Phison kicked off the transition to PCIe 4.0 for storage in 2019, and dominated the high-end SSD market for over a year with the only available PCIe 4.0 solution. There are now several competing PCIe 4.0 NVMe SSDs and controllers that handily outperform the Phison E16, but Phison has stayed competitive by bringing out a second-generation PCIe 4.0 controller, the E18. Today we're looking at one of many drives built around that controller: the Inland Performance Plus 2TB.

The Inland brand is owned by the parent company of American retailer Micro Center. Most or all Inland-branded SSDs are simply Phison reference designs with little or no customization beyond cosmetics. Inland SSDs are frequently great value options—especially for Micro Center's in-store only deals, but even their online prices tend to be very competitive. Part of the discount comes from their tendency toward shorter warranty periods: the Inland Performance Plus has only a three year warranty despite being a high-end flagship model. Fortunately, the total write endurance rating is the same as competing drives that carry five year warranties, and the SSD hardware itself is identical to other brands selling the same SSD reference design under different heatsinks and labels.

As part of the second wave of PCIe 4.0 SSD controllers, the Phison E18 aims to use substantially all of the performance available from the PCIe 4.0 x4 interface: sequential transfers up to around 7.4 GB/s and random IO up to about 1M IOPS. Hitting that level of performance while staying within M.2 power delivery and thermal dissipation limits required migrating to 12nm FinFET fabrication from the cheaper 28nm widely used by PCIe 3.0 SSD controllers and by the Phison E16. But even so, the Phison E18 can draw more power than the E16 controller because the increase in performance is so large. Competition for the Phison E18 includes in-house controllers used in the latest flagship consumer SSDs from Samsung and Western Digital, newcomer Innogrit's IG5236 Rainier controller, and Silicon Motion's upcoming SM2264 controller.

Phison High-End NVMe SSD Controller Comparsion
  E12 E16 E18
Manufacturing Process 28 nm 12 nm
CPU Cores 2x Cortex R5 3x Cortex R5
Error Correction 3rd Gen LDPC 4th Gen LDPC
DRAM DDR3/4 DDR4 DDR4, LPDDR4
Host Interface PCIe 3.0 x4 PCIe 4.0 x4
NVMe Version NVMe 1.3 NVMe 1.4
NAND Channels,
Interface Speed
8 ch,
667 MT/s
8 ch,
800 MT/s
8 ch,
1600 MT/s
Max Capacity 16 TB 16 TB 16 TB
Sequential Read 3.4 GB/s 5.0 GB/s 7.4 GB/s
Sequential Write 3.2 GB/s 4.4 GB/s 7.0 GB/s
4KB Random Read IOPS 700k 750k 1M IOPS
4KB Random Write IOPS 600k 750k 1M IOPS
Controller Power 2.1 W 2.6 W 3.0 W
Sampling Q2 2018 Q1 2019 Q1 2020
Retail SSD Availability Q4 2018 Q3 2019 Q4 2020

The Inland Performance Plus does not quite hit the theoretical limits of the Phison E18 controller. The 1TB model is clearly handicapped on some performance metrics compared to the 2TB model, but even the latter is only rated for 7GB/s sequential reads and 650-700k IOPS instead of 7.4GB/s and 1M IOPS. This mostly comes down to the Inland Performance Plus and other current E18 drives using 96L TLC NAND with 1200MT/s IO between the NAND and the controller, while the E18 can support up to 1600MT/s IO. A new round of E18-based products will start hitting the market soon using Micron 176L TLC that operates with the higher IO speed and should bring some other performance and efficiency improvements. We expect some of these new drives to be announced at Computex next month.

Inland Performance Plus
SSD Specifications
Capacity 1 TB 2 TB
Form Factor M.2 2280 PCIe 4.0 x4
Controller Phison E18
NAND Flash Micron 96L 3D TLC
Sequential Read (GB/s) 7.0 7.0
Sequential Write (GB/s) 5.5 6.85
Random Read IOPS (4kB) 350k 650k
Random Write IOPS (4kB) 700k 700k
Warranty 3 years
Write Endurance 700 TB
0.6 DWPD
1400 TB
0.6 DWPD
Retail Price (In Store Only) $189.99
(19¢/GB)
$379.99
(19¢/GB)

Like most drives using the Phison E18 controller, the Inland Performance Plus comes with a fairly substantial heatsink installed. The controller package is small enough to share space with a DRAM package and four NAND packages on the front of the PCB, which means there's a lot of heat concentrated in a small area. (The Inland Performance Plus also has DRAM and NAND on the back of the PCB.) PCIe 4.0 has barely started showing up in laptops and using the full performance of a drive like the Inland Performance Plus requires more power than most laptops are able to sink away from their M.2 slots, so it's reasonable to regard this drive as pretty much desktop-only.

