News Phison E26 SSD Preview: PCIe 5.0 SSDs Are Finally Here

[Admin]

The Phison E26 sample is the first PCIe 5.0 SSD that we’ve tested and it is also the all-around fastest drive to . More bandwidth is yours to have with the proper platform, but cooling has become a serious concern with a drive this fast.

Phison E26 SSD Preview: PCIe 5.0 SSDs Are Finally Here : Read more

 

[Zizo007]

Crazy that the gen4 Samsung 990 pro also has 1550k iops.

 

[DavidLejdar]

Nice. I have my MB ready for it, AM5, so no taking away of PCIe 5.0 lanes from the GPU. And for casual use it sure seems quite over the top these days - and more so when there is a relatively weak CPU, since such is not likely to make full use of the 4K-random-read IOPS. But as this controller allows for up to 32 TB capacity, that is quite some potential to hope for reasonably priced at least 4TB or even 8TB drives.

 

[cyrusfox]

Going to have a hard time to make use of 10GB+/s transfers, 1-2GB/s is plenty, usually don't experience speeds in excess of SATA in actual day to day usage.

Very interested to see how this controller stacks up to best gen4 drives as well as how it compares to the aging and last of the line Optane 5800x. Fully expecting diminishing returns. For mobile though, does 2xlanes PCIe gen 5 take more or less power than 4 lanes PCIe gen 4? That is one application where gen 5 might make sense.

 

[TechieTwo]

A year of hype and at least six months late to market with so, so performance. Caveat emptor.

 

[Deleted member 14196]

They got you working like a slave to buy stuff that you don’t need

 

[setx]

Power consumption is horrible.

What is this drive designed for? For home I'd rather have cool PCIe 4 SSD. For work (saving data from high-speed cameras) sustained write is unacceptable.

 

[Math Geek]

what i wonder about most is how do these run so hot? i mean <12w at full throttle is not that much. just trying to figure out how it takes active cooing for very little power used overall. the drive acts like its using 100w.....

 

[DonQuixoteIII]

Early days yet, but already the nemesis of quiet is raising its ugly head. If these SSDs require active cooling to avoid throttling, tthen hopefully MB mfg's will re-arrange placement of M.2 slots for easier heatsink placement. Of course, not everyone will need (or want) five of these for their use case (four in a RAID with a spare for redundancy), but there will be some, mostly using workstation level MB's, that do. As well as a few well heeled gamers 'just because'. 28kGBs... Woot!

 

[Deleted member 14196]

Raid is basically useless with SSDs. No real world performance gain

 

[bit_user]

Keeping in mind this is an engineering sample, I think it's pretty impressive.

The first thing that needs to be addressed is why the left side of this graph isn't zero. Since I didn't notice that on any other graph, I'm guessing it was a mistake/oversight:

Next, I found it interesting that it doesn't really pull ahead at sequential reads, until the transaction size reaches 128 kB. Not saying it's a problem, just interesting. Nice that it peaks already by 1 MB, but the subsequent drop seems truly bizarre.

The story with sequential writes is a bit better, although you generally care about that less, since the OS can already buffer short busts at even higher speeds:

Power Consumption is clearly its Achilles heel, using nearly 2x the Samsung 990 Pro's full power mode!

That said, another (lesser) trouble spot is in IOPS and random performance. Hopefully, those areas can be polished a bit, prior to launch.

Anyway, thanks for the preview! It's interesting to see how much difference it made in the application benchmarks. Nice to see it noticeably pull ahead in something more than pure synthetics!

 

[CRamseyer]

Crazy that the gen4 Samsung 990 pro also has 1550k iops.

What is nice is that Phison can do it with 1600MT/s flash and Samsung needs 2000MT/s flash.

 

[CRamseyer]

Power consumption is horrible.

What is this drive designed for? For home I'd rather have cool PCIe 4 SSD. For work (saving data from high-speed cameras) sustained write is unacceptable.

It is an early drive. Power is one if the last optimizations in the process. That will all be tamed soon.

 

[Jackka]

Can someone tell me if the actual game or app loading time will have any detectable difference between a pcie 5 ssd and a pcie 4 ssd?

What would be the actual in use difference in loading an app? 0 sec? 0.001 sec? 0.1 sec? 1 sec? A few seconds?

I feel like this type of number should be the first thing mentioned in an article for any ssd, because isn’t the whole purpose of the article to help a potential buyer of the product determine whether the product is worth the money spent? What use is all the numbers and graphs if it’s still not clear to the reader what actual difference they all mean to him?

 

[Math Geek]

You saw the same article we saw. Why would any of us have any inside info you did not see?? We're all just plain ol regular readers/users like you...

 

[Jackka]

You don’t know what someone might know. Could be someone involved in the product development or the tester himself or someone with enough specific engineering background or experience to know if there is a difference and/or about how much it would be.

Assuming no one else would know anything I don’t know is probably a horrible way to go about life.

 

[Math Geek]

ok good luck then. hope it works out for you and you get all the insider info

 

[Jackka]

ok good luck then. hope it works out for you and you get all the insider info

Not really insider info.
Good luck to your life as well. lol

 

[bit_user]

I feel like this type of number should be the first thing mentioned in an article for any ssd,

Please understand that this is a hands-on tech preview. It is Toms reporting about new tech they see on the CES show floor, where they have a million different exhibitors to see and report on. So, try to be understanding if their coverage lacks some polish.

