Not long ago, you might have heard me grumbling about the aggressive onslaught of QLC drives and pining for the reassuring embrace of TLC NAND. Samsung must have been listening in, because today the company is launching a new, PCIe, TLC V-NAND SSD. Feast your eyes on the Samsung 970 EVO Plus 500 GB.
The 970 EVO Plus doesn’t offer us a lot to talk about that we didn’t already cover when we first got our hands on the 970 EVO. PCIe, NVMe, and M.2? Check. Intelligent TurboWrite? Check. Copper-film, heat-spreading sticker on the underside? Check. Nickel-coated Phoenix controller? Check.
The substantive difference between the 970 EVO and the 970 EVO Plus is the flash. The 970 EVO Plus upgrades to Samsung’s fifth-generation V-NAND, which the company started mass-producing last summer. Fourth-generation V-NAND was stacked 64 layers high, and the new flash increases the layer count by about 50%. Samsung is keeping quiet about exactly how many layers make up the stuff, saying only that it’s “more than 90 layers.” We think 96 seems like a safe bet, but we couldn’t get a definitive answer from company reps.
|Samsung 970 EVO Plus|
|Capacity||Max sequential (MB/s)||Max random (IOps)||Price|
Aside from the 500-GB sample we have on hand, the 970 EVO Plus is also launching in 250-GB and 1-TB capacities. An additional 2-TB version is in the works, due to be released in April. Samsung’s claiming higher speeds across the board for these revamped drives. Unfortunately, the original 970 EVO we tested was a 1-TB unit, so we won’t be able to do a true apples-to-apples comparison of the old and the new. Speaking of the old, the 970 EVO is now officially discontinued, fully handing over the reigns to the 970 EVO Plus.
Beneath its label, the 970 EVO Plus is scarcely distinguishable from the 970 EVO. It’s a single-sided drive with two V-NAND packages rubbing elbows with a 512MB DRAM cache and a nickel-adorned Phoenix controller. Samsung calls the Phoenix “newly enhanced,” but the specific form those enhancements might take remains a mystery, aside from the obvious fifth-generation V-NAND compatibility.
The endurance ratings haven’t changed from those of the 970 EVO, but its specs were already robust. The 500-GB 970 EVO Plus can take 300 TB written, and Samsung backs the drive with a five-year warranty. And just like the 970 EVO, the 970 EVO Plus protects your secrets with hardware-accelerated encryption.
The biggest change that the 970 EVO Plus brings seems to be launch price. In a rare move for an SSD manufacturer, Samsung has set suggested prices for the 970 EVO Plus drives that are in line with market realities. So instead of the $230 launch price of last year’s 970 EVO 500 GB, the 970 EVO Plus 500 GB gets a much humbler $130 sticker.
Out with the old, in with the new. Our wallets are grateful for Samsung’s new pricing strategy, but the new drive has to prove that it’s worthy of the EVO name.
IOMeter — Sequential and random performance
IOMeter fuels much of our latest storage test suite, including our sequential and random I/O tests. These tests are run across the full capacity of the drive at two queue depths. The QD1 tests simulate a single thread, while the QD4 results emulate a more demanding desktop workload. For perspective, 87% of the requests in our old DriveBench 2.0 trace of real-world desktop activity have a queue depth of four or less. Clicking the buttons below the graphs switches between results charted at the different queue depths. Our sequential tests use a relatively large 128-KB block size.
The Samsung 970 EVO Plus starts off strong, with the highest sequential read and write speeds of any 500-GB class drive in our test set at QD1. Its writes are particularly noteworthy, pulling far ahead of the 760P and SX8200. At QD4, it even breaks the 3000 MB/s barrier and surpasses the 970 EVO 1 TB. Quite an auspicious start!
The 970 EVO Plus posts the fastest random read response times we’ve seen yet, narrowly edging out the 970 EVO 1 TB and SX8200. Its random write response times aren’t as impressive, but they’re respectable nonetheless.
The 970 EVO Plus hasn’t let us down yet. It’s faster than similarly sized PCIe drives and even trades blows with larger ones at times. Time for more rigorous tests.
