Samsung SM961 SSD Review

  • Thread starter Thread starter Guest
  • Start date Start date
Toggle sidebar Toggle sidebar
Status
Not open for further replies.
G

Guest

Guest
The SM961 is the SSD that everyone is talking about because it provides up to 3,200 MB/s of sequential performance. No more rumors, today we test the new Samsung SM961 1TB NVMe SSD from the SSI group. Is this your next SSD?

Samsung SM961 SSD Review : Read more
 


It will be interesting to see who sues first.
 
My 3 month old 950 Pro is already obsolete 😛 OK not really. It is great to see these drives getting better and cheaper though. The 960 Pro should be a beast.
 
My Lenovo T460S bought last month with a generically described "1TB NVMe" came with an OEM PM961 in it. Very nice and fast although having to use software bitlocker so far as either it's not eDrive/OPAL or can't enable it as Samsung Magician only works on retail drives...
 
Ah, thanks for the update. The PM961 is certainly on my radar. It's the TLC flash brother to the SM961. I would love to get my hands on that drive for three days and 9TB of data writes.
 
"Intel RST issues in RAID 0 on Z170 (Intel's Fault)"
This is a deal-breaker for me - and why is it Intel's fault? SM951 works fine with RST on Z170, while SM961 does not - and it's not Samsung's fault?
 
Unless I'm mistaken, there are articles on the web around how to setup a bootable RAID with multiple Samsung 950 Pros on certain motherboards. The key is that it only works if the mobo has Intel RST built into the UEFI. Here's the best article I've found on it: http://www.thessdreview.com/daily-news/latest-buzz/understanding-m2-3xraid0-nvme-boot-performance/

Now, I've only seen Z170 boards with more than 1 M.2 slot, so it's arguably not worthwhile, as that site's tests showed. The limited PCIe bandwidth available on the Z170 probably negates any performance gains from such a setup. X99, however, has tons more PCIe lanes available. I don't get why we haven't seen X99 boards with multiple M.2 slots thus far. That seems like a perfect use of all those lanes--especially given NVIDIA's recent dropping of support for 3-way and 4-way SLI. What else are you going to use all those lanes for, now?
 


I'm looking into it deeper now to see if it was something added in a firmware update that changed some microcode. As I mentioned in the article, OCZ has an issue as well with RST.
 
Lack of IEEE-1667 (aka "eDrive") is a blocker for me, so hanging on for the full retail version. Worth noting that the 950 Pro also doesn't yet support this, which is a real pain for those of us who use FDE.
 
Hello ,

I know this mite be expensive , but how about testing the TBW yourself ? fill it up/delete loops until it fails?

No need to use the 1TB one , get the 256GB one and test its TBW (Tera Bytes Write till fail)

a Review Should Confirm the TBW as well not Only the Performance .

Use the lowest Model for this in all SSD reviews , we can predict the higher capacities TBW from the lower ones TBW ...

make your software for it please .. and TEST the SSD maker Claim of TBW ...
 
There is a lot more to testing endurance than just filling the drive, erasing and filling it again. I have the software to run the tests, I even have dedicated hardware for it but having the tools is different than having the time and power to space for such a project. If I were to run the test before the review then the review would come out many, many months later. On products with V-NAND, the review would come out even longer than that. Just because the WMI turns to 0 doesn't mean the flash is bad. The TBW is just what the drives are warrantied for.

If you want to learn more about the process this is the a good place to start.

http://www.flashmemorysummit.com/English/Collaterals/Proceedings/2011/20110810_T1B_Cox.pdf

The doc has links to the consumer and enterprise tests. You could buy a Ulink DriveMaster setup and automate the entire process.
 
I have just purchased the SM961 and performance is terrible, in my latest benchmark sequential Read is 1120.83 MB/s and Sequential Write is 224.61 MB/s. The only drivers supplied/available are the inbuilt Windows 10 NVMe drivers so this may be part of the problem. The Samsung 950 Pro which is older has sequential Red of around 2036.85 MB/s and Write 930.27 MB/s so I may as well have purchased the 950 Pro. The M.2 SM961 is installed in an NVMe PCIe card and then installed in a x4 Gen 3 PCIe slot so everything is optimal.
 
So you tested the SM961 against the 950 Pro under the same conditions? Both in that same 4x PCIe adapter, same storage driver, etc? What about the Magician software? Thanks
 
I used the same motherboard for all NVMe tests other than the RAID test.

The standard PCIe SSD board is an Asrock Z97 Extreme6. The PCIe RAID board is an Asrock Z170 Extreme7+.

Magacian doesn't work with the SM961 and neither does the retail NVMe driver. I tested the drive with HP's Samsung NVMe driver, with the Windows NVMe driver (the one for the benchmarks presented in the review). There wasn't much of a change with the HP custom driver. The 950 Pro gets a performance increase from the Samsung NVMe driver and that is what we tested with.

As of right now there is not a SM961-specific NVMe driver from Samsung. When asked, Samsung said to use the built in Windows driver.
 
Intel RST issues in RAID 0 on Z170 (Intel's Fault)
Which MB manufacturers have you tested RAID 0 with NVMe?
Intel Hardware RAID 0 on H/Z-170 NVMe works on some ASUS H/170 ASROCK MB
Who do you point the finger to ?
 
Status
Not open for further replies.

TRENDING THREADS

Latest posts

Moderators online

Share this page

COMPANY
RESOURCES
FOLLOW
Top Bottom