Friday, February 4th 2022
Mainstream PCIe 5.0 SSDs Only Expected in 2024
Although we've already seen some companies both tease and announce PCIe 5.0 consumer SSDs, it seems like we shouldn't expect mainstream PCIe 5.0 SSDs until 2024, at least if Silicon Motion's earnings call is anything to go by. Wallace Kou, Silicon Motion's CEO was quoted as saying ""It is likely that PCIe Gen4 will last a few years since Intel, AMD both continue to bring new upgrade variant of CPU with PCIe Gen4 to the market," continuing "Similarly, we are preparing for the launch of our third-generation PCIe Gen4 controller next year before transitioning to PCIe Gen5 in the following year."
This obviously has something to do not only with development time, but also with recuperating the costs of developing the previous generation of PCIe 4.0 SSD controllers before introducing new products that would have limited market share due to at least initially high prices. Silicon Motion is said to be working on multiple PCIe 5.0 SSD controllers with the enthusiast grade SM2508 expected towards the end of this year and it's set to compete with Phison's PS5026-E26 and InnoGrit's IG5666 controllers, plus unannounced inhouse controllers from the likes of Samsung and WD. Silicon Motion's mainstream PCIe 5.0 controller is said to be the SM2507, which is also said to be more suitable for mobile applications, most likely due to lower power consumption. However, the first PCIe 5.0 controller from Silicon Motion should be the SM8366 enterprise grade controller that was announced last year and which should be shipping in the second half of this year. For most users, PCIe 5.0 SSDs are unlikely to make a huge difference, unless we see some major improvements when it comes to random read and write performance, as this is currently the real bottleneck with SSDs.
Sources:
ArsTechnica, Tom's Hardware
This obviously has something to do not only with development time, but also with recuperating the costs of developing the previous generation of PCIe 4.0 SSD controllers before introducing new products that would have limited market share due to at least initially high prices. Silicon Motion is said to be working on multiple PCIe 5.0 SSD controllers with the enthusiast grade SM2508 expected towards the end of this year and it's set to compete with Phison's PS5026-E26 and InnoGrit's IG5666 controllers, plus unannounced inhouse controllers from the likes of Samsung and WD. Silicon Motion's mainstream PCIe 5.0 controller is said to be the SM2507, which is also said to be more suitable for mobile applications, most likely due to lower power consumption. However, the first PCIe 5.0 controller from Silicon Motion should be the SM8366 enterprise grade controller that was announced last year and which should be shipping in the second half of this year. For most users, PCIe 5.0 SSDs are unlikely to make a huge difference, unless we see some major improvements when it comes to random read and write performance, as this is currently the real bottleneck with SSDs.
30 Comments on Mainstream PCIe 5.0 SSDs Only Expected in 2024
What a wholesale move to more current generation I/O would get us would mostly be much more expensive motherboards. We're already seeing this, and ditching USB 2.0 for even 3.0 would only exacerbate the issue further.
Heck, let's look at AMD B550 - AMD's mid-range chipset for going on two years. The CPUs deliver 4x 10G USB ports. The chipset delivers another 2x 10G, 2x 5G, and 6x 480M. That's 14 USB ports, the majority of which are high speed. Is there any realistic need for more than that? That can't be rectified by the OEM sticking another USB controller onto a PCIe lane from the chipset? I would say no. And if you somehow need more than that, and need a ton of 5G or higher devices connected at once? Accept that your needs are very niche and get a hub.
There is one potential major benefit of faster I/O that could counteract this cost hike - but one that will sadly never come to pass: lane reductions. PCIe 5.0 can deliver 3.0x4 speeds with a single lane, meaning we could quadruple our port counts with only the same increase in cost and complexity as a single 5.0x4 port. We can see this in the Xbox Series X/S, where they use two lanes of PCIe 4.0 for their drives, simplifying signalling while maintaining good drive speeds. This could deliver significant, real benefits to users (though admittedly most users have 1-2 storage devices and never upgrade them) through more ports at marginal cost increases, or lowering costs for the same port counts. But it won't happen. Why? Marketing and perception. Motherboards won't implement 5.0x1 NVMe ports because there won't be drives for them, and they'd perform poorly with 3.0x4 drives, cutting them to >1GB/s max speed. SSDs won't implement 5.0x1 interfaces because they'd perform badly in older motherboards, there'd be no motherboards matching the ports, and every reviewer in the universe would complain about the drive "leaving performance on the table." Reviewers would also complain if any motherboards implemented lower lane count m.2 slots. And most customers would balk at buying a seemingly cut-down drive, even if it is an entirely reasonable choice that is likely to perform well - because its core feature, its defining characteristic, would be "cut down". That doesn't sell.
Heck, with PCIe 5.0 across the board we could equip a motherboard with four ~3.5GB/s SSDs and a 3.0x16 equivalent GPU with just eight TX/RX pairs from the CPU. That's ridiculously low, and could make for small, cheap, efficient motherboards. Or you could add another four SSDs with twelve total TX/RX pairs. But because it would always be seen as "cut down", this will never come to market, outside of niche industrial applications and other made-to-order/appliance style equipment. Instead, we'll keep getting ever more expensive full lane count stuff that has no practical use, because "bigger number better". And that's a shame.