Sustained and scaling I/O rates
Our sustained IOMeter test hammers drives with 4-KB random writes for 30 minutes straight. It uses a queue depth of 32, a setting that should result in higher speeds that saturate each drive’s overprovisioned area more quickly. This lengthy—and heavy—workload isn’t indicative of typical PC use, but it provides a sense of how the drives react when they’re pushed to the brink.
We’re reporting IOPS rather than response times for these tests. Click the buttons below the graph to switch between SSDs.
The Samsung 970 EVO Plus 500 GB peaks at a rate right in the neighborhood of the 970 EVO 1 TB’s peak, which has held the record so far in this iteration of our test data. The 970 EVO Plus’ steady-state rate looks to be much lower, though.
TurboWrite magic works about as well in the 500-GB drive as in the older 1-TB drive, yielding those satisfyingly high peaks. But once pseudo-SLC caches are exhausted, our 970 EVO Plus can’t compete with the larger drive. It’s still just as fast as the SX8200 480 GB, though, which is no small feat.
Our final IOMeter test examines performance scaling across a broad range of queue depths. We ramp all the way up to a queue depth of 128. Don’t expect AHCI-based drives to scale past 32, though—that’s the maximum depth of their native command queues.
For this test, we use a database access pattern comprising 66% reads and 33% writes, all of which are random. The test runs after 30 minutes of continuous random writes that put the drive in a simulated used state. Click the buttons below the graph to switch between the different drives. Note that each drive uses a different scale for IOPS to allow us to view the shape of its curves.
Samsung’s PCIe drives have always offered graceful scaling into the higher queue depths, and the 970 EVO Plus is no exception. Transaction rates climb steadily to QD64 before leveling off.
Adata’s XPG SX8200 480 GB seems to ramp up a little more quickly than the 970 EVO Plus does, but the drives arrive in the same ballpark by QD64. By comparison, Intel’s 760P barely scales at all.
None of our IOMeter tests have exposed any real flaws in the 970 EVO Plus. It seems so far that Samsung’s done a bang-up job with this one. It’s doubtful that our real-world tests will provide any substantial challenge for the drive, but let’s dive right into RoboBench and find out.
TR RoboBench — Real-world transfers
RoboBench trades synthetic tests with random data for real-world transfers with a range of file types. Developed by our in-house coder, Bruno “morphine” Ferreira, this benchmark relies on the multi-threaded robocopy command build into Windows. We copy files to and from a wicked-fast RAM disk to measure read and write performance. We also cut the RAM disk out of the loop for a copy test that transfers the files to a different location on the SSD.
Robocopy uses eight threads by default, and we’ve also run it with a single thread. Our results are split between two file sets, whose vital statistics are detailed below. The compressibility percentage is based on the size of the file set after it’s been crunched by 7-Zip.
|Number of files||Average file size||Total size||Compressibility|
|Media||459||21.4 MB||9.58 GB||0.8%|
|Work||84,652||48.0 KB||3.87 GB||59%|
RoboBench’s write and copy tests run after the drives have been put into a simulated used state with 30 minutes of 4KB random writes. The pre-conditioning process is scripted, as is the rest of the test, ensuring that drives have the same amount of time to recover.
The media set is made up of large movie files, high-bitrate MP3s, and 18-MP RAW and JPG images. There are only a few hundred files in total, and the data set isn’t amenable to compression. The work set comprises loads of TR files, including documents, spreadsheets, and web-optimized images. It also includes a stack of programming-related files associated with our old Mozilla compiling test and the Visual Studio test on the next page. The average file size is measured in kilobytes rather than megabytes, and the files are mostly compressible.
Let’s take a look at the media set first. The buttons switch between read, write, and copy results.
The Samsung 970 EVO Plus snags new records in both the read and copy tests. It’s handily outclassed by the SX8200 480 GB in the write tests, though. You can’t win ’em all, but four out of six ain’t bad!
Forget four out of six, in the work set it becomes five out of six. The 970 EVO Plus’ much-improved random speeds carry it to victory in the write tests this time.
