Why you can trust Tom's Hardware Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Find out more about how we test.
Comparison Products
The XPG Mars 980 Blade, or just 980 Blade, has a lot of competition. The class leaders are the SanDisk WD Black SN8100 with BiCS8 TLC and the Crucial T710 with 276-Layer Micron TLC flash. The proprietary Samsung 9100 Pro also belongs here, especially as it reached 8TB first. Another fast alternative with BiCS8 is the Kingston Fury Renegade G5, which, along with the Black SN8100, has an 8TB option on the way. All of these have a flash advantage over the 980 Blade. Upcoming drives based on Phison's E28 SSD controller should also have this advantage, arriving with BiCS8 TLC.
The 980 Blade instead competes as a pseudo-budget option against the likes of the Acer Predator GM9000, which has the same hardware, as well as older E26-based drives such as the Adata Legend 970 and newer DRAM-less heavyweights like the Biwin Black Opal X570. The 980 Blade, having DRAM and being much more efficient than E26 drives, makes it easier to digest with aggressive pricing. It’s a matter of where your priorities lie and what kind of performance you’re willing to trade.
Trace Testing — 3DMark Storage Benchmark
Built for gamers, 3DMark’s Storage Benchmark focuses on real-world gaming performance. Each round in this benchmark stresses storage based on gaming activities including loading games, saving progress, installing game files, and recording gameplay video streams. Future gaming benchmarks will be DirectStorage-inclusive and we also include notes about which drives may be future-proofed.
Right away, we see that the 980 Blade’s use of older flash impacts its performance. This flash has it falling behind the 276-Layer flash on the T710 and the BiCS8 on the Black SN8100 and Fury Renegade G5, drives that use the same controller. However, it’s not far off the 9100 Pro and E28, and it easily beats older, DRAM-less options like the Legend 970 and Black Opal X570, respectively. It’s good enough in 3DMark to put it over any PCIe 4.0 drive and many, if not most, PCIe 5.0 drives.
Trace Testing — PCMark 10 Storage Benchmark
PCMark 10 is a trace-based benchmark that uses a wide-ranging set of real-world traces from popular applications and everyday tasks to measure the performance of storage devices. The results are particularly useful when analyzing drives for their use as primary/boot storage devices and in work environments.
We see something similar in PCMark 10: the 980 Blade is certainly a fast drive, but it’s not on the level of the best PCIe 5.0 ones out there. Its performance is good enough if you just want a high-end drive for your fancy PCIe 5.0 M.2 slot, though. It might even be a good choice depending on prices and your budget, which is, of course, the idea with this drive. At the time this drive was cooked up, the AI memory spend wasn’t in full swing yet, but due to that new reality, the 980 Blade makes even more sense.
Console Testing — PlayStation 5 Transfers
The PlayStation 5 supports one additional PCIe 4.0 or faster SSD for extra game storage. While any 4.0 drive will technically work, Sony recommends drives that can deliver at least 5,500 MB/s of sequential read bandwidth for optimal performance. In our testing, PCIe 5.0 SSDs don’t offer much advantage and generally shouldn’t be used in the PS5, especially since they may require additional cooling. Check our Best PS5 SSDs article for more information.
Our testing utilizes the PS5’s internal storage test and manual read/write tests with over 192GB of data, both from and to the internal storage. Throttling is prevented where possible to see how each drive operates under ideal conditions. While game load times should not deviate much from drive to drive, our results can indicate which drives may be more responsive in long-term use.
We think that using a PCIe 5.0 SSD in a PS5 is a waste, but there are cases where it might make sense. There may come a time when PCIe 5.0 drives are close to the price of PCIe 4.0 drives, and, in fact, history suggests PCIe 4.0 might even end up more expensive.
Things are sketchy right now with prices trending rapidly upward, but most of that cost is on the flash and, to some extent, the DRAM. So it’s possible it could be worth grabbing a drive like the 980 Blade as an investment, even if you only use it temporarily in your PS5. Its performance in the console is excellent, and you can always swap it out later if you do a future PCIe 5.0 build.
Transfer Rates — DiskBench
We use the DiskBench storage benchmarking tool to test file transfer performance with a custom, 50GB dataset. We write 31,227 files of various types, such as pictures, PDFs, and videos to the test drive, then make a copy of that data to a new folder, and follow up with a reading test of a newly-written 6.5GB zip file. This is a real world type workload that fits into the cache of most drives.
We’re less pleased with the 980 Blade’s copy performance. In general, 2.2+ GB/s is an excellent result for the file mix we use, but we’ve come to expect more from high-end drives. In most cases, the copy transfer rate is limited by the write speed – the write portion usually falls inside the pSLC cache – so results are pretty predictable. We would expect the 980 Blade to be closer to the Predator GM9000, but for whatever reason, it didn’t get there for us today.
