Author:
Subject: Storage
Manufacturer: Western Digital

WD Black SN750 NVMe SSD Review

Western Digital today is launching the latest version of its Black-series NVMe SSDs. Like its predecessor, the WD Black SN750 is targeted at gamers, introducing a new "Gaming Mode" that tunes the drive to favor performance over power efficiency.

The drive will be available in two variants — one including a heatsink and one without — in capacities up to 2TB. Western Digital worked with cooling experts EK to design the heatsink.

wd-black-sn750-heatsink-compare.jpg

We had a brief time to review the 1TB non-heatsink model and have some initial performance results to share.

Read on for our review of the WD Black SN750 NVMe SSD.

Subject: Storage
Manufacturer: DeepSpar

Introduction

DeepSpar is the big name in data recovery, making all sorts of data recovery hardware used by many of the big data recovery warehouses. They've recently ventured into getting their recovery hardware into the hands of smaller operations. A couple of years back, they launched the RapidSpar (reviewed here), which offered a nice little package that enabled smaller shops and small businesses to bring a fair chunk of their data recovery operations in-house. While these tools could also be used for data forensics, that's a 'different crowd' really. Forensic operations want to just be able to plug a drive into a write blocker and hit GO on their imaging software. Write blockers are hardware devices that prevent any write requests from ever reaching the storage device, which lets the forensic shop later prove to the court (if needed) that the evidence (source drive) has not been tampered with. Historically, write-blocking hardware has not implemented data recovery functionality, meaning that a drive that times out with read errors would do the same thing when connected via a write blocker. This equates to added headaches for the data forensics guys that are just trying to get their drives imaged and get on with their cases (digging through the image looking for evidence of system compromise, illegal activity, etc). A few hard drive errors throwing a big wrench into the drive imaging process should be a solvable problem, and DeepSpar has stepped in to take a crack at just that:

181217-171214.jpg

Enter the Guardonix. This simple little box sits inline, between the capture PC and the USB device (flash drive, HDD in a USB dock, etc). It naturally performs the typical write blocking functionality expected from the device, but it throws in a round of data recovery functionality as well. Let's look at the simple software interface to help explain further:

2018-12-04-09-42-08.png

Connecting the device to the system the first time mounts a small volume containing software to get up and running. The app handles firmware and driver updates within its own interface, making things simple. DeepSpar recommends using the Asmedia USB3 controller on your system board for best possible compatibility, with the vendor driver installed (don't use the Microsoft InBox driver - download the USB 3 controller driver from your motherboard/laptop vendor). The same Asmedia controller recommendation applies to the use of a USB 3 dock connected to the Guardonix - Asmedia controllers best support the necessary device resets necessary for the data recovery tricks it is capable of.

2018-12-04-16-05-12.png

Once up and running, there is a series of configuration and data recovery options available. Logging options are extensive and necessary for inclusion in forensic reports. The 'PRO' settings (added cost) enable greater control of read timeouts, allow file system mounting, and enable some cool tricks like the ability to fake write attempts instead of replying with 'write denied' errors.

2018-12-04-16-15-50.png

Above is a typical setup showing the whole operation in action. I'm using a simple data recovery app instead of ($$$) dedicated forensic software, but the principles are the same.

2018-12-04-16-09-22.png

Here's a look at the Guardonix output while pushing through a drive containing read errors. Note that once past the errors, we see full speed of the source drive (a 2.5" SATA HDD in this case). The configurable timeouts are 1.25 (short), 4 (medium), and 10 (long) seconds. If the drive fails to come back after each reset attempt, the Guardonix is able to repower the drive a few seconds later. The error handling is definitely robust. I was able to go as far as to remove and reinsert the drive from the dock during imaging, and it just picked right back up from where it left off. Here's the Guardonix demo video:

Pricing and conclusion:

The base Guardonix goes for $320 at the time of this writing, with the PRO add-on features tacking on another $470. This may seem steep, but compared to other write-blocking hardware I've seen in the past, it's about average, with the PRO add-on tacking on some data recovery options capabilities not normally possible with simpler write blockers. So long as you are ok with only USB and docked SATA connectivity, that $470 is actually a good deal compared to the pricier RapidSpar (but not nearly as feature-packed).