 

The Competition

The most important competitors for the Inland Performance Plus are other Phison E18 drives and the current flagship PCIe 4.0 drives from Samsung and Western Digital. We have fresh results in this review for the Samsung 980 PRO, retested with the latest 3B2QGXA7 firmware. We've also included results from some older top of the line drives: the Intel Optane 905P and Samsung 970 PRO (their last consumer NVMe drive to use MLC NAND), and the Silicon Power US70 representing the first wave of PCIe 4.0 drives that used the Phison E16 controller.

WD Black SN850 PCIe 4.0 x4 WD Custom G1 96L TLC
Samsung 980 PRO PCIe 4.0 x4 Samsung Elpis 128L TLC
Silicon Power US70 PCIe 4.0 x4 Phison E16 96L TLC
Intel Optane SSD 905P PCIe 3.0 x4 Intel Custom 3D XPoint G1
Samsung 970 PRO PCIe 3.0 x4 Samsung Phoenix 64L MLC

The rest of the drives included in this review are more mainstream models, mostly PCIe 3.0 drives, some with four-channel controllers instead of the usual eight for the high-end, and even a few with QLC NAND. This includes the Inland Premium, which is based on the Phison E12S and TLC NAND.

Inland Premium PCIe 3.0 x4 Phison E12S 96L TLC
SK hynix Gold P31 PCIe 3.0 x4 SK hynix Custom (4ch) 128L TLC
Samsung 970 EVO Plus PCIe 3.0 x4 Samsung Phoenix 92L TLC
WD Black SN750 PCIe 3.0 x4 WD Custom G1 64L TLC
HP EX950 PCIe 3.0 x4 SM2262EN 64L TLC
Kingston KC2500 PCIe 3.0 x4 SM2262EN 96L TLC
Intel SSD 670p PCIe 3.0 x4 SM2265 (4ch) 144L QLC
ADATA Gammix S50 Lite PCIe 4.0 x4 SM2267 (4ch) 96L TLC
Corsair MP600 CORE PCIe 4.0 x4 Phison E16 96L QLC
Trace Tests: AnandTech Storage Bench and PCMark 10
POST A COMMENT

118 Comments

View All Comments

  • Samus - Sunday, May 16, 2021 - link

    Microsoft really has to get with the times and launch ReFS on the client end already. NTFS is a joke compared to even legacy file systems like EXT3 and hasn't been updated in 20 years (unless you consider the journaling update starting with Windows 8) Reply
  • GeoffreyA - Monday, May 17, 2021 - link

    Well, NTFS might not have been updated much, but you know what they say, if it ain't broke, don't fix it. It was quite advanced for its time. Still is solid. Had journalling from the start, Unicode, high-precision time, etc. Compression came next. Then in NT 5, encryption, sparse files, quotas, and all that. Today, the main things it's lacking are copy-on-write, de-duplication, and checksums for data. Microsoft seems to have downplayed ReFS, owing to some technical issues. Reply
  • MyRandomUsername - Tuesday, May 18, 2021 - link

    Have you tried compression on NTFS (particularly on small files). I/O performance on a high end NVME drive plummets to first gen SSD level. Absolutely unusable. Reply
  • GeoffreyA - Wednesday, May 19, 2021 - link

    Haven't got an NVMe drive but I'll try some experiments and see how it goes. Could be that many, small files stagger any SSD. Reply
  • mode_13h - Tuesday, May 18, 2021 - link

    > copy-on-write, de-duplication

    A huge use case for that is snapshots. They're my favorite feature of BTRFS.
    Reply
  • GeoffreyA - Wednesday, May 19, 2021 - link

    Glancing over it, Btrfs looks impressive. Reply
  • mode_13h - Thursday, May 20, 2021 - link

    Copy-on-write can cause problems, in some cases. BTRFS lets you disable it on a per-file, per-directory, or per-subvolume basis.

    One feature of BTRFS I haven't touched is its built-in RAID functionality. I've always used it atop a hardware RAID controller or even a software RAID. And if you're using mechanical disks, software RAID is plenty fast, these days.
    Reply
  • GeoffreyA - Thursday, May 20, 2021 - link

    Whenever there's sharing of this sort, there's always trouble round the corner. Reply
  • mode_13h - Friday, May 21, 2021 - link

    > Whenever there's sharing of this sort, there's always trouble round the corner.

    Maybe. I think the issue is really around pretending you have a unique copy, when it's really not. In that sense, it's a little like caches -- usually a good optimization, but there's pretty much always some corner case where you hit a thrashing effect and they do more harm than good.
    Reply
  • GeoffreyA - Sunday, May 23, 2021 - link

    "I think the issue is really around pretending you have a unique copy, when it's really not."

    You hit the nail there. A breaking down between concept ("I've got a unique copy") and implementation. And so the outside world, tying itself to the concept, runs into occasional trouble.
    Reply

Log in

Don't have an account? Sign up now