Since we look at our results in order when preparing a review, at this stage, we would expect a bad result here to be reflected somewhere in our later write saturation test. We mention that because any reader wanting to understand and identify drive characteristics should know where to look to confirm certain impressions. If you're someone who buys more than one drive every few years, these lessons can inform you about drives we don’t directly review, as almost every one we do review has “twins” for sale. We’re not just reviewing a specific drive; we’re exploring patterns that can be extrapolated to other products for careful readers.
Synthetic Testing — ATTO / CrystalDiskMark
ATTO and CrystalDiskMark (CDM) are free and easy-to-use storage benchmarking tools that SSD vendors commonly use to assign performance specifications to their products. Both of these tools give us insight into how each device handles different file sizes and at different queue depths for both sequential and random workloads.
The ATTO data is mostly as expected, but the 980 Blade does have some nuance to its read and write results at high block sizes. Specifically, we see the same drop at 2MiB reads that we do with the Legend 970. We can probably ignore the 4MiB drop for writes, but the 4MiB recovery for reads also mirrors the Legend 970’s results. Given that these two drives have different controllers and controller manufacturers, we can guess it comes down to the flash.
Both are using Micron’s 232-Layer TLC flash, and both are labelled by Adata. Historically, Adata has bought flash by the wafer and done its own binning, which also allows it the freedom to encode the flash itself. This can make the flash more difficult to identify, even when specialized software tools are used. However, we can guess based on the results here that the 980 Blade and 970 Legend are almost certainly using the same flash, with other differences borne out by the controller change. Considering the 980 Blade underperforms the GM9000 in some areas and should be better, if anything, due to potentially newer or optimized firmware, we can guess this flash is either of a lower grade or Adata has it configured to perform differently.
We can spend all day speculating on why this is, but assuming the latter, there are many reasons why a manufacturer might have flash that doesn’t perform exactly the same as other models in synthetic tests. It could be to temper wear more readily, something that was the case during the short-lived Chia plotting days. Users tend to frown on this because it sounds like performance is being “held back” intentionally, but if you take these drives into a real-world setting, it’s usually a negligible difference. Trading synthetic performance for endurance on the sly doesn’t exactly sound like shady business. Either way, our goal is to point out that Adata does seem to be doing something different here. It doesn’t translate to much difference in CDM’s sequential results aside from QD1 reads being a little underbaked.
Everybody gets more excited by random read results, anyway. For 4KB reads at QD1, the 980 Blade delivers a respectable 38.47µs of latency, which is close to the 9100 Pro. We find this absolutely sufficient and better than any Gen 4 drive. 4KB QD1 write latency is even better, suggesting maybe Adata did some tuning on this drive that might explain some of the other discrepancies. While random writes aren’t as important for daily use, they can help in some productivity workloads, which means the 980 Blade could end up with better balance overall.
Sustained Write Performance and Cache Recovery
Official write specifications are only part of the performance picture. Most SSDs implement a write cache, which is a fast area of pseudo-SLC (single-bit) programmed flash that absorbs incoming data. Sustained write speeds can suffer tremendously once the workload spills outside of the cache and into the "native" TLC (three-bit) or QLC (four-bit) flash. Performance can suffer even more if the drive is forced to fold, which is the process of migrating data out of the cache in order to free up space for further incoming data.
We use Iometer to hammer the SSD with sequential writes for 15 minutes to measure both the size of the write cache and performance after the cache is saturated. We also monitor cache recovery via multiple idle rounds. This process shows the performance of the drive in various states as well as the steady state write performance.
The 980 Blade writes at 12.6 GB/s in the fastest single-bit pSLC cache mode for over 30 seconds. The total cache is over 405GB, which is on the larger size but below the maximum size possible. Its overall output is similar to the Predator GM9000 and T710, demonstrating that Micron TLC flash – regardless of generation – performs similarly. The drives with different flash, like the 9100 Pro, the Black SN8100, and the Fury Renegade G5, have larger caches. The three outliers are the Phison E28, which is a different controller entirely, the Legend 970, which is an older drive, and the Black Opal X570, which is high-end but DRAM-less. If we look at steady state write performance, we don’t see any drives that break old records, but the 980 Blade underperforms to some extent. We anticipated this when reviewing the DiskBench results above.
The good news is that 3.68 GB/s is still very fast, and many other drives, even good ones, are left in the dust. The bad news is that you can get this level of performance or higher with many high-end PCIe 4.0 drives. There’s also the PCIe 5.0 Sabrent Rocket 5, which has superlative sustained write performance. The bottom line is this: the 980 Blade delivers within the expected range but does not awe us in any way. You’re trading the “fastest drive ever” brag for “very fast, and I saved money” instead.
Power Consumption and Temperature
We use the Quarch HD Programmable Power Module to gain a deeper understanding of power characteristics. Idle power consumption is an important aspect to consider, especially if you're looking for a laptop upgrade as even the best ultrabooks can have mediocre stock storage. Desktops may be more performance-oriented with less support for power-saving features, so we show the worst-case.
Some SSDs can consume watts of power at idle while better-suited ones sip just milliwatts. Average workload power consumption and max consumption are two other aspects of power consumption but performance-per-watt, or efficiency, is more important. A drive might consume more power during any given workload, but accomplishing a task faster allows the drive to drop into an idle state more quickly, ultimately saving energy.
