The Intel Optane SSD 900p 480GB Review: Diving Deeper Into 3D XPoint
by Billy Tallis on December 15, 2017 12:15 PM ESTAnandTech Storage Bench - Light
Our Light storage test has relatively more sequential accesses and lower queue depths than The Destroyer or the Heavy test, and it's by far the shortest test overall. It's based largely on applications that aren't highly dependent on storage performance, so this is a test more of application launch times and file load times. This test can be seen as the sum of all the little delays in daily usage, but with the idle times trimmed to 25ms it takes less than half an hour to run. Details of the Light test can be found here. As with the ATSB Heavy test, this test is run with the drive both freshly erased and empty, and after filling the drive with sequential writes.
The Light test shows much greater differences between full and empty drive performance, for both flash SSDs and for the rather variable 280GB Optane SSD 900p. The 480GB model shows less variation in its average data rater between the full and empty runs. Overall, the Optane SSDs outperform a full flash-based SSD but are unimpressive compared to a fresh out of the box flash-based SSD.
Aside from the different behavior of full vs empty, the average and 99th percentile latency scores of the Optane SSDs are not too interesting. The best-case performance is not quite as fast as the best from a flash based SSD, but once the flash drive is slowed down by being full, the Optane SSD shows a meaningful latency advantage.
The average read latency of the Optane SSDs on the Light test is not hurt by filling the drive, giving it much better latency in the worst case scenario than any flash-based SSD. When the Light test is run on freshly-erased drives, the Optane SSD's average read latency is about the same as the best flash-based drives. Neither Optane SSD sets a record for average write latency, and Samsung's fastest NVMe drives have a clear advantage.
As with the average read latency, the 99th percentile read latency of the Optane SSDs on the Light test only impresses when compared to the performance of flash-based SSDs in unfavorable conditions like being completely full. Otherwise, the Samsung PM981 performs just as well, and the 960 PRO isn't far behind. The 99th percentile write latency of the Optane SSDs is clearly worse than Samsung's top NVMe SSDs.
The Optane SSD 900p again requires much more energy than most NVMe SSDs, and the larger Optane drive requires significantly more power—three times as much as the most efficient NVMe SSD we've tested.
Facebook
Twitter
RSS
69 Comments
View All Comments
thestryker - Friday, December 15, 2017 - link
I'm curious if the power consumption on the u.2 version would be any different.Any chances of Intel hooking AnandTech up with a u.2 version? I know the storage bench system doesn't have u.2, but I'm sure there's a system around which does. I believe there's also a sku with m.2 to u.2 adapter also.
Billy Tallis - Friday, December 15, 2017 - link
The U.2 drive uses the same 12V supply as the add-in card, unlike SATA SSDs that use 5V. Any differences in power consumption would probably be minor variations due to different operating temperature.CheapSushi - Friday, December 15, 2017 - link
It's been so satisfying to see all the Optane haters, dismissers, general naysayers and "meh, ___ is good enuff" crowd, who pretend to be enthusiasts, finally backtracking on their comments about it. Good times.tricomp - Saturday, December 16, 2017 - link
Can't wait seeing my customer's jaws dropping... I build heavy multi-core workstations for 3D and post production. Using 480 jet like this for the OS is something they will truly appreciatemapesdhs - Monday, December 18, 2017 - link
Responsiveness, etc. with pro apps wasn't tested here. Where's the evidence it would be any better than a 960 Pro? I'd be more interested in a Puget Systems review with real world situations.tricomp - Monday, December 18, 2017 - link
I agree with mapesdhs. The main strength of this unit should be tested and compared, not to mention - mentioned - in an article called "deeper diving into 3D Xpoint"lilmoe - Saturday, December 16, 2017 - link
Pardon the ignorance, but is can XPoint memory packages run on lower voltages, or is operation dependent on a single constant voltage setting? Are there any plans for low-power based XPoint like LPDDR or DDRL? If so, I wonder how much performance and latency would degrade.As it is, these will never be able to compete with NAND in terms of power. Lots of users (like) me want this kind of power on the go. Samsung and others are simply NOT trying anymore. I've REALLY delayed purchasing a mobile workstation till these technologies get sorted out and it's clear for me what type of expansion I'll need for compatibility.
wanderer66 - Saturday, December 16, 2017 - link
There won't be mainstream memory modules until late next year, based on what I've read. I wouldn't count on seeing mobile workstation/laptop capability until 2019 or 2020, and that depends on several things: 2nd or 3rd gen optane modules using less power (due to die shrinkage), and a reference design from Intel that supports them on that kind of motherboard. Even then count on them consuming 10-15 watts for a loaded configuration.wanderer66 - Saturday, December 16, 2017 - link
Two things: This is first gen Optane architecture. *First Gen* sisters and brothers... In the next several years, performance will evolve as the controllers improve (greater parallelism and other performance tweaks), power usage will decrease as process optimization and die shrinkage improves, and the design moves beyond being able to use NVMe as the interface, which it will.Second, 550k iops. That's mind-blowing, really. This may not be hugely important to single-user workstations, but in the hosting/cloud markets, this is one of the largest leaps that can be made..
In five years time, Optane will be to flash SSDs what flash SSDs are to HDDs today.
djayjp - Sunday, December 17, 2017 - link
Would *really* like to see real world testing, not traces. In such tests no difference is ever apparent between the bargain basement SSDs and the absolute top tier, thus the current tests AT uses are nonsense.