Subject: Storage | August 18, 2015 - 02:20 PM | Allyn Malventano
Tagged: XPoint, ssd, Optane, Intel, IDF 2015
Just three weeks ago, we reported 3D XPoint Technology. This was a 2-layer stack of non-volatile memory that couples the data retention of NAND flash memory with speeds much closer to that of DRAM.
The big question at that time was less about the tech and more about its practical applications. Ryan is out covering IDF, and he just saw the first publically announced application by Intel:
Intel Optane Technology is Intel’s term for how they are going to incorporate XPoint memory dies into the devices we use today. They intend to start with datacenter storage and work their way down to ultrabooks, which means that XPoint must come in at a cost/GB closer to NAND than to DRAM. For those asking specific performance figures after our earlier announcement, here are a couple of performance comparisons between an SSD DC P3700 and a prototype SSD using XPoint:
At QD=8, the XPoint equipped prototype comes in at 5x the performance of the P3700. The bigger question is how about QD=1 performance, as XPoint is supposed to be far less latent than NAND?
Yes, you read that correctly, that’s 76k IOPS at QD=1. That means only issuing the SSD one command at a time, waiting for a reply, and only then issuing another command. Basically the worst case for SSD performance, as no commands are stacked up in the queue to enable parallelism to kick in and increase overall throughput. For comparison, SATA SSDs have a hard time maintaining that figure at their maximum queue depths of 32.
Exciting to see a follow-on announcement so quickly after the announcement of the technology itself, but remember that Intel did state ‘2016’ for these to start appearing, so don’t put off that SSD 750 purchase just yet.
More to follow as we continue our coverage of IDF 2015!
Subject: Storage | August 14, 2015 - 04:44 PM | Allyn Malventano
Tagged: FMS 2015, silicon motion, SM2260, SM2256, SM2246EN, pcie, NVMe, ssd, controller
We’ve reviewed a few Silicon Motion SSDs in the past (Angelbird | Corsair Force LX | Crucial BX100), and I have always been impressed with their advances in SSD controller technology. Their SM2246EN SATA controller was launched two years ago, and strived to be a very efficient and performant unit. Based on our reviews that turned out to be true, and this allowed Silicon Motion to slide into the void left by SandForce, who repeatedly delayed their newer developments and forced the many companies who were sourcing their parts to look elsewhere.
The many SSDs using Silicon Motion’s SM2246EN controller.
Silicon motion pushed this further with their SM2256, which we first saw at the 2014 Flash Memory Summit and later saw driving SLC/TLC hybrid flash at this past Consumer Electronics Show. While the SM2256 makes its way into more and more products, I was glad to see an important addition to their lineup at this year’s FMS:
Finally we see Silicon Motion doing a PCIe controller! This is the SM2260, seen here in the M.2 form factor…
…and here in SATA Express. While the latter will likely not be as popular due to the more limited PCIe lanes present in SATA Express, I’m sure we will see this controller appearing in many PCIe devices very soon. The stated performance figures may be a bit shy of currently comparing SSDs like the Intel SSD 750 and Samsung SM951, but with the recent introduction of Z170 motherboards and RST PCIe RAID, it is now easier to RAID a smaller capacity pair of these devices, increasing the performance of slower units. Further, the point of the SM2260 is likely to get a low cost NVMe PCIe SSD controller into the hands of SSD makers, which can only mean good things for those looking to make the move away from SATA.
I’ve included Silicon Motion’s FMS press blast after the break.
Subject: Storage | August 13, 2015 - 08:12 PM | Allyn Malventano
Tagged: FMS 2015, ssd, sata, SAS, pcie, NVMe, novachips, HLNAND, flash
It turns out Samsung wasn’t the only company to have 16TB SSDs at Flash Memory Summit after all:
Now that I’ve got your attention, Novachips is an SSD company that does not make their own flash, but I would argue that they make other peoples flash better. They source flash memory wafers and dies from other companies, but they package it in a unique way that enables very large numbers of flash dies per controller. This is handy for situations where very large capacities per controller are needed (either physically or logically).
Normally there is a limit to the number of dies that can communicate on a common bus (similar limits apply to DRAM, which is why some motherboards are picky with large numbers of DIMMs installed). Novachips gets around this with an innovative flash packaging method:
The 16-die stack in the above picture would normally just connect out the bottom of the package, but in the Novachips parts, those connections are made to a microcontroller die also present within the package. This part acts as an interface back to the main SSD controller, but it does so over a ring bus architecture.