For temperature recording we currently poll the drive’s primary composite sensor during testing with a ~22°C ambient. Our testing is rigorous enough to heat the drive to a realistic ceiling temperature.
Power efficiency is a funny thing. Many people don’t really care about it, while others make it their mission to get the most performance out of the fewest watts possible. This is certainly more of a game for high-consumption devices like CPUs and GPUs, but high-end SSDs are starting to draw significant wattage at peak. Consumer drives still, by far and large, are idle most of the time, but future game requirements might change this equation, especially if you need to run multiple SSDs to handle the larger games of tomorrow. Besides, reducing the overall heat inside your desktop computer – for laptops, even more so – is always a bonus. Luckily, the restrictively high heat output of early high-end PCIe 5.0 drives, which required a heatsink for operation, is becoming a thing of the past.
The 980 Blade uses one of the newer controllers that help keep power consumption and heat under control. Its efficiency is not fantastic, but it leaves PCIe 4.0 drives in the dust. With around 4W of average power consumption during our sustained write test – your own experience may vary – this is not a drive you have to worry about. Just compare it to the Legend 970, which only hit 10 GB/s at that. The 980 Blade only hit 66°C during our test, which is 17°C below the initial throttling point. This leaves a decent amount of headroom and confirms that the heatspreading label is effective.
Test Bench and Testing Notes
CPU | |
Motherboard | |
Memory | |
Graphics | Intel Iris Xe UHD Graphics 770 |
CPU Cooling | |
Case | |
Power Supply | |
OS Storage | |
Operating System |
We use an Alder Lake platform with most background applications such as indexing, Windows updates, and anti-virus disabled in the OS to reduce run-to-run variability. Each SSD is prefilled to 50% capacity and tested as a secondary device. Unless noted, we use active cooling for all SSDs.
Adata XPG Mars 980 Blade Bottom Line
The Adata XPG Mars 980 Blade is not a great drive, but it’s not bad, either. Its overall performance is quite good compared to most drives and any PCIe 4.0 drive, but among the newest crop of high-end PCIe 5.0 SSDs, it is mediocre at best. This goes for its power efficiency, too, which is at least significantly better than earlier drives in this class. None of this is prohibitive as the 980 Blade is priced to move when it’s available. This is a good opportunity to get a fast PCIe 5.0 drive at a discount. The limits of the interface are already being pushed, and prices are only going up, so the drive even works as a preemptive buy if you want to have one waiting in the wings.
On the other hand, we prefer the Crucial T710 if you’re going for a 1TB SSD. It has the best flash for that capacity to get the highest bandwidth. If you want the top drive otherwise, the SanDisk WD Black SN8100 remains our pick at 2TB and 4TB. We expect that drive to be great at 8TB when it arrives, and the 8TB version of the Kingston Fury Renegade G5 has also been announced. Until then, the Samsung 9100 Pro has the best and only 8TB option in this class, and it was as low as $749.99 during recent sales. If capacity is your game, then we would suggest the WD Black SN850X as a fallback compromise.
If other drives with the SM2508 are a better deal at the time of shopping, we recommend ones with BiCS8 TLC flash for the best latency and 276-Layer Micron TLC flash for the most bandwidth. Drives like the 980 Blade, with 232-Layer Micron TLC flash, are the budget option as a better pick than older E26-based drives. We can’t offer any suggestions around the Phison E28 controller just yet.
Newer mid-range PCIe 5.0 SSDs, like the Crucial P510, are also a possible solution if you’re still using a PCIe 4.0 slot. These newer drives will still be faster and more power-efficient overall and can be used as a secondary drive in faster systems down the road. We still think the SN850X and Samsung 990 Pro are the best overall drives here, with the SK hynix Platinum P41 being the budget choice if you demand DRAM. The price cut does imply that SK hynix has given up on fixing a write issue with the drive, but it’s still a good drive for most use cases. Alternatively, the Crucial T500 also has TLC and DRAM, but it is a little weak with sustained writes. If you choose to go DRAM-less, then we would suggest checking our reviews on budget drives.
So, who is the target buyer for the 980 Blade? Well, if you are lucky enough to have more than one PCIe 5.0 M.2 slot, then it would make for a good second or even third drive. It might also be one of the last chances to get this level of performance at a reasonable price. It should be fine in older systems, desktops, or laptops, and the PS5 if you are buying for future plans. If you are on a strict budget or, alternatively, want the very best, we would tell you to steer clear. This is 100% an affordable luxury type item which would be at home as a “PCIe 5.0 SSD” on a prebuilt if the company wanted 14+ GB/s on the label and ran out of E26 drives. At least until DRAM-less drives like the Biwin Black Opal X570 become more common, as rising DRAM costs might alter the balance. For now, the 980 Blade is a safe bet to check the important boxes without doing anything exciting.
MORE: Best SSDs
MORE: Best External SSDs
