Toshiba XG3 M.2 NVMe SSD Review (1TB) – Rocket Ship NVMe SSD

At The SSD Review, we test our SSDs slightly different depending upon the drive’s marketed purpose, be it consumer/oem or enterprise focused SSD. For a oem SSD, our goal is to test in a system that has been optimized with our SSD Optimization Guide, however, CPU C States may or may not have been altered, dependent on motherboard UEFI features. Benchmarks for our consumer tests are that of fresh drives (PCMark 8 testing exempt), so that we can verify that the manufacturer’s specifications match the SSD. Additionally, we also include links to the benchmarks used in our reports so that you as the reader can replicate our tests to confirm that your SSD is top-notch.

TSSDR Corsair Z170 Test Bench 1090

TSSDR Z170 TEST BENCH COMPONENTS

Our Z170 Test bench was the result of some great sponsorship’s and our appreciation goes to Samsung, Corsair, ASRock, PNY and Intel for helping us with this build. All of the hardware we use for testing is available for purchases at a reasonable price; albeit this specific build is a tad high-end. The links provided below can assist in pricing and availability of the hardware contained within this system:

PC CHASSIS: Corsair 760T White Full Window
MOTHERBOARD: ASRock Z170 Extreme7+ ATX DDR4
CPU: Intel I7-6700K 4.00 GHz
CPU COOLER: Corsair Hydro Series H110i GTX
POWER SUPPLY: Corsair HX1200i ATX12V
GRAPHICS: PNY GTX 980 4GB XLR8 Pro OC
MEMORY: Corsair Dominator Pl 32GB 2800
STORAGE: Intel 750 Series 1.2TB NVMe SSD
KEYBOARD: Corsair Vengeance K70 Mech
MOUSE: Corsair White M65 Laser
OS Microsoft Windows 10 Home 64 Bit

BENCHMARK SOFTWARE

The software used for today’s analysis is typical of many of our reports and consists of ATTO Disk BenchMark, Crystal DiskMark, AS SSD, Anvil Storage Utilities, PCMark 8,  as well as PCMark Vantage. In addition, we are also going to include some pretty impressive ‘real world tests’ that demonstrate and compare different types of M.2 SSDs. Most of the software that we use is FREE and access to all programs can be done by simply clicking on the title of the benchmark. For a complete background and linkage to the software we use, check out our recent article, “The Ultimate Guide To SSD Benchmark Software“.

ATTO DISK BENCHMARK VER. 2.47

ATTO Disk Benchmark is perhaps one of the oldest benchmarks going and is definitely the main staple for manufacturer performance specifications. ATTO uses RAW or compressible data and, for our benchmarks, we use a set length of 256mb and test both the read and write performance of various transfer sizes ranging from 0.5 to 8192kb. Manufacturers prefer this method of testing as it deals with raw (compressible) data rather than random (includes incompressible data) which, although more realistic, results in lower performance results.

Toshiba XG3 1TB NVMe M.2 SSD Atto Disk Benchmark

ATTO seems to draw the picture that both read and write performance exceed that of listed specifications, at 2.7GB/s read and 1.6GB/s write speeds.  The overall appearance of this benchmark is that of a solid SSD as we can see that performance increases steadily as file size increases, and we are well above the SATA 3 threshold for read and write speeds at the 4k file size.

19
Leave a Reply

avatar
9 Comment threads
10 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
12 Comment authors
R. Rubbjp1wc1Douglas PayneNevin Sweigartdravo1 Recent comment authors
  Subscribe  
newest oldest most voted
Notify of
Benjamin Hojnik
Guest
Benjamin Hojnik

Thats some pretty good stuff from toshiba. And from 2D MLC flash.

I do wonder however what controller is that. Obviously its not made by toshiba. Something from OCZ maybe ? Or phison E7?

Les@TheSSDReview
Guest

There is a bit of investigation about the net that eludes to this being the Phison E-7, however, not enough to confirm or mention such within the article.

Shamoy Rahman
Guest
Shamoy Rahman

No, the controller is solely Toshiba’s.

Les@TheSSDReview
Guest

Link? Maybe a bit of validation or reasoning behind your thought?

Les@TheSSDReview
Guest

This is the Fujisan controller that was on display with OCZ as part of their Revo 400 release at Computex last year. We have elaborated on this within the report in controller description and the final para. This link shows what we posted prior.

http://www.thessdreview.com/daily-news/latest-buzz/ocz-prepares-new-revodrive-400-m-2-nvme-ssd-for-retail-release-computex-2015-update/

Benjamin Hojnik
Guest
Benjamin Hojnik

Thats some pretty good stuff from toshiba.

DarthDVD
Guest
DarthDVD

Bring on the 1Tb M.2 NVME Drives!!! (its the only thing stopping me from dropping a lot of moneys (and selling 1/2 a liver) and getting a new Rig.

Greg Zeng
Guest
Greg Zeng

Your claim for Crystal Disk Benchmark is several times higher than mine, on my 2013 Dell XPS-15 notebook computer. The original factory mSATA SSD was replaced a few months ago with a terabyte Samsung 850 EVO.

How comparable are the results of your tests, compared to those of your readers? If I install one of your tested products, how much performance difference should we expect? Several times?

My next upgrade might be to replace to original terabyte spinning HDD with a SSD of one or two terabytes. Perhaps.

DarthDVD
Guest
DarthDVD

The Samsung 850 EVO SSD (mSata) uses the mSata Standard and can not go as fast as the drives in this review.

The Drives in this review are M.2 (PCIE NVME) SSD’s and have access to 4 PCIE lanes which is Considerably much faster than Sata be it on: mSata on mini-pci(e) or M.2

https://en.wikipedia.org/wiki/M.2

Shamoy Rahman
Guest
Shamoy Rahman

You should’ve bought an M.2 or PCIE SSD if you wanted pure speed and didn’t care about the cost.

SkOrPn
Guest
SkOrPn

All I will say is you can’t really get away with comparing mSATA or SATA against PCIe storage. Its kinda like comparing PCIe video cards to AGP video cards, or even PCI to PCIe, it just isn’t a fair comparison. The PCIe bus is magnitudes better at moving data than the SATA bus will ever be. Now if you want to put FOUR 850 EVOs into RAID0, then we can talk comparisons because that MIGHT (I stress might, lol) compete with the single PCIe SSD given the usage scenario.

dzezik
Guest
dzezik

The advice to disable cache flush is wrong. You should only mark this option is the SSD has capacitors to protect unflushed data on power loss. So the drive runs faster but Your data is not safe, this is trade off. pease be aware of that. if the performance without this option is low then the controller or firmware is not well designed or… other controllers do not respect host request to flush cache. Do You have any information what is the real issue? Regards

Les@TheSSDReview
Guest

This is not uncommon. It is also much the same regardless of system and, yes is a tradeoff.