The ADATA XPG SX950 480GB SSD Review: In Search of Premium
by Billy Tallis on October 9, 2017 8:00 AM ESTRandom Read Performance
Our first test of random read performance uses very short bursts of operations issued one at a time with no queuing. The drives are given enough idle time between bursts to yield an overall duty cycle of 20%, so thermal throttling is impossible. Each burst consists of a total of 32MB of 4kB random reads, from a 16GB span of the disk. The total data read is 1GB.
The short-burst QD1 random read speed of the ADATA XPG SX950 is good, though Samsung still has a clear lead. The SX950 is 16% faster than the Crucial BX300 that uses the same NAND and controller.
Our sustained random read performance is similar to the random read test from our 2015 test suite: queue depths from 1 to 32 are tested, and the average performance and power efficiency across QD1, QD2 and QD4 are reported as the primary scores. Each queue depth is tested for one minute or 32GB of data transferred, whichever is shorter. After each queue depth is tested, the drive is given up to one minute to cool off so that the higher queue depths are unlikely to be affected by accumulated heat build-up. The individual read operations are again 4kB, and cover a 64GB span of the drive.
With a longer test and higher queue depths, the ADATA SX950's standing drops somewhat, but it still outperforms most TLC SSDs and the Crucial BX300.
The power efficiency of the SX950 during random reads is decent but not outstanding. The planar MLC-based PNY CS2211 beats the SX950 on both performance and power efficiency, but otherwise the SX950 is only beat by a few other 3D NAND SSDs.
 |
|||||||||
For an MLC-based SSD, the ADATA SX950 does a poor job of scaling up random read performance with higher queue depths. Its QD1 performance is fine, but by QD8 it's lagging behind many of its competitors. The Crucial BX300 is marginally slower until QD32, where the SX950's performance starts to level off while the BX300 gets very close to the peak speeds reached by the best SATA SSDs.
Random Write Performance
Our test of random write burst performance is structured similarly to the random read burst test, but each burst is only 4MB and the total test length is 128MB. The 4kB random write operations are distributed over a 16GB span of the drive, and the operations are issued one at a time with no queuing.
After seeing clear indicators from the ATSB tests that the ADATA SX950 is very aggressive with SLC write caching, it's good to see that the QD1 burst random write performance is near the top of the charts.
As with the sustained random read test, our sustained 4kB random write test runs for up to one minute or 32GB per queue depth, covering a 64GB span of the drive and giving the drive up to 1 minute of idle time between queue depths to allow for write caches to be flushed and for the drive to cool down.
On the longer random write test with higher queue depths included, the ADATA XPG SX950's random write score is unimpressive: barely faster than the TLC-based ADATA SU800 and well behind the Crucial and Samsung drives.
In spite of mediocre performance on the longer random write test, the SX950 delivers great power efficiency, in second place only slightly behind the Crucial MX300.
 |
|||||||||
The SX950's random write speed mostly levels off in the second half of the test as queue depths grow beyond 4, and even at QD32 the SX950 is not really close to saturating the SATA bus. But at QD1 and QD2, its performance is as good as any SATA drive and its power consumption is unbeatable.
Facebook
Twitter
RSS
45 Comments
View All Comments
meacupla - Monday, October 9, 2017 - link
ADATA's pricing of their lower end is usually in line with the competition. Or, at least, the last drive I bought from them was.This one... not so much
KAlmquist - Monday, October 9, 2017 - link
If the intention is for these drives to sell at well below MSRP, Adata is not getting off to a good start. Amazon and B&H Photo are both pricing the 480GB model $20 higher than the MSRP, and Newegg is not selling it at all. My guess is that something tipped the retailers off to the fact that there is not going to be a lot of demand for this product, so they either went for a high markup (to compensate for the cost of holding a low turnover item in stock), or in the case of Newegg, decided to pass on it entirely.I recently bought a Samsung 850 Pro, which proves that there is still at least one person who is (stupid? gullible? bat shit crazy?) enough to pay up for a premium SATA SSD. :-) With a premium SATA SSD, you are paying for:
1) Consistent performance. For example, in the Anandtech Storage Bench light test, the ADATA drive does well if the drive is empty, but performance plummets if the drive is full. The Samsung 850 Pro performs almost identically regardless of whether the drive is full or empty.
2) Reliability. I have no reason to believe the Adata drive is unreliable, but the Samsung 850 Pro has a 10 year warranty and, more important, a long track record in the field. So the 850 Pro wins this category as well.
IndianaKrom - Monday, October 9, 2017 - link
A couple years ago when I picked up an 850 pro/1 TB, it was at the time the best SATA SSD. Today it is still the best SATA SSD, and it will probably always be. At this stage I would be surprised if anyone manages to extract any more performance out of SATA than what an 850 Pro can do._mb - Monday, October 9, 2017 - link
Where is the "Performance Consistency" test?I hope you guys haven't stopped doing that one as that test is the most interesting one and sets you guys apart from other reviewers which don't do that.
Billy Tallis - Monday, October 9, 2017 - link
The performance consistency test will be reintroduced soon. Since it was the least relevant to real-world desktop usage and the most likely to kill drives, it's been the lowest priority to run on the new 2017 testbed. Now that I'm pretty much done running all my drives through the 2017 test suite, I'll start going back and running the new performance consistency test on them. Those results will probably start being included in the SSD reviews in November, and they'll be added to the Bench database as they're available.Maleorderbride - Monday, October 9, 2017 - link
I realize this is not on you Billy, but why is the Mushkin Enhanced Reactor series not part of the 2017 SSD bench? That series is one of only four that someone might actually purchase knowingly.xype - Monday, October 9, 2017 - link
So, at which point will it become a waste of time to review SSDs? Unless such a review only takes 15 minutes, I’d assume there’s plenty of hardware where the conclusions is not a simple "Get a Samsung" >90% of the time — or am I being too optimistic?RaistlinZ - Monday, October 9, 2017 - link
Q: "So, at which point will it become a waste of time to review SSDs?"A: 2016
xype - Wednesday, October 11, 2017 - link
Yeah :-/jabber - Monday, October 9, 2017 - link
I don't care. The issue is that SATAIII is saturated and all we need now are reliable mainstream hum drum SSD drives for a cheap price. There is nothing else left to achieve on SATAIII. It's like RAM FFS it's all within a few % whether you spend $100 or $200. They get away with it by adding pointless crap like RGB. I bet by XMAS we'll see SATAIII SSD drives with built in RGB on the edges. Anything to cover up and distract from the fact they are no longer anything special and all the same for day to day purposes.