To clarify, those 800 or 1600 MB/sec figures on the above slide are the transfer rates *per ring*, and Novachips controller is 8-channels, meaning the flash side of the controller can handle massive throughputs. Ring busses are not limited by the same fanout requirements seen on parallel addressed devices, which means there is no practical limit to the number of flash packages connected on a single controller channel, making for some outrageous amounts of flash hanging off of a single controller:
That’s a lot of flash on a single card (and yes, the other side was full as well).
The above pic was taken at last years Flash Memory Summit. Novachips has been making steady progress on controller development as well. Here is a prototype controller seen last year running on an FPGA test system:
…and this year that same controller had been migrated to an ASIC:
It’s interesting to see the physical differences between those two parts. Note that both new and old platforms were connected to the same banks of flash. The newer photo showed two complete systems – one on ONFi flash (IMFT Intel / Micron) and the other on Toggle Mode (Toshiba). This was done to demonstrate that Novachips HLNAND hardware is compatible with both types.
Novachips also had NVMe PCIe hardware up and running at the show.
Novachips was also showing some impressive packaging in their SATA devices:
At the right was a 2TB SATA SSD, and at the left was a 4TB unit. Both were in the 7mm form factor. 4TB is the largest capacity SSD I have seen in that form factor to date.
Novachips also makes an 8TB variant, though the added PCB requires 15mm packaging.
All of this means that it is not always necessary to have huge capacity per die to achieve a huge capacity SSD. Imagine very high capacity flash arrays using this technology, connecting a single controller to a bank of Toshiba’s new QLC archival flash or Samsung’s new 256Gbit VNAND. Then imagine a server full of those PCIe devices. Things certainly seem to be getting big in the world of flash memory, that’s for sure.
Even more Flash Memory Summit posts to follow!
Subject: Storage | August 11, 2015 - 08:40 PM | Allyn Malventano
Tagged: toshiba, ssd, FMS 2015, flash, BiCS, Archive, Archival, 3d
We occasionally throw around the '3-bit MLC' (Multi Level Cell) term in place of 'TLC' (Triple Level Cell) when talking about flash memory. Those terms are interchangeable, but some feel it is misleading as the former still contains the term MLC. At Toshiba's keynote today, they showed us why the former is important:
Photo source: Sam Chen of Custom PC Review
That's right - QLC (Quadruple Level Cell), which is also 4-bit MLC, has been mentioned by Toshiba. As you can see at the right of that slide, storing four bits in a single flash cell means there are *sixteen* very narrow voltage ranges representing the stored data. That is a very hard thing to do, and even harder to do with high performance (programming/writing would take a relatively long time as the circuitry nudges the voltages to such a precise level). This is why Toshiba pitched this flash as a low cost solution for archival purposes. You wouldn't want to use this type of flash in a device that was written constantly, since the channel materials wearing out would have a much more significant effect on endurance. Suiting this flash to be written only a few times would keep it in a 'newer' state that would be effective for solid state data archiving.
The 1x / 0.5x / 6x figures appearing in the slide are meant to compare relative endurance to Toshiba's own planar 15nm flash. The figures suggest that Toshiba's BiCS 3D flash is efficient enough to go to QLC (4-bit) levels and still maintain a higher margin than their current MLC (2-bit) 2D flash.
More to follow as we continue our Flash Memory Summit coverage!
Subject: Storage | August 6, 2015 - 06:37 PM | Allyn Malventano
Tagged: SSD 750, ssd, pcie, NVMe, Intel
A new 800GB SKU of the Intel SSD 750 Series of PCIe SSDs was hinted at with the Skylake launch press materials, and it appears to have been a reality:
They may not be on the shelves yet, but appearing on ARK is a pretty good indicator that these are coming soon. We don't have pricing yet, but I would suspect a cost/GB closer to the 1.2TB model than to the 400GB model, which should come in at around $700. Performance sees a slight hit for the 800GB model, likely since this is an 'uneven' number of dies for the design of the SSD DC P3500 line it was based on.
Which would you prefer - a single 800GB or a pair of 400GB SSD 750's in a RAID (now that it is possible)?