*edit* Prices adjusted slightly after publishing. Article updated to reflect current prices.

PCPerEditorsChoicePNG-300.png

Overall this is good stuff from DeepSpar. I'm glad to see them venturing into the forensics space, as that arena could stand to benefit from less frustration during their imaging operations. I know it would have saved me a bunch of time and headaches back when I was dealing with data forensics!

Subject: Storage
Manufacturer: Crucial

Introduction

Once we saw Intel launch QLC flash installed in their recent 660p M.2 part, I had a feeling that Micron would not be far behind, and that feeling has been confirmed with the launch of the Crucial P1 M.2 SSDs:

181129-144634.jpg

Both the 500GB and 1TB models are single sided. The 2TB (not yet released) will likely have packages installed at the rear.

181129-144503.jpg

No surprises with the packaging. Does the job just fine.

specs.png

Specs are also reasonably standard for an NVMe SSD at this point, though we do see a bit more of a falloff at the lower capacities here. This is partially due to the use of QLC flash, even though these specs are likely assuming full use of the available SLC cache. Since QLC allows for higher capacity per die, that translates to fewer dies for a given SSD total capacity, which lowers overall performance even at SLC speeds. This is a common trait/tradeoff for the use of higher capacity dies.

Read on for our review of the Crucial P1!

Subject: Storage
Manufacturer: Samsung

Introduction

For years we have been repeatedly teased by Samsung. Launch after successful launch in the consumer SSD space, topping performance charts nearly every time, but what about enterprise? Oh sure, there were plenty of launches on that side, with the company showing off higher and higher capacity 2.5" enterprise SSDs year after year, but nobody could ever get their hands on one, and even the higher tier reviewers could not confirm Samsung's performance claims. While other SSD makers would privately show me performance comparison data showing some Samsung enterprise part walking all over their own enterprise parts, there was not much concern in their voices since only a small group of companies had the luxury of being on Samsung's short list of clients that could purchase these products. Announcements of potentially groundbreaking products like the Z-SSD were soured by press folk growing jaded by unobtanium products that would likely never be seen by the public.

181207-183150.jpg

Samsung has recently taken some rather significant steps to change that tune. They held a small press event in September, where we were assured that enterprise SSD models were coming to 'the channel' (marketing speak for being available on the retail market). I was thrilled, as were some of the Samsung execs who had apparently been pushing for such a move for some time.

As a next step towards demonstrating that Samsung is dedicated to their plan, I was recently approached to test a round of their upcoming products. I accepted without hesitation, have been testing for the past week, and am happy to now bring you detailed results obtained from testing eight different SSDs across four enterprise SSD models. Testing initially began with three of the models, but then I was made aware that the Z-SSD was also available for testing, and given the potential significance of that product and its placement as a competitor to 3D XPoint products like Intel's Optane, I thought it important to include that testing as well, making this into one heck of a Samsung Enterprise SSD roundup!

One large note before we continue - this is an enterprise SSD review. Don't expect to see game launches, SYSmark runs, or boot times here. The density of the data produced by my enterprise suite precludes most easy side-by-side comparisons, so I will instead be presenting the standard full-span random and sequential results for fully conditioned drives, marking the rated specs on the charts as we go along. High-Resolution QoS will also be used throughout, as Quality of Service is one of the most important factors to consider when choosing SSDs for enterprise usage. In short, the SSDs will be tested against their own specifications, with the exception of some necessary comparisons between the Samsung Z-SSD and the Intel Optane SSD DC P4800X which I will squeeze in towards the end of this very lengthy and data-dense review.

Read on for our full review of Samsung's new enterprise products!

