The Intel SSD 660p SSD Review: QLC NAND Arrives For Consumer SSDs
by Billy Tallis on August 7, 2018 11:00 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 Intel SSD 660p delivers excellent random read performance from its SLC cache, coming in behind only the drives using Silicon Motion's higher-end controllers with Intel/Micron TLC. When reading data from a full drive where background processing is probably still ocurring, the performance is halved but remains slightly ahead of the Intel 600p.
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.
On the longer random read test, the 660p maintains its outstanding SLC cache performance that beats anything else currently on the market, but filling the drive it is slower than almost any other NVMe SSD - the exception being the Toshiba RC100 that doesn't use a large enough host memory buffer for the data range this test covers.
 |
|||||||||
| Power Efficiency in MB/s/W | Average Power in W | ||||||||
With the combination of lower power consumption afforded by its small NVMe controller and excellent random read performance, the Intel 660p earns the top efficiency score for this test. When it's slowed down by being full and still grinding away at background cleanup, its efficiency is much worse but still an improvement over the 600p.
 |
|||||||||
At high queue depths the 660p's random read speed begins to fall behind high-end NVMe SSDs, but it isn't significant until well beyond the queue depths that are relevant to real-world client/consumer usage patterns.
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.
The burst random write speed of the Intel SSD 660p is not record-setting, but it is comparable to high-end NVMe SSDs.
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, the 660p is slower than most high-end NVMe SSDs but still performs much better than the other entry-level NVMe drives or the SATA drive. After filling the drive (and consequently the SLC write cache), the performance drops below the SATA drive but is still more than twice as fast as the Toshiba RC100.
 |
|||||||||
| Power Efficiency in MB/s/W | Average Power in W | ||||||||
Power efficiency when performing random writes to a clean SLC cache is not quite the best we've measured, but it is far ahead of what the other low-end NVMe SSD drives or the Crucial MX500 SATA drive can manage
 |
|||||||||
After QD4 the 660p starts to show signs of filling the SLC write cache, which is a little bit sooner than expected given how large the SLC cache should be for the mostly-empty drive condition. The performance doesn't drop very far, showing that the idle time is enough for the drive to mostly keep up with flushing the SLC cache when the test is writing to the drive with a 50% duty cycle.
Facebook
Twitter
RSS
86 Comments
View All Comments
mapesdhs - Wednesday, August 8, 2018 - link
If you have quite literally "valuable info" then don't use a consumer SSD at all. Heck, damn the speed, you're far better with even a used 840 Pro. That's why I obtained one for this build I did, along with an SM951 for a scratch video drive:http://www.sgidepot.co.uk/misc/charitypc1.html
BurntMyBacon - Wednesday, August 8, 2018 - link
First point of interest is always have a backup plan. If information is valuable, don't rely on any single copy of it.As to your question of endurance, I don't think most personal use cases are likely to have an issue. If you have a professional workload, get a professional drive. The 840 Pro that mapesdhs keeps evangelizing is actually a pretty good option, though a Pro series (MLC) nvme drive will provide better performance while still providing endurance is the same ballpark as the 840Pro.
As to whether it will refresh the cell if powered on, I would expect most Samsung drive will, though it is not known whether
BurntMyBacon - Wednesday, August 8, 2018 - link
As to whether it will refresh if powered on, I don't believe that Samsung flash required the refresh cycle once the moved to 3D NAND with a larger feature size. That said, since QLC halves the voltage swing (and corresponding charge) vs TLC, it is likely that Samsung will need to do something to prevent voltage drift. This may not necessarily require active refreshing, though. It is not known (by me) whether this is a requirement for other manufacturer's 3DQLC NAND either.BurntMyBacon - Wednesday, August 8, 2018 - link
I get why they don't want an edit feature, but would it really hurt if they added a time limited recall type edit feature for when you fat thumb a hot key that posts your unfinished message before you are done with it. Maybe give you five minutes after a post initiate the edit to catch typos or grammar issues. It wouldn't really be enough to alter a conversation as it is unlikely that others will have responded within this time frame.AbRASiON - Tuesday, August 7, 2018 - link
Considering the abysmal performance of this thing, I think you really need a $/GB chart on the page and it would be nice to put in a very fast, modern hard drive. Something huge and 7200RPM with a lot of cache on it.Just to put it in perspective, because as it stands, wow this thing looks terrible. I expect VERY cheap prices if they're gonna run like this.
Oxford Guy - Tuesday, August 7, 2018 - link
No matter how terrible QLC is it is going to succeed in the market because consumers respond well to big and cheap.So, I think one interesting question is going to be how much disguising there will be of products having QLC. Microcenter, for instance, is apparently selling a TLC Inland drive, calling it MLC.
piroroadkill - Wednesday, August 8, 2018 - link
That's how I want QLC drives to be compared - to the best hard drives people might actually buy today to store their games on, for example.I'd love a cheap and large 4TB drive for my games, but it has to be both much faster than the HDD setup I use for games (2× 2TB 3.5" Seagate Hybrid drives in RAID0) and not too far off the same price.
zodiacfml - Wednesday, August 8, 2018 - link
Impressive performance. Easily beats my SATA 850 EVO in performance and twice the capacity I bought last December for the same price.There should be no reason for notebook manufacturers to settle for HDD except the cheapest laptops.
mapesdhs - Wednesday, August 8, 2018 - link
Given the 850 EVO's strong reliability reputation though, I wouldn't be overly eager to recommend this new QLC model for anyone wanting a decent degree of confidence that their data is safe. But then, most consumers don't have backup strategies anyway. :DSpunjji - Wednesday, August 8, 2018 - link
If you want safe data, make regular backups. Anything else is a false sense of security!