If IOMeter was a success for this drive, RoboBench has been nothing short of a triumph. The 970 EVO Plus 500 GB posts some of the fastest speeds we’ve ever seen. Our next and last page of tests will run with the drive serving as a boot device.
Until now, all of our tests have been conducted with the SSDs connected as secondary storage. This next batch uses them as system drives.
We’ll start with boot times measured two ways. The bare test depicts the time between hitting the power button and reaching the Windows desktop, while the loaded test adds the time needed to load four applications—Avidemux, LibreOffice, GIMP, and Visual Studio—automatically from the startup folder. These tests cover the entire boot process, including drive initialization.
The Samsung 970 EVO Plus lands near the top of both charts. Its loaded boot time is the fastest of any drive other than the RC100 480 GB, which perplexingly secured a big win in this test despite a poor performance throughout the rest of the test suite.
Next, we’ll tackle load times with two sets of tests. The first group focuses on the time required to load larger files in a collection of desktop applications. We open a 790-MB 4K video in Avidemux, a 30-MB spreadsheet in LibreOffice, and a 523-MB image file in the GIMP. In the Visual Studio Express test, we open a 159-MB project containing source code for Microsoft’s PowerShell.
Load times for the first three programs are recorded using PassMark AppTimer. AppTimer’s load completion detection doesn’t play nice with Visual Studio, so we’re still using a stopwatch for that one.
From the above, we get two more chart-topping performances from the 970 EVO Plus. They’re lesser victories than the previous ones, since the differences are only a tenth of a second or so, but a record is still a record! Last, let’s fire up some games.
There are no first-place finishes for the 970 EVO Plus this time. It loads Batman a full half-second slower than the EVO 1 TB did, but it lands near the top of the ranges for the other two games. In terms of capacity, 500 GB can’t hold all that many of today’s big-budget games, but our 970 EVO Plus serves up what it can hold with little delay.
That’s all of our tests, and I didn’t get a single chance to say something mean about this drive. Ugh. The next page covers our test methods.
Test notes and methods
Here are the essential details for all the drives we tested:
|Adata XPG SX8200 480 GB||PCIe Gen3 x4||Silicon Motion SM2262||64-layer Micron 3D TLC|
|Crucial MX500 500 GB||SATA 6Gbps||Silicon Motion SM2258||64-layer Micron 3D TLC|
|Crucial P1 500 GB||PCIe Gen3 x4||Silicon Motion SM2263||64-layer Micron 3D QLC|
|Intel X25-M G2 160 GB||SATA 3Gbps||Intel PC29AS21BA0||34-nm Intel MLC|
|Samsung 850 EVO 1 TB||SATA 6Gbps||Samsung MEX||32-layer Samsung TLC|
|Samsung 860 EVO 1 TB||SATA 6Gbps||Samsung MJX||64-layer Samsung TLC|
|Samsung 860 QVO 1 TB||SATA 6Gbps||Samsung MJX||64-layer Samsung QLC|
|Samsung 970 EVO 1 TB||PCIe Gen3 x4||Samsung Phoenix||64-layer Samsung TLC|
|Samsung 970 EVO Plus 1 TB||PCIe Gen3 x4||Samsung Phoenix||90+-layer Samsung TLC|
|Toshiba RC100||PCIe Gen3 x2||Toshiba||64-layer Toshiba BiCS TLC|
The SATA SSDs were connected to the motherboard’s Z270 chipset. The PCIe drives were connected via one of the motherboard’s M.2 slots, which also draw their lanes from the Z270 chipset.
We used the following system for testing:
|Processor||Intel Core i7-6700K|
|Motherboard||Gigabyte Aorus Z270X-Gaming 5|
|Memory size||16 GB (2 DIMMs)|
|Memory type||Corsair Vengeance LPX DDR4 at 2133 MT/s|
|System drive||Corsair Force LS 240 GB with S8FM07.9 firmware|
|Power supply||Rosewill Fortress 550 W|
|Operating system||Windows 10 x64 1803|
Thanks to Gigabyte for providing the system’s motherboard, to Intel for the CPU, to Corsair for the memory and system drive, and to Rosewill for the PSU. And thanks to the drive makers for supplying the rest of the SSDs.