Subject: Storage
Manufacturer: Samsung
Tagged: ssd, slc, sata, Samsung, QLC, 860 QVO, 2.5

Introduction

With recent QLC SSD launches like the Intel 660P and Crucial P1, folks may have been wondering when Samsung would jump on the QLC bandwagon. I'm happy to report that your wait is now over:

181127-094929.jpg

Samsung has opted to name this new product 'QVO'. The Q presumably stems from the use QLC flash, which can store four bits per cell.

turbowrite.png

While QLC writes are far slower than what we are used to seeing from a modern SSD, SLC caching is the answer to bridging that performance gap. The 860 QVO employs Samsung's Intelligent TurboWrite, which has a minimum 6GB static cache plus a dynamic cache of up to 72GB. This dynamic cache varies based on available QLC area which can be reconfigured to operate in SLC mode. Do note the 'After TubroWrite' speeds of 80 and 160 MB/s - that's the raw QLC speeds that you will see if the cache has been exhausted during an extended write period.

specs.png

The rest of the specs are about what we expect from a SATA SSD, but I do have a concern with those QD1 4KB random read ratings of only 7,500 IOPS. This is on the low side especially for Samsung, who typically dominate in low QD random read performance.

Read on for the full review!

Subject: Storage
Manufacturer: Drobo

Introduction

It has been 9 years since I reviewed the DroboPro. For its time, that product was a beast of a device, with the closest to a 'set it and forget it' RAID implementation I had ever seen. It was also robust enough to shrug off any combination of power loss and pulling (failing) disks that I could throw at it. The ease of use/durability combination was a good formula for Drobo that has now lasted over a decade. The main hurdles over the years have been more on the performance side of things. The original DroboPro was indeed quicker than previous Drobos and other competing models, but competition quickly surpassed them in performance. Later Drobo models brought decent performance and capabilities for competitive prices (like the Drobo 5C), but we haven't had a worthy successor to the original DroboPro. They came close in the form of the B810 series, but those were still limited by Gigabit links. We needed the 8-bay form factor to have a larger pipe - and now we do:

drobo8d-4-.jpg

Read on for our review of the Drobo 8D

Subject: Storage
Manufacturer: MyDigitalDiscount

MyDigitalDiscount doesn't seem to have been satisfied with their performance BPX line or their value SBX line, and have now launched a BPX Pro, which looks to carry the budget pricing of the SBX while offering performance *higher* than the original BPX. How much faster is the BPX Pro than the BPX? That's what this review sets to find out, so let's get to it.

180926-212918.jpg

Specs:

specs.png

Internals:

180926-215204.jpg

With the label peeled back, we find the Phison E12, coupled to Toshiba BiCS3 TLC NAND. PCBs are single sided up to 480GB. 960GB (and 2TB - not in this review) employ a different PCB with additional DRAM and two more flash packages on the flip side.

Read on for the results and conclusion!

Subject: Storage
Manufacturer: Intel
Tagged: U.2, ssd, Optane, Intel, HHHL, AIC, 905P

Review

Intel just sent over a note that they have officially launched the 1.5TB capacity for the Optane SSD 905P (for both HHHL and U.2 form factors). We'd been expecting this for a while now, considering we had tested a full system incorporating the U.2 version of this very capacity two months ago. That system has now been given away, but I borrowed the SSD while Ken was tearing down the system for his review. With the product now officially launched, I thought it appropriate to take a quick look at this higher capacity part, both inside and out.

Outside

180717-180547.jpg

180717-180834.jpg

Inside

180717-182158.jpg

7 packages on one side of a single PCB. This is unexpected for a U.2 SSD since there is usually some sort of folded-over PCB sandwich, which doubles the available area for packages. Odd finding a single PCB here given the large 1.5TB capacity combined with XPoint dies only holding 16GB each.

180717-182742.jpg

7 more packages along with the now standard XPoint controller. No DRAM necessary because, well, XPoint can easily pull double duty in that respect. Alright, so we have 1.5TB spread across only 14 packages. Throughout every Intel SSD we have ever laid our hands on for review, we've never seen *any* product (NAND or 3D XPoint) stack more than 4 dies per package. Had Intel stuck with that limit here, we would only have a maximum raw media capacity of 896GB. This is a 1.5TB SSD, so the only possible answer here is that we apparently have the first 8-die-per-package SSD to come out of Intel.

Read on for the test results!

Subject: Storage
Manufacturer: Toshiba

Today we take a quick look at an update to Toshiba's line of OEM SSDs. The first product to employ 96-layer 3D TLC NAND, the XG6:

180906-122143.jpg

I'm going to keep this one brief since this is to be an OEM-only product that is not expected to be available in retail channels. It's good to have some results out there since it will appear in many laptops and may result in the creation of a parallel retail product at some point in the future.

