ATTO Disk Benchmark is a relatively easy-to-use benchmark tool, which happens to be the benchmark of choice for many manufacturers. ATTO uses compressible data rather than random data, which results in higher performance and thus, higher benchmark scores. In our testing, we have selected the transfer size to range from 0.5KB to 8192KB, and have set the total length of the test to be 256MB.
Throughout, we will see virtually identical result from both the 4 and 8TB capacities of the Novachips Scalar HLNAND SSDs, however, what we really need to be watching is the performance. Unlike ever before in a published independent review, this performance was attained through a single controller solution and requiring no more power than any other SSD to do so. In fact, continuous transfer speed progression as sample data size increases is a sign of a very solid SSD, not to mention great SATA 3 performance.
CRYSTAL DISK BENCHMARK VER. 3.0.3 x64
Crystal Disk Benchmark is visually straightforward, and is used for measuring the speeds at which your storage device reads and writes in both compressible (oFill/1Fill) and random, mostly incompressible, data. Random data is more consistent with everyday use of a computer, such as transferring videos, pictures and music. We run the benchmark twice, using oFill data first, and then proceeding to test with random data. Since results typically return with nearly identical scores, we only include the results for random data samples.
You might notice that the 4TB result on the left was achieved with highly compressible (oFill) data while that of the 8TB capacity on the right uses in compressible data. The truth is that, regardless of sample date type, performance was very consistent and that of a superior SATA 3 SSD.
AS SSD Benchmark uses incompressible data in their testing of SSDs, essentially providing results that would be consistent with using the heaviest workload, thus lower speeds are expected.
Performance of AS SSD appears just as strong in throughput but we did notice that the overall ‘Score’ appeared a bit low, most likely the result of the slightly slower than normal write access time.
Specifications list IOPS of up to 80K, whereas these are somewhat lower. In speaking to Novachips, they explained that this is the result of an early firmware release and that they assured that they would not only reach the 80K mark, but exceed it with the new update.
Considering we haven’t looked at SATA 3 AS SSD Copy Benchmark results in some time, these results are actually pretty good with 400MB/s transfer speeds being the norm for both ISO and Game transfers.
You have to wonder if Samsung, Toshiba, Intel or Micron had an interest in this technology earlier but found issues with it and could not reveal them publicly due to nondisclosure agreements. With a 3-year warranty I have to wonder about the write life of these high-end SSDs. Do they wear level as well as the competition?
We ran the crap out of the 4TB sample and it is now in my base system as the boot drive. It is just as strong as before testing. We would expect a 3-year warranty from any new company, however your mentioning of wear leveling brings up a good point. We are unable to determine total writes as it is not in the SMART attributes and doesn’t appear in any software programs that we might typically use, although some of that same software identifies SSD health as excellent. I am very curious as to the write count of the 4TB drive as we ran it for so long and Novachips is looking into this for us.
what causes the s.m.a.r.t. attributes to not display? is it the firmware of the drives, the software program used, a combination of the 2 or something else?
It is the choice of the manufacturer, however, because HLNAND is simply more than one memory chip, there may be more in play here…waiting for an answer from the manufacturer.
why would a manufacturer not want s.m.a.r.t. attributes to display? also, in this review and others it seems like data is retrieved but, the attribute name is listed as vendor specific. do the vendors have internal names that are not the standard s.m.a.r.t. attribute name? s.m.a.r.t. is a standard that has many attributes covered, why not stick to it?
I cannot answer that and there are several SSD vendors that list only minimal SMART attributes….looking for that F1 value!
No reply from Novachips yet? Probably working up a new marketing spin for their questionable write durability. 🙂
Hi dravo1, I am a technical marketing director of novachips, and thanks for your interests in our SSDs. For the endurance, 4TB has 1.9 PBW and 8TB has 3.8 PBW based on JEDEC standards. For the SMART attributes, we are working on correct display of total writes, but as Les said, it is the choice of manufacturer. Some shows, some doesn’t. Thanks again, and if you have more questions, please contact me at “email@example.com” then I can give you some good DC for your continuous interests and for your test too.
Thanks for the speedy response. I noticed on the website that the price on the 8TB unit was dropped from $8000 to $6000 and is expected to ship in 4-6 weeks. Can you clarify how warranty support will be handled in the US? Since I couldn’t find a corporate physical address listed on the website I had some concerns.
Hi dravo1, all warranty support will be handled by either S. Korea HQ or USA office. Novachips has 3 locations. Please see here; https://www.novachips.com/contact_us.shtml
Any info on power consumption?
We haven’t tested power consumption just yet and, should we proceed with full enterprise reviews, it will be complete. Specifications are listed.
“NAND pricing aside, the difficulty with producing a higher capacity SSD has been the fact that higher volume chips were not yet available and too many memory chips were required to make a notebook SSD feasible.”
But there is plenty of room in a 3.5″ form factor.
There are a lot of systems out there with 3.5″ spinning rust that could accommodate a product like that.
Agree totally and we have seen similar out of AIC retail SSDs but…. the main consideration in the case of a notebook SSD is that of creating a single controller design. With what they have now, they could create a 32TB single controller SSD in the 3.5″ design..nobody else can do this. The problem previously was fitting the memory in a single controller design with acceptable heat dissipation and adequate performance…this would have meant a dual controller design.
Every thing looks good but are the 4k read speeds a little slow for the new ssds?
Your Nvidia GTX980 is very twisted under the load of the PCIX cables and you have nice but wrong wire management . It isn`t good for it for long time. Good luck . Nice review.
Explain further as i don’t see what you are speaking of whatsoever? Are you saying the physical positioning of the wires?
The video card is bended upwards from the PCiX cables from the pict with the case in page 3 in the review .
It is simply the look..card sits fine.
I agree, it looks like you have pulled your PCIex cables for the graphics card alittle to snug, and its bending the card ever so slightly upwards. Which will be pulling stress onto the PCIex slot on the motherboard.
If you mark me an email adress I can show your pictures with further explaining . Or let me put picture on disqus .