The Samsung 960 EVO (1TB) Review
by Billy Tallis on November 15, 2016 10:00 AM ESTRandom Read Performance
The random read test requests 4kB blocks and tests queue depths ranging from 1 to 32. The queue depth is doubled every three minutes, for a total test duration of 18 minutes. The test spans the entire drive, which is filled before the test starts. The primary score we report is an average of performances at queue depths 1, 2 and 4, as client usage typically consists mostly of low queue depth operations.
It is unsurprising to see that the TLC-based 960 EVO has slower random read speeds than the MLC-based 950 Pro and 960 Pro, but the 960 EVO still manages to be faster than all the non-Samsung drives.
The 960 EVO's power consumption is essentially the same as Samsung's other drives, which puts it at an efficiency disadvantage to their MLC PCIe SSDs but more efficient than all the lower-performing drives.
 |
|||||||||
As with Samsung's other SSDs, random read speed scales with queue depth until hitting a limit at QD16.
Random Write Performance
The random write test writes 4kB blocks and tests queue depths ranging from 1 to 32. The queue depth is doubled every three minutes, for a total test duration of 18 minutes. The test is limited to a 16GB portion of the drive, and the drive is empty save for the 16GB test file. The primary score we report is an average of performances at queue depths 1, 2 and 4, as client usage typically consists mostly of low queue depth operations.
The Samsung 960 EVO's random write speed is essentially tied with the 960 Pro and the OCZ RD400A, while the Intel 750 holds on to a comfortable lead.
The 960 EVO is not as power efficient as the 960 Pro, but it is still far better than everything else.
 |
|||||||||
The scaling behavior of the 960 EVO is essentially the same as the 960 Pro: full performance is reached at QD4, and there's no indication of any severe thermal throttling.
Facebook
Twitter
RSS
87 Comments
View All Comments
ddriver - Tuesday, November 15, 2016 - link
TOMs has tested it. As expected, it is marginally slower.Bensant - Tuesday, November 15, 2016 - link
Just received my 960 Pro today, installed and everything is working properly apart from the Samsung driver. Have spent the last 40mins trying to locate the NVME 2.0 driver to no avail. Would anyone have a link to it yet? Or is it still unavailable and coming with the new magician software at the end of the month?XabanakFanatik - Wednesday, November 16, 2016 - link
Yeah, you should be able to use the version 1.0 driver until they finally get around to releasing the new one with Magician 5.0.What capacity pro did you buy that you actually received this early? 512GB?
Bensant - Wednesday, November 16, 2016 - link
Idk that's a bit funny then, the original drivers (For the 950 pro) failed to detect my 960 pro for some reason. It's been installed and is booting as my OS drive too, just using the Microsoft driver!And yeah, was the 512GB that I ordered, couldn't exactly justify getting the higher capacities after just spending more then $4000 on a new triple monitor setup haha
jeffbui - Wednesday, November 16, 2016 - link
Benchmarks are great but where are the real world measurements? How will this affect me vs the other drives?jeffbui - Wednesday, November 16, 2016 - link
http://www.anandtech.com/show/2614Look at all the real world measurements: Game load times, application load times, multitasking performance,
Billy Tallis - Thursday, November 17, 2016 - link
Kristian did a good job of explaining why we rely on playing back traces of real-world I/O rather than re-running the applications themselves: http://www.anandtech.com/show/8979/samsung-sm951-5...It has only gotten more impractical to build a valid and reproducible application benchmark suite, to the point that any such system would have to be cut off from the Internet to prevent automatic updates from changing the conditions of the test.
From the perspective of the SSD, our ATSB trace-based tests present a nearly identical workload to running the applications themselves, but with far better reproducibility. It might be possible to improve how we present the results of those three tests, but I do not believe that splitting those traces into a dozen different scenarios would make it any easier to come to a purchasing decision than by considering the measurements we currently report.
RaistlinZ - Wednesday, November 16, 2016 - link
I'm currently using an 850 EVO on my ASUS X99 Pro motherboard. Will my mobo fully support the 960? Also, is it better to do a fresh Windows 10 install on an NVMe drive, or does cloning still work well?ghojezz - Wednesday, November 16, 2016 - link
I don't understand, anandtech's using Z97 Deluxe for benchmark but it only supports 10Gbps M.2 Bandwidth, right? So theoretically, you didn't push 960 to its max performance. Anyone care to explain?Billy Tallis - Thursday, November 17, 2016 - link
The motherboard's built-in M.2 slot is not used, because it does not permit measuring power consumption. M.2 PCIe drives are connected through an adapter and riser card to the primary PCIe 3.0 x16 slot, which will continue to be sufficient until PCIe 4 SSDs and motherboards arrive.