It's also meant to highlight the SSD controller chip, rather than demonstrating an actual end-user product!

isn’t the whole purpose of the article to help a potential buyer of the product determine whether the product is worth the money spent?

It's a technology site, more than just a PC buyers' guide. They cover lots of tech that you and I can't buy, but that many of us like to read about, like supercomputers, quantum computers, big AI systems, semiconductor manufacturing, etc.

Once they get actual shipping products (which this is not!) into their lab, then they publish a proper product review. At that point, it's fair to say they should make sure it's relevant to SSD shoppers. But, again, this was a technology demo and not something you could buy if you wanted.

because What use is all the numbers and graphs if it’s still not clear to the reader what actual difference they all mean to him?

They did include some application benchmark suites, if you dig through the graphs. These are designed to reflect user experience, when running demanding applications on their PC.

I hope & expect their full review will include some game loading time benchmarks and maybe some DirectStorage test, but this should already give you a rough idea that it's not a revolutionary change from what we have today. It might be worth buying, for those trying to build the absolute fastest PC, but almost everyone else will do just fine with a good PCIe 4.0 SSD (or less!).

 

[Jackka]

Please understand that this is a hands-on tech preview. It is Toms reporting about new tech they see on the CES show floor, where they have a million different exhibitors to see and report on. So, try to be understanding if their coverage lacks some polish.

It's also meant to highlight the SSD controller chip, rather than demonstrating an actual end-user product!


It's a technology site, more than just a PC buyers' guide. They cover lots of tech that you and I can't buy, but that many of us like to read about, like supercomputers, quantum computers, big AI systems, semiconductor manufacturing, etc.

Once they get actual shipping products (which this is not!) into their lab, then they publish a proper product review. At that point, it's fair to say they should make sure it's relevant to SSD shoppers. But, again, this was a technology demo and not something you could buy if you wanted.


They did include some application benchmark suites, if you dig through the graphs. These are designed to reflect user experience, when running demanding applications on their PC.

I hope & expect their full review will include some game loading time benchmarks and maybe some DirectStorage test, but this should already give you a rough idea that it's not a revolutionary change from what we have today. It might be worth buying, for those trying to build the absolute fastest PC, but almost everyone else will do just fine with a good PCIe 4.0 SSD (or less!).

Yes, I agree on everything.

Seeing that they had an actual early sample that they bothered to put through numerous benchmarks, I was just airing out my frustration that most SSD reviews or articles(not just Tom’s Hardware) never bother to communicate any real-world performance differences or whether any differences exist.

The ~600 points of jump in the benchmark could be a nanosecond or a few seconds, or even more. We’ll never know. I suspect, as you do, that the actual difference is going to be negligible if not undetectable outside of a benchmark. Which is all well and fine, but I just wish the eventual “reviews” actually informed that there is no practical difference to the user, or otherwise at least a vague idea of the actual usable gains to be expected outside of a graph. It’s like the reviews are showing you numbers purely for the sake of showing you numbers while, for some reason, keeping mum about the actual difference. Makes me wonder what the intent of the “review” is.

This article does say at one point that the improvements are difficult to detect between pcie 3 and pcie 4 SSDs. But, again, we have no idea if that means no difference, or no practical difference, or no clearly noticeable difference with the bare eye, or what.

It’s almost comical that we will likely end up reading a multipage review of these SSDs including 10 graphs each, but if our 5 year-old nephew then asked us, “So how much faster is it going to make our computer?” We’d basically have to say, I don’t know, anywhere between not at all and a little bit quicker.

 

[bit_user]

The ~600 points of jump in the benchmark could be a nanosecond or a few seconds, or even more. We’ll never know.
...
It’s almost comical that we will likely end up reading a multipage review of these SSDs including 10 graphs each, but if our 5 year-old nephew then asked us, “So how much faster is it going to make our computer?” We’d basically have to say, I don’t know, anywhere between not at all and a little bit quicker.

These application benchmark suites are designed by 3DMark (UL Labs) and whoever makes PC Mark specifically to answer the question of how much speedup the user should expect. I think the correct way to interpret them is as a relative measure (i.e. how much faster will drive X feel than drive Y). That said, I cannot personally attest for either of them. However, they seem to be in the right direction of what you want.

I suspect, as you do, that the actual difference is going to be negligible if not undetectable outside of a benchmark.

I didn't say that. I wouldn't be surprised if there was a measurable difference in game loading time, for instance. Not huge, but at least measurable.

I just wish the eventual “reviews” actually informed that there is no practical difference to the user, or otherwise at least a vague idea of the actual usable gains to be expected outside of a graph.

The reviewers sometimes do mention qualitative observations, but you must be aware those are notoriously unreliable - no matter who is the reviewer. What's needed is simply tests that are more relevant to specific users' use cases and needs. Game loading time is a perfect example, and I'm sure I've seen that measured for a few games, in previous SSD reviews on this site.

 

[CRamseyer]

Please remember that power optimizations are one of the last pieces to work on in the firmware process. We didn't expect anyone to run power testing. Since this article, we are already several firmware versions past this one. You can expect higher performance and lower power consumption between the preview article drives and the retail drives. You can go back and see the E18 preview articles and the E18 retail drive differences to verify.

I think everyone is going to love the E26. I've had one in my gaming system for a couple of weeks and it feels as fast as the Optane P5800X it replaced in daily use workloads. That is the real achievement.