Specs:

specs.png

Internals (sorta):

180906-122541.jpg

180906-122501.jpg

XG6 at the top. XG5 at the bottom. Pretty much identical with the labels removed, the major exception being the flash memory, which is now 96-layer BiCS.

Read on for the results and conclusion!

Author:
Subject: Storage
Manufacturer: Synology

Synology DS1618+ Review

Synology's 2018 product lineup includes a new network-attached storage device that merges a prosumer price point with an enterprise-level (albeit entry-level enterprise) feature set. The Synology DS1618+ is a six-bay NAS sporting a quad-core Intel processor, up to 32GB of DDR4 memory, and, most importantly, a PCIe expansion slot.

It's that last key feature -- a PCIe 3.0 x8 (x4 link) slot -- that really makes the DS1618+ interesting, as it lets users optionally expand the capabilities of the device with add-ons like NVMe flash adapters or 10GbE ports. Synology has long offered PCIe expansion capabilities in their products, but they've generally been limited to the much costlier enterprise models. With the costs of 10-gigabit networking continuing to fall, however, the DS1618+ is perfectly timed to bring ultra-fast networked storage to home power users.

synology-ds1618+-1.jpg

Synology loaned us a DS1618+ for review, and we've spent the last few weeks testing it with our existing 10GBase-T network.

Read on to find out how this new NAS performs, and take a look at some new software-based features that Synology is bringing to the home.

Subject: Storage
Manufacturer: Samsung

Introduction, Specifications, and Packaging

Samsung has been in the portable SSD business for a good while now. They released their T1 back in 2015, with the T3 and T5 coming in at a yearly cadence. Keeping with tradition, today we see the release of a new model on a new interface - Samsung's new Portable SSD X5:

180828-085034b.jpg

(970 EVO included for scale)

While the 'T' branded predecessors were USB 3.0 and 3.1 (Gen1 - limited to 5Gbps), Samsung has now jumped onto the Thunderbolt 3 bandwagon, taking a firmware-tweaked (for encryption) 970 EVO and placing it behind an Intel Alpine Ridge DSL6340 Thunderbolt 3 controller.

Specifications

specs.png

Specs of note are the nearly 3GB/s sequential read speed. 2.3GB/s writes are nothing to sneeze at, either. No random performance noted here, but we will fix that with our test suite later on in the article.

Packaging

180828-084958.jpg

Nice packaging and presentation.

Read on for our review of the Samsung Portable SSD X5!

Author:
Subject: Storage
Manufacturer: Various

We aim to find out

Back in April of this year we first took a look at the storage performance of the then-new X470 chipset for the 2nd generation of Ryzen processors. Allyn dove into NVMe RAID performance and also a new offering called StoreMI. Based on a software tiered storage solution from Enmotus, StoreMI was a way for AMD to offer storage features and capabilities matching or exceeding that of Intel’s mainstream consumer platforms without the need for extensive in-house development.

Allyn described the technology well:

AMD has also launched their answer to Intel RST caching. StoreMI is actually a more flexible solution that offers some unique advantages over Intel. Instead of copying a section of HDD data to the SSD cache, StoreMI combines the total available storage space of both the HDD and SSD, and is able to seamlessly shuffle the more active data blocks to the SSD. StoreMI also offers more cache capacity than Intel - up to 512 256GB SSD caches are possible (60GB limit on Intel). Lastly, the user can opt to donate 2GB of RAM as an additional caching layer.

slide1.png

We recently did some testing with StoreMI after the release of the 2nd generation Threadripper processor evaluation was out of the way, just to get a feel for the current state of the software offering and whether or not it could really close the gap with the Optane caching solutions that Intel was putting forward for enthusiasts.

Continue reading our look at StoreMI and Optane Memory Caching!

Subject: Storage
Manufacturer: Intel
Tagged: ssd, SMI, QLC, Intel, 660p, 512GB, 3d nand, 2TB, 1TB

Introduction, Specifications, and Packaging

Introduction:

Flash Memory Summit 2018 is on, and it's rapidly looking like the theme of the year is 'QLC'. QLC stands for Quad Level Cell, which is a bit of a misnomer since there are actually 16 voltage levels of a QLC cell - the 'quad' actually relating to the four bits of data that can be stored at any specific location.

