The Intel SSD 660p SSD Review: QLC NAND Arrives For Consumer SSDs
by Billy Tallis on August 7, 2018 11:00 AM ESTAnandTech Storage Bench - Heavy
Our Heavy storage benchmark is proportionally more write-heavy than The Destroyer, but much shorter overall. The total writes in the Heavy test aren't enough to fill the drive, so performance never drops down to steady state. This test is far more representative of a power user's day to day usage, and is heavily influenced by the drive's peak performance. The Heavy workload test details can be found here. This test is run twice, once on a freshly erased drive and once after filling the drive with sequential writes.
When the Heavy test is run on an empty Intel SSD 660p, the test is able to operate almost entirely within the large SLC cache and the average data rate is competitive with many high-end NVMe SSDs. When the drive is full and the SLC cache is small, the low performance of the QLC NAND shows through with an average data rate that is slower than the 600p or Crucial MX500, but still far faster than a mechanical hard drive.
The average and 99th percentile latency scores of the 660p on the empty-drive test run are clearly high-end; the use of a four-channel controller doesn't seem to be holding back the performance of the SLC cache. The full-drive latency scores are an order of magnitude higher and worse than other SSDs of comparable capacity, but not worse than some of the slowest low-capacity TLC drives we've tested.
The average read latency of the Intel 660p on the Heavy test is about 2.5x higher for the full-drive test run than when the test is run on a freshly-erased drive. Neither score is unprecedented for a NVMe drive, and it's not quite the largest disparity we've seen between full and empty performance. The average write latency is where the 660p suffers most from being full, with latency that's about 60% higher than the already-slow 600p.
The 99th percentile read latency scores from the 660p are fine for a low-end NVMe drive, and close to high-end for the empty-drive test run that is mostly using the SLC cache. The 99th percentile write latency is similarly great when using the SLC cache, but almost 20 times worse when the drive is full. This is pretty bad in comparison to other current-generation NVMe drives or mainstream SATA drives, but is actually slightly better than the Intel 600p's best case for 99th percentile write latency.
The Intel SSD 660p shows above average power efficiency on the Heavy test, by NVMe standards. Even the full-drive test run energy usage is lower than several high-end drives.
Facebook
Twitter
RSS
86 Comments
View All Comments
dromoxen - Friday, August 10, 2018 - link
You would hope these things would have even larger dram buffers than tlc. I will pass on these 1st gen and stick with with HD.Has intel stopped making ssd controllers?
To do some tests , write endurance, why not cool down the m.2 nand to LN2 temps, I'm sure debauer has some pots and equipment. I expect these will be even cheaper by jan 19
tomatotree - Tuesday, August 14, 2018 - link
Intel makes their own controllers for all their enterprise drives, and all 3DXP drives, but for consumer NAND drives they use 3rd party controllers with customized firmware.As for LN2 cooling, what would that show? That the drive might fail if you use it in a temperature range way out of spec?
351Cleveland - Monday, August 20, 2018 - link
I’m confused. Why would I buy this over, say, an MX500 (my default go-to)? This thing is a dog in every way. How can Anandtech recommend something they admit is flawed?icebox - Thursday, December 6, 2018 - link
I don't understand why everybody fusses about retention and endurance so much. Do you really buy ssd's to leave them on a shelf for months or years? Retention ? If it dies during warranty you exchange it. If it dies after it then it's probably slow and small in comparison with what's available than.You do have backups, right? Because no review or test or battery of tests won't guarantee that *your drive* won't die.
BTW that's the only way I saw ssd's die - it works perfectly and after a reboot it's gone, not detected by the system.
icebox - Thursday, December 6, 2018 - link
The day has come when choosing storage is 4 tiered.You have fast nvme, slow nvme, sata ssd's and traditional hdd's. At least I kicked hdd's off my desktop. I have a samsung nvme for boot and applications and sata ssd's for media and photos. Now I'm looking of replacing those with the 2tb 660p and moving those to the nas for bulk storage.
southleft - Tuesday, May 14, 2019 - link
It would be very helpful if the review would show just how full the drive can be before performance degrades significantly. Clearly, when the drive is "full" its performance sucks, but can we expect good performance when the drive is half-full, two-thirds full, three-quarters full? C'mo, Anandtech, tell us something USEFUL here!boozed - Monday, December 30, 2019 - link
There's something wrong with the 970 EVO's results on page 3. Full performance exceeds empty performance. This is not reflected in the 970 EVO review.