SK hynix this week reported its financial results for the second quarter, as well as offering a glimpse at its plans for the coming quarters. Notably among the company's plans for the year is the release of a SK hynix-branded 60 TB SSD, which will mark the firm's entry into the ultra-premium enterprise SSD league.
"SK hynix plans to expand sales of high-capacity eSSD and lead the market in the second half with 60TB products, expecting eSSD sales to be more than quadrupled compared to last year," a statement by SK hynix reads.
Currently there are only two standard form-factor 61.44 TB SSDs on the market: the Solidigm D5-P5336 (U.2/15mm and E1.L), and the Samsung BM1743 (U.2/15mm and E3.S). Both are built from a proprietary controller (Solidigm's controller still carries an Intel logotype) with a PCIe 4.0 x4 interface and use QLC NAND for storage.
SK hynix's brief mention of the drive means that tere aren't any formal specifications or capabilities to discuss just yet. But it is reasonable to assume that the company will use its own QLC memory for their ultra-high-capacity drives. What's more intriguing are which controller the company plans to use and how it is going to position its 60 TB-class SSD.
Internally, SK hynix has access to multiple controller teams, both of which have the expertise to develop an enterprise-grade controller suitable for a 60 TB drive. SK hynix technically owns Solidigm, the former Intel SSD and NAND unit, giving SK hynix the option of using Solidigm's controller, or even reselling a rebadged D5-P5336 outright. Alternatively, SK hynix has their own (original) internal SSD team, who is responsible for building their well-received Aries SSD controller, among other works.
Ultra-high-capacity SSDs for performance demanding read-intensive storage applications, such as AI inference on the edge or content delivery networks, is a promising premium market. So SK hynix is finding itself highly incentivized to enter it with a compelling offering.
SSDsNVIDIA's AD102 GPU Pops Up in MSI GeForce RTX 4070 Ti Super Cards As GPU families enter the later part of their lifecycles, we often see chip manufacturers start to offload stockpiles of salvaged chips that, for one reason or another, didn't make the grade for the tier of cards they normally are used in. These recovered chips are fairly unremarkable overall, but they are unsold silicon that still works and has economic value, leading to them being used in lower-tier cards so that they can be sold. And, judging by the appearance of a new video card design from MSI, it looks like NVIDIA's Ada Lovelace generation of chips has reached that stage, as the Taiwanese video card maker has put out a new GeForce RTX 4070 Ti Super card based on a salvaged AD102 GPU. Typically based on NVIDIA's AD103 GPU, NVIDIA's GeForce RTX 4070 Ti Super series sits a step below the company's flagship RTX 4080/4090 cards, both of which are based on the bigger and badder AD102 chip. But with some number of AD102 chips inevitably failing to live up to RTX 4080 specifications, rather than being thrown out, these chips can instead be used to make RTX 4070 cards. Which is exactly what MSI has done with their new GeForce RTX 4070 Ti Super Ventus 3X Black OC graphics card. The card itself is relatively unremarkable – using a binned AD102 chip doesn't come with any advantages, and it should perform just like regular AD103 cards – and for that reason, video card vendors rarely publicly note when they're doing a run of cards with a binned-down version of a bigger chip. However, these larger chips have a tell-tale PCB footprint that usually makes it obvious what's going on. Which, as first noticed by @wxnod, is exactly what's going on with MSI's card. Ada Lovelace Lineup: MSI GeForce RTX 4070 TiS (AD103), RTX 4070 TiS (AD102), & RTX 4090 (AD102) The tell, in this case, is the rear board shot provided by MSI. The larger AD102 GPU uses an equally larger mounting bracket, and is paired with a slightly more complex array of filtering capacitors on the back side of the board PCB. Ultimately, since these are visible in MSI's photos of their GeForce RTX 4070 Ti Super Ventus 3X Black OC, it's easy to compare it to other video cards and see that it has exactly the same capacitor layout as MSI's GeForce RTX 4090, thus confirming the use of an AD102 GPU. Chip curiosities aside, all of NVIDIA GeForce RTX 4070 Ti Super graphics