Micron QLC.jpg

Doubling the number of voltage states allows you to store 33% more data in a given number of flash cells, but comes at a cost. The tighter voltage tolerances required and higher sensitivity to cell leakage mean that endurance ratings cannot be as high as TLC or MLC, and programming (writing) requires greater voltage precision, meaning slower writes. Reads may also see a slight penalty since it is more difficult to discriminate more finely grained voltage thresholds. SSD makers have been trying to overcome these hurdles for years, and it seems that Intel is now the first to crack the code, launching their first mainstream QLC SSD:

180805-213321.jpg

Specifications:

specs.png

Specifications are not earth shattering but respectable for a budget-minded NVMe SSD. 1.8GB/s sequentials and 250,000 IOPS fall well within NVMe territory. The write figures may be higher than expected given this article intro, but Intel has a few tricks up their sleeves here that help them pull this off:

cache.png

While not specifically called out in the specs, Intel has implemented a large dynamic write cache to help overcome slower QLC media write speeds. The idea here is that in the vast majority of typical usage scenarios, the user should never see QLC speeds and will only ever be writing to SLC. The dynamic cache is created by simply operating sections of the QLC media in SLC mode (1TB of QLC = 256GB of SLC). Intel could have gone higher here, but doing so would more negatively impact endurance since erasing blocks of cells wears the flash similarly regardless of the mode it is currently operating in.

Packaging:

180805-213043.jpg

Simple packaging. Nothing to write home about.

Read on for our full review of the Intel SSD 660p 1TB QLC SSD!

Subject: Storage
Manufacturer: Toshiba

Toshiba RC100 240GB/480GB SSD Review

Introduction:

Budget SSDs are a tough trick to pull off. You have components, a PCB, and ultimately assembly - all things which costs money. Savings can be had when major components (flash) are sourced from within the same company, but there are several companies already playing that game. Another way to go is to reduce PCB size, but then you can only fit so much media on the same board as the controller and other necessary parts. Samsung attempted something like this with its PM971, but that part was never retail, meaning the cost savings were only passed to the OEMs implementing that part into their systems. It would be nice if a manufacturer would put a part like this into the hands of regular customers looking to upgrade their system on a budget, and Toshiba is aiming to do just that with their new RC100 line:

DSC04992.JPG

Not only did Toshiba stack the flash and controller within the same package, they also put that package on an M.2 2242 PCB. No need for additional length here really, and they could have possibly gotten away with M.2 2230, but that might have required some components on the back side of the PCB. Single-sided PCBs are cheaper to produce vs. a PCB that is 12mm longer, so the design decision makes sense here.

Specifications:

specs.png

Bear in mind these are budget parts and small ones at that. The specs are decent, but these are not meant to be fire-breathing SSDs. The PCIe 3.0 x2 interface will be limiting things a bit, and these are geared more towards power efficiency with a typical active power draw of only 3.2 Watts. While we were not sampled the 120GB part, it does appear to maintain decent specified performance despite the lower capacity, which is a testament to the performance of Toshiba's 64-layer 3D BiCS TLC flash.

Packaging:

DSC04989.JPG

Not much to talk about here. Simple, no frills, SSD packaging. Just enough to ensure the product arrives undamaged. Mission accomplished.

Read on for our full review of the Toshiba RC100 240GB and 480GB SSDs!

Author:
Subject: Storage
Manufacturer: Intel

A little Optane for your HDD

Intel's Optane Memory caching solution, launched in April of 2017, was a straightforward feature. On supported hardware platforms, consisting of 7th and 8th generation Core processor-based computers, users could add a 16 or 32gb Optane M.2 module to their PC and enable acceleration for their slower boot device (generally a hard drive). Beyond that, there weren't any additional options; you could only enable and disable the caching solution. 

However, users who were looking for more flexibility were out of luck. If you already had a fast boot device, such as an NVMe SSD, you had no use for these Optane Memory modules, even if you a slow hard drive in their system for mass storage uses that you wanted to speed up.

