|
ADATA Legend 970 PCIe Gen 5 SSD: Currently $339 (2TB)
The
|
|
|
- Competitive Overall Performance
- Great Game Level Loads
- PCIe Gen 5 Interface
- Low Latency, Good Responsiveness
|
- Audible Active Cooler
- Price Premium
|
|
At this point in time, PCIe 5.0 SSDs have been around for while, and we've already evaluated
quite a few of them. Prices on these drives are starting to fall to somewhat more palatable price points too, at least for some models. ADATA, for example, has a history of providing reasonably-priced SSDs with complete feature sets. In the case of the ADATA Legend 970 we'll be showing you here, that means a PCIe 5.0 interface, high performance and included active cooling.
ADATA's Legend series SSDs are targeted at content creators and other productivity use cases. This opposes them to the company's
XPG lineup, which is explicitly targeted at gamers. Of course, savvy readers will already be thinking that any PCIe 5 SSD with high-end performance is likely to suffice for either or both tasks. Indeed, the Legend 970 is ADATA's first mass-market PCIe 5.0 SSD, and it's a direct successor to the previous-generation Legend 960.
We won't beat around the bush too much on this one, but as usual, let's take a look at the specs before we get into benchmarks and discussion of this solid state drive.
ADATA Legend 970 SSD Specifications And Features
Find The ADATA Legend 970 PCIe 5 SSD @ Amazon
Examining the ADATA Legend 970, we see a familiar configuration: a Phison E26 controller mated to Micron 232-layer NAND flash. ADATA specs the drive for maximum sequential throughput of about 10 gigabytes per second either way, and promises 1.4 million IOPS in 4K-aligned random reads and writes, although those latter numbers are likely in a mostly-unrealistic benchmark with a high queue depth and number of threads. The drive comes in 1TB and 2TB variations; we're testing the 1TB drive today.
Yep, that's a SATA power connector hanging off the heatsink. Just like with the
Phison E26 reference platform that we looked at before, the ADATA Legend 970 includes active cooling. It would be easy to look at this as a failing of the ADATA drive, but the correct perspective is that ADATA is simply making sure that your SSD gives its full performance at all times. E26 drives run hot, and Phison actually recommends active cooling, even though very few of these drives include it.
The bottom of the drive bears the sticker with the serial number and other information. We'd like to see this become standard on M.2 SSDs; having the sticker on top impedes cooling a bit, and also makes this information prone to getting destroyed by thermal pads and heat. The "Warranty Void If Removed" marker is not valid in the United States, but perhaps it applies in other territories where these drives are sold.
Like many other SSDs in its class, the Legend 970 implements an SLC-like cache to enhance write performance. As you can see above, with the 1TB drive, that cache will operate at full speed until just 150GB of data is sequentially written to the drive, at which point write performance dips considerably. 1700 MB/sec isn't bad, but it is a long way from the top speed of this drive.
ADATA Legend 970 SSD Benchmarks
Under each test condition, the SSDs showcased here were installed as secondary volumes in our testbed, with a separate drive used for the OS and benchmark installations. Our testbed's motherboard was updated with the latest BIOS available at the time of publication and Windows 11 was fully updated. Windows firewall, automatic updates, and screen savers were all disabled before testing and Focus Assist was enabled to prevent any interruptions.
In all test runs, we rebooted the system, ensured all temp and prefetch data was purged, and waited several minutes for drive activity to settle and for the system to reach an idle state before invoking a test. All of the drives here have also been updated to their latest firmware as of press time. Where applicable, we would also typically use any proprietary NVMe drivers available from a given manufacturer. When not available, the drives used the Microsoft driver included with Windows 11.
HotHardware's Test System:
Processor:
Intel Core i9-13900K
Motherboard:
MSI Z790 Godlike
Video Card:
GeForce RTX 3080
Memory:
32GB Micron DDR5-6000
Storage:
ADATA XPG GAMMIX S70 Blade (OS Drive)
ADATA XPG GAMMIX S70 (2TB)
Seagate FireCuda 540 (2TB)
ADATA Legend 970 (1TB)
Samsung SSD 990 Pro (2TB)
Corsair MP700 (2TB)
Crucial T700 (2TB) |
OS:
Windows 11 Pro x64
Chipset Drivers:
Intel v10.1.19284
Benchmarks:
IOMeter 1.1
HD Tune v5.75
ATTO v4.01.01f
AS SSD
SiSoftware SANDRA
CrystalDiskMark v8.0.4c x64
Final Fantasy XIV: Endwalker
PCMark 10 Storage Bench
3DMark Storage Tests
|
IOMeter Benchmarks
IOMeter is a well-respected industry standard benchmark. However, despite our results with IOMeter scaling as expected, it is debatable as to whether or not certain access patterns actually provide a valid example of real-world performance. The access patterns we tested may not reflect your particular workloads, for example. That said, we do think IOMeter is a reliable gauge for relative throughput, latency, and bandwidth with a given storage solution. In addition, there are certain highly-strenuous workloads you can place on a drive with IOMeter, that you can't with most other storage benchmark tools.
