IOMeter is another open source synthetic benchmarking tool which is able to simulate the various loads placed on hard drive and solid state drive technology.
We test with both random read and write 4k tests, as shown above. There are many ways to measure the IOPS performance of a Solid State Drive, so our results will sometimes differ from manufacturer’s quoted ratings. We do test all drives in exactly the same way, so the results are directly comparable.
In the IOMeter 4K random tests, the drive produced a read score of 205,564 IOPS and writes came in at 157,826 IOPS which fall somewhere in-between the two sets of official figures for the drive.
While the results may be some way short of the top end figures that Samsung quote (due to their differing test procedure), they completely eclipse the performance of the preceding SSD950 PRO drive.
You have some kind of bottleneck since you don’t achieve maximum specification speeds.
This will set you back at least 3 grand.
its est at $1299 USD lol.
The IOMeter IOPS results aren’t near the specification performance because a different test procedure is used to the one that gives Samsung its specified figures. IOPS numbers can change quite significantly based on the tested QD and number of Threads.
that is truly impressive, I would like to see some reviews for the lower capacity models
Should be released on 10/30 (or 30/10 for you euro’s) here in the states, and I cannot wait to get my 2tb 960 pro! I’ve literally been postponing a whole new build just to wait for this drive, but it’s going to be well worth the wait!
“…that’s a bit of an understatement to say the least as Samsung quote Sequential read/write figures for the 2TB drive as 3,500MB/s and 2,100MB/s respectively. Incidentally, they are the same figures as for both the 512GB and 1TB drive..”
This text is directly from the first page of the review….did you even read the article?
http://www.tweaktown.com/reviews/7909/samsung-960-pro-2tb-2-nvme-pcie-ssd-review/index.html
Tweaktown’s review…only they test drives by making them the OS drive, then filling it to 75% capacity to more accurately mimic the conditions a real user will be using the drive under…
just because it is rated for the same speed, doesn’t mean that it will perform exactly the same, the random read/write performance isn’t as fantastic as the ratings are showing