DSC04972.JPG

At GDC this year, Intel alongside the announcement of 64GB Optane Memory modules, announced that they are bringing support for secondary drive acceleration to the Optane Memory application.

Now that we've gotten our hands on this new 64GB module and the appropriate software, it's time to put it through its paces and see if it was worth the wait.

Performance

The full test setup is as follows:

Test System Setup
CPU

Intel Core i7-8700K

Motherboard Gigabyte H370 Aorus Gaming 3 
Memory

16GB Crucial DDR4-2666 (running at DDR4-2666)

Storage

Intel SSD Optane 800P 

Intel Optane Memory 64GB and 1TB Western Digital Black

Sound Card On-board
Graphics Card NVIDIA GeForce GTX 1080Ti 11GB
Graphics Drivers NVIDIA 397.93
Power Supply Corsair RM1000x
Operating System Windows 10 Pro x64 RS4

optanecache-5.png

In coming up with test scenarios to properly evaluate drive caching on a secondary, mass storage device, we had a few criteria. First, we were looking for scenarios that require lots of storage, meaning that they wouldn't fit on a smaller SSD. In addition to requiring a lot of storage, the applications must also rely on fast storage. 

Click here to continue reading our look at accelerating secondary drives with Optane

Author:
Subject: Storage
Manufacturer: ASUS

Is it a usable feature?

EDIT: We've received some clarification from Intel on this feature:

"The feature is actually apart of RST. While this is a CPU-attached storage feature, it is not VROC. VROC is a CPU-attached PCIe Storage component of the enterprise version of the product, Intel RSTe. VROC requires the new HW feature Intel Volume Management Device (Intel VMD) which is not available on the Z370 Chipset.

The Intel Rapid Storage Technology for CPU-attached Intel PCIe Storage feature is supported with select Intel chipsets and requires system manufacturer integration. Please contact the system manufacturer for a list of their supported platforms."

While this doesn't change how the feature works, or our testing, we wanted to clarify this point and have removed all references to VROC on Z370 in this review.

While updating our CPU testbeds for some upcoming testing, we came across an odd listing on the UEFI updates page for our ASUS ROG STRIX Z370-E motherboard.

asus-uefi.png

From the notes, it appeared that the release from late April of this year enables VROC for the Z370 platform. Taking a look at the rest of ASUS' Z370 lineup, it appears that all of its models received a similar UEFI update mentioning VROC. EDIT: As it turns out, while these patch notes call this feature "VROC", it is officially known as "Intel Rapid Storage Technology for CPU-attached Intel PCIe Storage " and slightly different than VROC on other Intel platforms.

While we are familiar with VROC as a CPU-attached RAID technology for NVMe devices on the Intel X299 and Xeon Scalable platforms, it has never been mentioned as an available option for the enthusiast grade Z-series chipsets. Could this be a preview of a feature that Intel has planned to come for the upcoming Z390 chipset?

Potential advantages of a CPU-attached RAID mode on the Z370 platform mostly revolve around throughput. While the chipset raid mode on the Z370 chipset will support three drives, the total throughput is limited to just under 4GB/s by the DMI 3.0 link between the processor and chipset.

Like we've seen AMD do on their X470 platform, CPU-attached RAID should scale as long as you have CPU-connected PCI-Express lanes available, and not being used by another device like a GPU or network card.

First, some limitations.

Primarily, it's difficult to connect multiple NVMe devices to the CPU rather than the chipset on most Z370 motherboards. Since the platform natively supports NVMe RAID through the Z370 chipset, all of the M.2 slots on our Strix Z370-E are wired to go through the chipset connection rather than directly to the CPU's PCIe lanes.

IMG_8161.jpg

To combat this, we turned to the ASUS Hyper M.2 X16 card, which utilizes PCIe bifurcation to enable usage of 4 M.2 devices via one PCI-E X16 slot. Luckily, ASUS has built support for bifurcation, and this Hyper M.2 card into the UEFI for the Strix Z370-E.

180523163122.png

Aiming to simplify the setup, we are using the integrated UHD 620 graphics of the i7-8700K, and running the Hyper M.2 card in the primary PCIe slot, usually occupied by a discrete GPU.

