Note: Our SSD testbed is currently producing suspiciously slow scores for The Destroyer, so those results have been omitted pending further investigation.

Note2: We are currently in the process of testing these benchmarks in PCIe 4.0 mode. Results will be added as they finish.

AnandTech Storage Bench - Heavy

Our Heavy storage benchmark is proportionally more write-heavy than The Destroyer, but much shorter overall. The total writes in the Heavy test aren't enough to fill the drive, so performance never drops down to steady state. This test is far more representative of a power user's day to day usage, and is heavily influenced by the drive's peak performance. The Heavy workload test details can be found here. This test is run twice, once on a freshly erased drive and once after filling the drive with sequential writes.

ATSB Heavy
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

The 250GB Samsung 980 PRO is a clear improvement across the board relative to the 970 EVO Plus. It still has some fairly high latency scores, especially for the full drive test run, but that's to be expected for this capacity class. The 1TB model seems to have sacrificed a bit of its full drive performance for in favor of a slight increase in empty-drive performance—the enlarged SLC caches are probably a contributing factor here.

Both drives show a significant reduction in energy usage compared to the older generation of Samsung M.2 NVMe drives, but there's still a ways to go before Samsung catches up to the most efficient 8-channel drives.

AnandTech 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.

ATSB Light
Average Data Rate
Average Latency Average Read Latency Average Write Latency
99th Percentile Latency 99th Percentile Read Latency 99th Percentile Write Latency
Energy Usage

The Samsung 980 PRO does not bring any significant improvements to performance on the Light test. Peak performance from most high-end NVMe drives is essentially the same, and the only meaningful differences are on the full-drive test runs. Aside from a relatively high 99th percentile write latency from the 250GB 980 PRO, neither capacity has any trouble with the full-drive test run.

Samsung has made significant improvements to energy efficiency with the 980 PRO. Samsung's previous generation of M.2 NVMe drives were among the most power-hungry in this segment, with their performance potential largely wasted on such a light workload. The 980 PRO cuts energy usage by a third compared to the 970 generation drives, bringing them more into competition with other high-end M.2 drives. But as with the Heavy test, there's still a lot of room for improvement as illustrated by drives like the WD Black SN750.

Cache Size Effects Random IO Performance
Comments Locked

137 Comments

View All Comments

  • 5j3rul3 - Wednesday, September 23, 2020 - link

    980 Pro (X)
    980 EVO (O)
  • DarkMatter69 - Wednesday, September 23, 2020 - link

    Could the comparison include some of the fastest M.2 SSDs already in market, e.g. Sabrent Rocket 4, Corsair MP600, Aorus NVM, etc.? the comparison drives used in this article are not the fastest ones, so it is difficult to understand how good is this M.2 drive vs all the other top ones in the market already. Thank you!
  • Slash3 - Wednesday, September 23, 2020 - link

    I'd also like to see a few more models make their way through the Anandtech tests, but the Seagate Firecuda 520 in this review is essentially representative of the models you listed. They're all based on what are effectively reference Phison E16 designs and can even be cross-flashed with the same firmware. Upcoming Phison E18 based drives should shake things up a little bit more and will be the true point of comparison for the 980 Pro.
  • Koenig168 - Wednesday, September 23, 2020 - link

    980 Evo masquerading as 980 Pro.
  • yetanotherhuman - Wednesday, September 23, 2020 - link

    TLC != Pro. Forget it. 2-bit or bust.
  • twtech - Wednesday, September 23, 2020 - link

    The write endurance on this drive is identical to the 970 EVO. Yeah, it may be a bit faster - especially being PCIE 4.0 - but it's not like you can use it in ways that you can't use the (much cheaper) non-Pro drives now.
  • Whiteknight2020 - Wednesday, September 23, 2020 - link

    And you are entirely missing the point. "Pro" is a generic, meaningless, marketing term. Just look on Amazon for "pro" branded items, ranging from cheap tat to quality (for specific use cases) items. You are choosing to interpret the way a marketing/branding term has previously been applied to product by a manufacturer as having a fixed value and meaning which it does not, it is merely branding and ascribes no specific technical, functional or physical properties to the product. That you are entitled to be aggrieved at the way the branding is used is not in question, what is is your giving the branding a meaning which it does not have.
  • XabanakFanatik - Wednesday, September 23, 2020 - link

    Pro is not a generic, meaningless marketing term. Pro is a branding on Samsung SSD's that Samsung has been cultivating for a decade, which has a very well-defined meaning. Samsung Pro SSD's are 2-bit MLC with sustained write performance and high endurance.

    This drive has none of the three things that has defined a Samsung Pro SSD for a decade.

    They just threw a decade of brand building away with one product.
  • edzieba - Wednesday, September 23, 2020 - link

    The near-zero change in random performance at QD1 for PCIe 3 vs. 4 was expected, but the very lot bump in high-QD sequential transfers was not. It's abundantly clear that PCIe 4 bandwidth, at least for desktop use, has no practical applications as of yet.
  • lightningz71 - Wednesday, September 23, 2020 - link

    I wonder how the lower end NVME drives will fare when they move to PCIe 4.0? One of the hangups of using host drive map caching was the slower data path between the drive controller and the host memory that was imposed by having to cross the PCIe 3.0 lanes to get to the host memory. Eventually, cacheless controllers will move to PCIe 4.0. Will it be cheaper to make a cacheless PCIe 4.0 controller that actually uses all 4 lanes (some of the cheapest PCIe 3.0 cacheless controllers only used 2 lanes) than to stay with a more mature PCIe 3.0 controller that has a modest amount of cache with it? Will the performance be close enough to make that decision moot?

Log in

Don't have an account? Sign up now