data set is computed as the average of all three passes.
The write workloads see the Extreme PRO v2 come out slightly better than the WD_BLACK P50 using the Haswell testbed. On the reads, we see the Hades Canyon / eGFX enclosure turning out to be better - this can be attributed in part to the capabilities of the testbed itself, rather than the PCIe tunneling chain. In any case, we don't see any significant gulf in the numbers between the different units as long as the observations are made within the USB SuperSpeed 10Gbps or USB SuperSpeed 20Gbps host configurations.We also instrumented our evaluation scheme for determining performance consistency.
Performance Consistency
Aspects influencing the performance consistency include SLC caching and thermal throttling / firmware caps on access rates to avoid overheating. This is important for power users, as the last thing that they want to see when copying over 100s of GB of data is the transfer rate going down to USB 2.0 speeds.
In addition to tracking the instantaneous read and write speeds of the DAS when processing the AnandTech DAS Suite, the temperature of the drive was also recorded at the beginning and end of the processing. In earlier reviews, we used to track the temperature all through. However, we have observed that SMART read-outs for the temperature in NVMe SSDs using bridge chips end up negatively affecting the actual transfer rates. To avoid this problem, we have restricted ourselves to recording the temperature at either end of the actual workloads set. The graphs below present the recorded data.
| Performance Consistency and Thermal Characteristics |
 |
The first three sets of writes and reads correspond to the photos suite. A small gap (for the transfer of the video suite from the internal SSD to the RAM drive) is followed by three sets for the video suite. Another small RAM-drive transfer gap is followed by three sets for the Blu-ray folder. An important point to note here is that each of the first three blue and green areas correspond to 15.6 GB of writes and reads respectively. There is no issue with thermal throttling - even in the fastest configuration, both the P50 and Extreme PRO v2 show an increase of less than 5C after the workload processing. The P50 seems to have slightly better thermal performance for this workload set.
Facebook
Twitter
RSS
81 Comments
View All Comments
six_tymes - Monday, October 5, 2020 - link
spot on. thank you for posting truths.vol.2 - Monday, October 5, 2020 - link
When I read it, it sounded like the issue was with USB 3.X devices operating on a USB4.0 chipset. My assumption, and I don't think it was explicitly addressed, is that USB4.0 would be "full speed" per it's own specs. Of course, it wasn't explicitly addressed (from what I took away from this), so I phrased my comment as a question; "So wait for USB4 devices then?"repoman27 - Monday, October 5, 2020 - link
You’re reading is pretty much on the money, but the answer to your question is a bit trickier.The first USB4 hosts to hit the market will (probably) be Intel Tiger Lake based products which have integrated Thunderbolt 4 and support USB4 40Gbps. The USB4 spec requires backwards compatibility with USB 3.2, including both the Gen 1 (5Gbps) and Gen 2 (10Gbps) PHYs. It does not, however, require USB3 dual-lane operation (Gen 2x2, 20Gbps), and Intel has not included this optional feature in the controller integrated into Tiger Lake CPUs.
If Intel doesn’t have any plans for integrated USB 3.2 20Gbps, I fail to see how it becomes widespread, unless Apple and AMD both embrace it in their future chipsets. On the other hand, USB 3.2 devices are probably always going to be cheaper than Thunderbolt or USB4 gear. Paying the premium for a USB 3.2 20Gbps device today is somewhat questionable, unless you have a capable host or the performance difference compared to other products when connected to a 10Gbps port is worth it to you.
magreen - Monday, October 5, 2020 - link
Why will USB3.2 20Gbps devices always be cheaper than USB43 gear? It seems likely USB3.2 20 Gbps will be a niche product and without being produced in high volume, street price won't come down. USB4 might be initially expensive, but volume production and competition may bring street prices down to what we see today for USB3.2 Gen 1 5Gbps devices.repoman27 - Monday, October 5, 2020 - link
Because USB4 is essentially Thunderbolt, but even more complicated. It will always take way more silicon and way more power than USB3 on the same node. Thus it’s never going to be as cheap. Economies of scale can’t solve everything.vol.2 - Thursday, October 8, 2020 - link
Sounds about right. I don't have a sudden need for USB 3.2 dual lane. It seems like the best case for more parties to forgo support for it altogether and push USB 4.0. On a related note, USB 3.X has always been very buggy and unstable/unreliable for me, so hopefully 4.X fixes some of that.Meteor2 - Monday, October 26, 2020 - link
Not if you plug a USB4-20Gbps or a USB4-40Gbps SSD into them.YB1064 - Tuesday, October 6, 2020 - link
Why is the ASM2364 winning in every scenario compared to Thunderbolt, if TB offers higher bandwidth? Am I reading this incorrectly?WTF is this godawful nomenclature dumpster fire??? The idiots on the USB standards committee need to be flogged with extreme prejudice.
repoman27 - Tuesday, October 6, 2020 - link
The ASMedia ASM2364 is the PCIe NVMe to USB3 20Gbps bridge chip used by the devices being tested for this review.The ASMedia ASM3242 is the USB3 20Gbps host controller that was used for testing these USB3 20Gbps drives.
The Intel JHL6540 is a Thunderbolt controller which includes an integrated USB3 10Gbps host controller for interoperability with USB3 devices. This was used to test these USB3 drives while connected to a USB3 10Gbps host. The ASM3242 is winning because it supports twice the USB3 signaling rate as the JHL6540.
When connected to a Thunderbolt 3 device, the JHL6540 supports up to 40 Gbit/s. In some of the tests, the ASM3242 card was actually plugged into a Thunderbolt 3 enclosure and connected to the host PC via the JHL6540.
Googer - Tuesday, October 6, 2020 - link
It's kind of sad to think that USB is now faster than SATA. Will there ever be a SATA 4 for SSD and future bulk storage technologies?