Continue reading our look at CPU-attached NVMe RAID on Z370 motherboards from ASUS!

Subject: Storage
Manufacturer: ADATA

Introduction, Specifications and Packaging

Introduction:

ADATA has a habit of occasionally coming out of the woodwork and dropping a great performing SSD on the market at a highly competitive price. A few of their recent SATA SSD launches were promising, but some were very difficult to find in online stores. This has improved more recently, and current ADATA products now enjoy relatively wide availability. We were way overdue for an ADATA review, and the XPG SX8200 is a great way for us to get back into covering this company's offerings:

180523-114049_2.jpg

For those unaware, XPG is a computing-related sub-brand of ADATA, and if you have a hard time finding details for these drives online, it is because you must look at their dedicated xpg.com domain. Parent brand ADATA has since branched into LED lighting and other industrial applications, such as solid-state drive motor controllers and the like. Some PC products bear the ADATA name, such as USB drives and external hard drives.

Ok, enough rambling about other stuff. Let's take a look at this XPG SX8200!

Specifications:

specs.png

Specs are mostly par for the course here, with a few notable exceptions. The SX8200 opts for a lower available capacity than you would typically see with a TLC SSD. That means a slight bump in OP, which helps nudge endurance higher due to that sacrifice. Another interesting point is that they have simply based their specs of 'up to 3200 MB/s read / 1700 MB/s write' from direct measurements of common benchmarking software. While the tests they used are 'short-run' benchmarks that will remain within the SLC cache of these SSDs, I do applaud ADATA for their openness here.

Packaging:

180523-114049.jpg

Straightforward packaging with a small bonus inside - in the form of a thermal adhesive-backed aluminum heat spreader. This is included as an option since some folks may have motherboards with integrated heat spreading M.2 socket covers or laptops with extremely tight clearances, and the added thickness may not play nicely in those situations.

Read on for our full review of the ADATA XPG SX8200 M.2 NVMe SSD!

Subject: Storage
Manufacturer: Intel

Introduction, Specifications and Packaging

Introduction:

Over the past couple of days, we saw some rumors and e-tailer appearances of the Intel SSD 905P. Essentially an incremental upgrade to the 900P, with a few notable differences. Specs see a slight bump across the board, as do capacities, but the most striking difference is Intel’s apparent choice to move forward with the blue-LED enabled design seen in a press deck slide that began circulating last year:

intel-optane-ssd-900p.jpg

That upper right design seemed pretty cool at the time, and I never thought we would see it materialize, but less than 24 hours ago this arrived at the office:

180502-163726.jpg

Note: The color is user adjustable - we just don't have the software for it yet.

*edit* colors are configurable via command line, using the most recent SSD toolbox app. The possible colors are limited (literally red/green/blue/off - that's it), but I've confirmed that the setting does persist after reboot / power cycling / changing systems. This is a welcome change over other RGB-enabled components that require software to always be installed to control (or even turn off) lighting. Here's a look at the other two colors:

180502-163529.jpg

180502-163629.jpg

*end edit*

Well now that it’s here, let’s see what it can do!

Read on for our full review of the Intel SSD 905P 960GB!

Subject: Storage
Manufacturer: Samsung

Introduction, Specifications and Packaging

Introduction:

We have been overdue for a Samsung NVMe SSD refresh, and with the launch of their 860 PRO and EVO back in January, folks have been itching for the 970's to come out. The 950 and 960 (PRO) lines were separated by about a year, but we are going on 18 months since the most recent 960 EVO launch. Samsung could afford to wait a bit longer since the 960 line already offered outstanding performance that remained unmatched at the top of our performance charts for a very long time. Recently, drives like the WD Black have started catching up, so it is naturally time for Samsung to keep the competition on their toes:

180423-175345.jpg

Today we will look at most of the Samsung 970 PRO and EVO lineup. We have a bit of a capacity spread for the EVO, and a single PRO. Samples are hard to come by so far since Samsung opted to launch both lines at the same time, but we tried to get the more common capacities represented. EVO 2TB and PRO 1TB data will have to come at a later date.