In the following tables, we're showing two sets of access patterns; a custom Workstation pattern, with an 8K transfer size, consisting of 80% reads (20% writes) and 80% random (20% sequential) access and a 4K access pattern with a 4K transfer size, comprised of 67% reads (33% writes) and 100% random access. Queue depths from 1 to 16 were tested...
The Kingston Fury Renegade's odd scaling aside, the Legend 970 comports itself fairly well in these benchmarks. This is a challenging workload, and all three of our Phison E26-based drives—that is, the Legend 970, the FireCuda 540, and the T700—run neck and neck across all of the tests. Curiously, in the 8K test, the XPG Gammix S70 and the Samsung SSD 990 Pro leap out ahead despite being PCIe 4.0 drives. Note, however, they are based on different controllers (Samsung and Innogrit)/ It serves to illustrate that interface speed isn't everything.
These numbers represent the average bandwidth for the drives we tested with both access patterns, across every queue depth. The Fury Renegade looks strong here, but remember its trailing performance at the all-important low queue depths. Overall, the other two PCIe 4.0 drives dominate in the 8K test, but all of the 5.0 drives are running neck and neck.
These latency tests basically represent the same data as the throughput tests above, just reversed. That's not necessarily the case exactly, but in this example, it is. The IOMeter Workstation Access Pattern test is punishing, and it's no surprise that the late-gen PCIe 4.0 drives outperform here given the emphasis on rapid response over peak throughput.
SiSoft SANDRA 2022
Next, we used SiSoft SANDRA, the System ANalyzer, Diagnostic and Reporting Assistant for some quick tests. Here, we used the File System Test and provide the results from our comparison SSDs. Read and write performance metrics, along with the overall drive score, are detailed below.
Sandra's storage benchmark is much more a test of sequential performance, and as you'd expect, our PCIe 5.0 drives leave the older PCIe 4.0 drives in the dust. These tests aren't super relevant to most users, but if you're doing a lot of file copying, or manipulating very large files frequently, then this might be the most important tests to you. The Legend 970 offers excellent performance in this test, on par with the Seagate drive—naturally, as both SSDs use the same controller and PCIe 5.0 interface.
ATTO Disk Benchmark
ATTO is another "quick and dirty" type of disk benchmark that measures transfer speeds across a specific volume length. It measures raw transfer rates for both reads and writes and graphs them out in an easily interpreted chart. We chose .5KB through 64MB transfer sizes and a queue depth of 6 over a total max volume length of 256MB. ATTO's workloads are sequential in nature and measure raw bandwidth, rather than I/O response time, access latency, etc.
In ATTO, the ADATA Legend 970 loses a bit of ground against the Seagate FireCuda 540, but neither drive can keep up with the Crucial T700 once the transfer size gets big enough. Crucial's drive just runs away from the pack, much like we saw in the SANDRA test above.
Where the XPG Gammix S70 was able to hang tough with the Samsung SSD 990 Pro in IOMeter, it struggles here, and both drives ultimately get left in the dust when transfer sizes grow enough that the PCIe 5.0 drives can flex their current-generation muscles. The performance of the three E26-based drives is very similar here, as you would expect. The differeces are mostly margin of error in this test.
AS SSD Compression Benchmark
Next up we ran the Compression Benchmark built-into AS SSD, an SSD specific benchmark being developed by Alex Intelligent Software. This test is interesting because it uses a mix of compressible and non-compressible data and outputs both Read and Write throughput of the drive. We only graphed a small fraction of the data (1% compressible, 50% compressible, and 100% compressible), but the trend is representative of the benchmark’s complete results.
The compressibility of the data being transferred across the drives we tested has virtually no impact on performance, but it's good to confirm that we've come a long way from the days of SandForce controllers losing two-thirds of their performance on non-compressible data.The only odd outlier is the small gain on the Adata Legend 970 on the write test. These drives definitely aren't abusing compression to increase their numbers. Most of the variation seen here with these drives is due to their behavior with this specific benchmark's workload.