We used the following versions of our test applications:
- IOMeter 1.1.0 x64
- TR RoboBench 0.2a
- Passmark AppTimer 1.0
- Avidemux 2.7.1 x64
- GIMP 2.10.0
- LibreOffice 184.108.40.206
- Visual Studio Community 2017 15.7.4
- Batman: Arkham Origins
- Tomb Raider
- Middle Earth: Shadow of Mordor
Some further notes on our test methods:
- To ensure consistent and repeatable results, the SSDs were secure-erased before every component of our test suite. For the IOMeter database, RoboBench write, and RoboBench copy tests, the drives were put in a simulated used state that better exposes long-term performance characteristics. Those tests are all scripted, ensuring an even playing field that gives the drives the same amount of time to recover from the initial used state.
- We run virtually all of our tests three times and report the median of the results. We run our sustained IOMeter test a second time to verify the results of the first test, and we perform additional runs only if necessary. The sustained test runs for 30 minutes continuously, so it already samples performance over a long period.
- Steps have been taken to ensure the CPU’s power-saving features don’t taint any of our results. All of the CPU’s low-power states have been disabled, effectively pegging the frequency at 4.0 GHz. Transitioning between power states can affect the performance of storage benchmarks, especially when dealing with short burst transfers.
The test systems’ Windows desktop was set at 1920 x 1200 at 60 Hz. Most of the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit up our forums to talk with us about them.
At this point in a review, we typically offer a pithy summary of a drive’s strengths and weaknesses, but the Samsung 970 EVO Plus 500 GB’s performance throughout our test suite was truly above reproach. Let’s see where it lands in the overall rankings so we can decide how heartily to belt out our praises. We distill the overall performance rating using an older SATA SSD as a baseline. To compare each drive, we then take the geometric mean of a basket of results from our test suite. Only drives that have been through the entire current test suite on our current rig are represented.
Even though the 970 EVO Plus often beat the 970 EVO 1 TB, when the larger drive won, it was by a much greater margin. But ultimately, we don’t expect 500-GB drives to beat 1-TB drives, so who cares? The 970 EVO Plus is the fastest 500-GB class drive we’ve benchmarked yet. Maybe it’s the “90+ layer” V-NAND, or maybe it’s the unspecified enhancements to the Phoenix controller and its firmware, but either way, the drive conquered our test suite without breaking a sweat.
The final stop on the analysis bus is price town. We already know that Samsung expects the 970 EVO Plus 500 GB to sell for around $130, but we have to see how that fits into the broader market before we can render a decision. In the graph below, the most compelling position is toward the upper left corner, where the price per gigabyte is low and performance is high.
We’re still in a golden age of SSD sales, with PCIe drives going for what were once SATA prices. The 970 EVO Plus works out to 26 cents per gigabyte, and the other 500-GBish PCIe drives fall right around that mark, too. But the SX8200 and 760P both get left behind by the Samsung drive’s impeccable performance. The 970 EVO 1 TB is more powerful and more cost-effective per gigabyte, but I’d expect the 970 EVO Plus 1 TB to beat it without trouble. If you’re in the market for a 1 TB drive, I’d spend the extra two bucks for the latest and greatest instead of $248 for the older EVO.
The best new drive you could ask for is a cheaper, faster version of one that’s already good. The 970 EVO Plus’ stellar performance has lifted my spirits and brought me right out of my post-QLC-review funk. The 500-GB version can easily fit into the budget for a mid-tier rig. In fact, Bruno already astutely selected a 970 EVO 500 GB for the Sweet Spot build of our latest system guide. If you’re on the verge of embarking on a similar build, you can and should get one of these new Plus drives instead.
It’s been a long time since I’ve been able to recommend a drive without caveats, asterisks, or reservations. Samsung has managed to take a solid formula and make it even better, resulting in an unqualified win. The Samsung 970 EVO Plus’ unmitigated speeds and attractive pricing have earned it the honor of our Editor’s Choice Award.