Subject: Storage | July 20, 2015 - 01:01 PM | Allyn Malventano
Tagged: vnand, ssd, SM863, sata, Samsung, PM863
...you get the Samsung PM863 and SM863 lines of enterprise SSDs! These 2.5" SATA units were just announced, and as we suspected after reviewing the new 2TB 850 EVO and Pro, these new models can include even more flash packages, dramatically increasing the flash capacity. Here is a breakdown of the launch pricing and capacities:
SM863 (2-bit MLC VNAND):
- 120GB - $140 ($1.17/GB)
- 240GB - $180 ($0.75/GB)
- 480GB - $330 ($0.69/GB)
- 960GB -
$870 ($0.91/GB) < possible typo$640 ($0.67/GB)
- 1.92TB - $1260 ($0.66/GB)
PM863 (3-bit MLC VNAND):
- 120GB - $125 ($1.04/GB)
- 240GB - $160 ($0.67/GB)
- 480GB - $290 ($0.60/GB)
- 960GB - $550 ($0.57/GB)
- 1.92TB - $1100 ($0.57/GB)
- 3.84TB - $2200 ($0.57/GB)
These are some very competitive prices for enterprise SSDs, and the fact that the TLC version can cram just under 4TB into a 7mm 2.5" form factor is just astounding. The MLC version capacities appear to still follow that of the 850 Pro, minus a bit of available capacity due to higher levels of over-provisioning.
More impressive is the endurance ratings of these SSDs. The SM863 line is rated (varying by capacity) from 770 Terabytes Written (TBW) to an astonishing 12,320 TBW for the 1.92TB model! That's over 12 Petabytes! The PM863 is rated lower as it is TLC based, but is still no slouch as it ranges from 170 to 5,600 TBW for the 3.84TB capacity. The SM863 carries a 5-year warranty, while the PM863 drops that to 3-years.
We've been waiting to see Samsung's 32-layer VNAND appear in enterprise units for some time now, and look forward to testing them just as soon as we can get our hands on them!
Full press blast after the break.
Subject: Storage | July 9, 2015 - 04:37 PM | Jeremy Hellstrom
Tagged: Samsung, 850 EVO, 850 PRO, M600, micron, Sandisk Extreme Pro, ssd, roundup, sata
[H]ard|OCP has just posted a roundup of four affordable SATA SSDs to show which would be the best one to pick up as the majority of users are not able to afford an NVME PCIe SSD. The drives are all within $50 above or below $200, with the 850 PRO having the highest cost per gigabyte and the EVO the least. They test content creation and moving large files as well as synthetic benchmarks to come out with a ranking of the four drives which you can refer to if you will be shopping for storage in the near future. In comparison they use the G.SKILL Phoenix Blade to show off what the new technology can do, for those that can afford it.
"Despite the performance benefits, PCIe SSDs remain an expensive niche market. That means that most of us are not going to be loading up a high end system with PCIe SSDs. Most of us mere mortals will be using SATA SSDs. We tested some of the best SATA drives with enthusiast-friendly price tags."
Here are some more Storage reviews from around the web:
- OCZ Trion 100 Series Entry Level SSD @ [H]ard|OCP
- OCZ Trion 100 @ The SSD Review
- OCZ Trion 100 SSD @ HardwareHeaven
- OCZ Trion 100 240GB and 480GB @ Kitguru
- OCZ Trion 100 480GB & 960GB SSD Review @ Hardware Canucks
- OCZ Trion 100 480 GB @ techPowerUp
- ASUSTOR AS-5102T 2-bay NAS Review @ Madshrimps
Introduction, Specifications and Packaging
Since their acquisition by Toshiba in early 2014, OCZ has gradually transitioned their line of SSD products to include parts provided by their parent company. Existing products were switched over to Toshiba flash memory, and that transition went fairly smoothly, save the recent launch of their Vector 180 (which had a couple of issues noted in our review). After that release, we waited for the next release from OCZ, hoping for something fresh, and that appears to have just happened:
OCZ sent us a round of samples for their new OCZ Trion 100 SSD. This SSD was first teased at Computex 2015. This new model would not only use Toshiba sourced flash memory, it would also displace the OCZ / Indilinx Barefoot controller with Toshiba's own. Then named 'Alishan', this is now officially called the 'Toshiba Controller TC58'. As we found out during Computex, this controller employs Toshiba's proprietary Quadruple Swing-By Code (QSBC) error correction technology:
Error correction tech gets very wordy, windy, and technical and does so very quickly, so I'll do my best to simplify things. Error correction is basically some information interleaved within the data stored on a given medium. Pretty much everything uses it in some form or another. Some Those 700MB CD-R's you used to burn could physically hold over 1GB of data, but all of that extra 'unavailable' space was error correction necessary to deal with the possible scratches and dust over time. Hard drives do the same sort of thing, with recent changes to how the data is interleaved. Early flash memory employed the same sort of simple error correction techniques initially, but advances in understanding of flash memory error modes have led to advances in flash-specific error correction techniques. More advanced algorithms require more advanced math that may not easily lend itself to hardware acceleration. Referencing the above graphic, BCH is simple to perform when needed, while LDPC is known to be more CPU (read SSD controller CPU) intensive. Toshiba's proprietary QSB tech claims to be 8x more capable of correcting errors, but what don't know what, if any, performance penalty exists on account of it.