cards – no matter whether they are based on the AD102 or AD103 GPU – come with a GPU with 8,448 active CUDA cores and 16 GB of GDDR6X memory, so it doesn't (typically) matter which chip they carry. Otherwise, compared to a fully-enabled AD102 chip, the RTX 4070 Ti Super specifications are relatively modest, with fewer than half as many CUDA cores, underscoring how the AD102 chip being used in MSI's card is a pretty heavy salvage bin. As for the rest of the card, MSI GeForce RTX 4070 Ti Super Ventus 3X Black OC is a relatively hefty card overall, with a cooling system to match. Being overclocked, the Ventus also has a slightly higher TDP than normal GeForce RTX 4070 Ti Super cards, weighing in at 295 Watts, or 10 Watts above baseline cards. Meanwhile, MSI is apparently not the only video card manufacturer using salvaged AD102 chips for GeForce RTX 4070 Ti Super, either. @wxnod has also posted a screenshot obtained on an Inno3D GeForce RTX 4070 Ti Super based on an AD102 GPU. Sources: MSI, @wxnod GPUs
SK hynix Wraps up Dev Work on High-End PCB01 PCIe 5.0 SSD for OEMs, Launching Later This Year SK hynix early in Friday announced that the company has finished the development of it's PCB01 PCIe Gen5 SSD, the company's forthcoming high-end SSD for OEMs. Based on the company's new Alistar platform, the PCB01 is designed to deliver chart-topping performance for client machines. And, as a sign of the times, SK hynix is positioning the PCB01 for AI PCs, looking to synergize with the overall industry interest in anything and everything AI. The bare, OEM-focused drives have previously been shown off by SK hynix, and make no attempt to hide what's under the hood. The PCB01 relies on SK hynix's Alistar controller, which features a PCIe Gen5 x4 host interface on the front end and eight NAND channels on the back end, placing it solidly in the realm of high-end SSDs. Paired with the Alistar controller is the company's latest 238-layer TLC NAND (H25T1TD48C & H25T2TD88C), which offers a maximum transfer speed of 2400 MT/second. Being that this is a high-end client SSD, there's also a DRAM chip on board, though the company isn't disclosing its capacity. As with other high-end PCIe 5.0 client SSDs, SK hynix is planning on hitting peak read speeds of up to 14GB/second on the drive, while peak sequential write speeds should top 12GB/second (with pSLC caching, of course) – performance figures well within the realm of possibility for an 8 channel drive. As for random performance, at Computex the company was telling attendees that the drives should be able to sustain 4K random read and write rates of 2 million IOPS, which is very high as well. The SSDs are also said to consume up to 30% less power than 'predecessors,' according to SK hynix, though the company didn't elaborate on that figure. Typically in the storage industry, energy figures are based on iso-performance (rather than peak performance) – essentially measuring energy efficiency per bit rather than toal power consumption – and that is likely the case here as well. At least initially, SK Hynix plans to release its PCB01 in three capacities – 512 GB, 1 TB, and 2 TB. The company has previously disclosed that their 238L TLC NAND has a capacity of 512Gbit, so these are typical capacity figures for single-sided drives. And while the focus of the company's press release this week was on OEM drives, this is the same controller and NAND that is also going into the company's previously-teased retail Platinum P51 SSD, so this week's reveal offers a bit more detail into what to expect from that drive family as well. Specs aside, Ahn Hyun, the Head of the N-S Committee at SK hynix, said that multiple global CPU providers for on-device AI PCs are seeking collaboration for the compatibility validation process, which is underway, so expect PCB01 drives inside PCs in this back-to-school and holiday seasons. "We will work towards enhancing our leadership as the global top AI memory provider also in the NAND solution space by successfully completing the customer validation and mass production of PCB01, which will be in the limelight," Ahn Hyun said. SSDs
G.Skill on Tuesday introduced its ultra-low-latency DDR5-6400 memory modules that feature a CAS latency of 30 clocks, which appears to be the industry's most aggressive timings yet for DDR5-6400 sticks. The modules will be available for both AMD and Intel CPU-based systems.