Specifications:

specs-PRO.png

specs-EVO.png

Specs come in at just slightly higher than the 960 lines, with some welcome additions like OPAL and encrypted drive (IEEE1667) support, the latter being suggested but never making it into the 960 products. Another welcome addition is that the 970 EVO now carries a 5-year warranty (up from 3).

specs-EVO-2.png

The 970 EVO includes 'Intelligent TurboWrite', which was introduced with the 960 line. This setup maintains a static SLC area and an additional 'Intelligent' cache that exists if sufficient free space is available in the TLC area.

Packaging:

Packaging is in line with the previous 960 series parts. Nice packaging. If it ain't broke, don't fix it.

180423-175542.jpg

Read on for our full review of the Samsung 970 PRO and EVO!

Subject: Storage
Manufacturer: AMD
Tagged: x470, StoreMI, raid, NVMe, amd

NVMe RAID and StoreMI

With Ken testing all of the new AMD X470 goodness that we had floating around the office here at PCPer, I snuck in some quick storage testing to get a look at just how the new platform handled a typical power user NVMe RAID configuration. We will be testing a few different platform configurations:

  • ASUS Z270 w/ 7700K
    • 1x SSD behind chipset (PCH)
    • 2x SSD (RAID-0) behind chipset (PCH)
    • 1x SSD directly connected to CPU
  • AMD X470 w/ 2600X
    • 1x SSD via RAIDXpert bottom driver
    • 2x SSD (RAID-0) via RAIDXpert
    • 1x SSD via MS InBox NVMe driver

For the AMD system we tested, all M.2 ports were direct connected to the CPU. This should be the case for most systems since the AMD chipset has only a PCIe 2.0 x4 link which would cut most NVMe SSD bandwidth in half if passed through it. The difference on AMD is that installing the RAIDXpert software also installs a 'bottom driver' which replaces the Windows NVMe driver, while Intel's RST platform handles this process more in the chipset hardware (but is limited to PCIe 3.0 x4 DMI bandwidth). Now onto the results:

Random Read IOPS

random.png

For random IO, we see expected scaling from AMD, but do note that IOPS comes in ~40% lower than the same configuration on Intel's platform. This is critical as much of the IO seen in general use is random reads at lower queue depths. We'd like to see AMD doing better here, especially in the case where a single SSD was operating without the interference of the RAIDXpert driver, which was better, but still not able to match Intel.

Random Read Latency

latency.png

This latency chart should better explain the IOPS performance seen above. Note that the across the board latency increases by ~10us on the X470 platform, followed by another ~20us when switching to the RAIDXpert driver. That combined ~30us is 50% of the 60us QD1 latency seen the Z270 platform (regardless of configuration).

Sequential Read

sequential.png

Ok, now we see the AMD platform stretch its legs a bit. Since Intel NVMe RAID is bottlenecked by its DMI link while AMD has all NVMe SSDs directly connected to the CPU, AMD is able to trounce Intel on sequentials, but there is a catch. Note the solid red line, which means no RAIDXpert software. That line tracks as it should, leveling off horizontally at a maximum for that SSD. Now look at the two dashed red lines and note how they fall off at ~QD8/16. It appears the RAIDXpert driver is interfering and limiting the ultimate throughput possible. This was even the case for a single SSD passing through the RAIDXpert bottom driver (configured as a JBOD volume).

StoreMI

2018-04-19-08-49-39.png

AMD has also launched their answer to Intel RST caching. StoreMI is actually a more flexible solution that offers some unique advantages over Intel. Instead of copying a section of HDD data to the SSD cache, StoreMI combines the total available storage space of both the HDD and SSD, and is able to seamlessly shuffle the more active data blocks to the SSD. StoreMI also offers more cache capacity than Intel - up to 512 256GB SSD caches are possible (60GB limit on Intel). Lastly, the user can opt to donate 2GB of RAM as an additional caching layer.

2018-04-19-08-49-55.png

AMD claims the typical speedups that one would expect with an SSD caching a much slower HDD. We have done some testing with StoreMI and can confirm the above slide's claims. Actively used applications and games end up running at close to SSD speeds (after the first execution, which comes from the HDD). StoreMI is not yet in a final state, but that is expected within the next week or two. We will revisit that topic with hard data once we have the final shipping product on-hand.