We will revisit this topic a bit later in the review, but for now lets focus on the other things we know about the Trion 100. The easiest way to explain it is this is essentially Toshiba's answer to the Samsung EVO series of SSDs. This Toshiba flash is configured in a similar fashion, meaning the bulk of it operates in TLC mode, while a portion is segmented off and operates as a faster SLC-mode cache. Writes first go to the SLC area and are purged to TLC in the background during idle time. Continuous writes exceeding the SLC cache size will drop to the write speed of the TLC flash.
Subject: Storage | July 6, 2015 - 03:28 PM | Jeremy Hellstrom
Tagged: ssd, Samsung, 850 PRO, 850 EVO, 2TB
Samsung is extending their 850 EVO and Pro lineups to include 2TB versions of the popular SSDs thanks to the use of 3D-VNAND; three bit memory on the EVO and two bit on the Pro. They are rated at the same speeds as their 500GB and above counterparts and The SSD Review had a chance to test that. Interestingly they did indeed find performance differences between the 1TB and 2TB model of the same design, which you can check out in the full review. Their results were not quite the same as Al's review which was just posted, you should compare the two reviews as well as the systems used for theories on why that is. You can expect to pay ~$1000 for the 850 Pro 2TB and ~$800 for the 850 EVO 2TB.
"If you look back over the past several years, there have always been three constants that needed to be addressed in order for SSDs to become a viable consumer solution to storage; value, reliability and capacity. One of our first SSD reviews was on an MTron 32GB SSD with a whopping price tag of more than $1500…and they sold!"
Here are some more Storage reviews from around the web:
- OCZ Vector 180 (480GB) @ Bjorn3d
- Kingston HyperX Savage SSD 240GB Review @ Neoseeker
- VisionTek 240GB Go Drive Review, Tough On The Go @ Bjorn3d
- Crucial BX100 256GB @ Bjorn3d
- Samsung SM951 256GB NVMe PCIe SSD @ Custom PC Review
- QNAP TVS-871U-RP-i3-4G NAS Server Review @ NikKTech
- WD My Cloud EX4100 4-Bay Expert Series 16TB NAS @ eTeknix
- Toshiba AL13SXB60EN 600GB SAS 12Gb/s HDD Review @ NikKTech
Introduction, Specifications and Packaging
Where are all the 2TB SSDs? It's a question we've been hearing since they started to go mainstream seven years ago. While we have seen a few come along on the enterprise side as far back as 2011, those were prohibitively large, expensive, and out of reach of most consumers. Part of the problem initially was one of packaging. Flash dies simply were not of sufficient data capacity (and could not be stacked in sufficient quantities) as to reach 2TB in a consumer friendly form factor. We have been getting close lately, with many consumer focused 2.5" SATA products reaching 1TB, but things stagnated there for a bit. Samsung launched their 850 EVO and Pro in capacities up to 1TB, with plenty of additional space inside the 2.5" housing, so it stood to reason that the packaging limit was no longer an issue, so why did they keep waiting?
The first answer is one of market demand. When SSDs were pushing $1/GB, the thought of a 2TB SSD was great right up to the point where you did the math and realized it would cost more than a typical enthusiast-grade PC. That was just a tough pill to swallow, and market projections showed it would take more work to produce and market the additional SKU than it would make back in profits.
The second answer is one of horsepower. No, this isn't so much a car analogy as it is simple physics. 1TB SSDs had previously been pushing the limits of controller capabilities of flash and RAM addressing, as well as handling Flash Translation Layer lookups as well as garbage collection and other duties. This means that doubling a given model SSD capacity is not as simple as doubling the amount of flash attached to the controller - that controller must be able to effectively handle twice the load.
With all of that said, it looks like we can finally stop asking for those 2TB consumer SSDs, because Samsung has decided to be the first to push into this space:
Today we will take a look at the freshly launched 2TB version of the Samsung 850 EVO and 850 Pro. We will put these through the same tests performed on the smaller capacity models. Our hope is to verify that the necessary changes Samsung made to the controller are sufficient to keep performance scaling or at least on-par with the 1TB and smaller models of the same product lines.