With every new generation of DDR memory comes an increase in data transfer rates and an extension of relative latencies. While for the vast majority of applications, the increased bandwidth offsets the performance impact of higher timings, there are applications that favor low latencies. However, shrinking latencies is sometimes harder than increasing data transfer rates, which is why low-latency modules are rare.
Nonetheless, G.Skill has apparently managed to cherry-pick enough DDR5 memory chips and build appropriate printed circuit boards to produce DDR5-6400 modules with CL30 timings, which are substantially lower than the CL46 timings recommended by JEDEC for this speed bin. This means that while JEDEC-standard modules have an absolute latency of 14.375 ns, G.Skill's modules can boast a latency of just 9.375 ns – an approximately 35% decrease.
G.Skill's DDR5-6400 CL30 39-39-102 modules have a capacity of 16 GB and will be available in 32 GB dual-channel kits, though the company does not disclose voltages, which are likely considerably higher than those standardized by JEDEC.
The company plans to make its DDR5-6400 modules available both for AMD systems with EXPO profiles (Trident Z5 Neo RGB and Trident Z5 Royal Neo) and for Intel-powered PCs with XMP 3.0 profiles (Trident Z5 RGB and Trident Z5 Royal). For AMD AM5 systems that have a practical limitation of 6000 MT/s – 6400 MT/s for DDR5 memory (as this is roughly as fast as AMD's Infinity Fabric can operate at with a 1:1 ratio), the new modules will be particularly beneficial for AMD's Ryzen 7000 and Ryzen 9000-series processors.
G.Skill notes that since its modules are non-standard, they will not work with all systems but will operate on high-end motherboards with properly cooled CPUs.
The new ultra-low-latency memory kits will be available worldwide from G.Skill's partners starting in late August 2024. The company did not disclose the pricing of these modules, but since we are talking about premium products that boast unique specifications, they are likely to be priced accordingly.
MemoryMicrochip recently announced the availability of their second PCIe Gen 5 enterprise SSD controller - the Flashtec 5016. Like the 4016, this is also a 16-channel controller, but there are some key updates:
Microchip's enterprise SSD controllers provide a high level of flexibility to SSD vendors by providing them with significant horsepower and accelerators. The 5016 includes Cortex-A53 cores for SSD vendors to run custom applications relevant to SSD management. However, compared to the Gen4 controllers, there are two additional cores in the CPU cluster. The DRAM subsystem includes ECC support (both out-of-band and inline, as desired by the SSD vendor).
At FMS 2024, the company demonstrated an application of the neural network engines embedded in the Gen5 controllers. Controllers usually employ a 'read-retry' operation with altered read-out voltages for flash reads that do not complete successfully. Microchip implemented a machine learning approach to determine the read-out voltage based on the health history of the NAND block using the NN engines in the controller. This approach delivers tangible benefits for read latency and power consumption (thanks to a smaller number of errors on the first read).
The 4016 and 5016 come with a single-chip root of trust implementation for hardware security. A secure boot process with dual-signature authentication ensures that the controller firmware is not maliciously altered in the field. The company also brought out the advantages of their controller's implementation of SR-IOV, flexible data placement, and zoned namespaces along with their 'credit engine' scheme for multi-tenant cloud workloads. These aspects were also brought out in other demonstrations.
Microchip's press release included quotes from the usual NAND vendors - Solidigm, Kioxia, and Micron. On the customer front, Longsys has been using Flashtec controllers in their enterprise offerings along with YMTC NAND. It is likely that this collaboration will continue further using the new 5016 controller.
Storage
0 Comments