Plextor M8Se 256GB & 512GB NVMe PCIe SSD Review

1. Introduction, Drive Specifications, Pricing & Availability
2. Drive Details
3. Test System Setup, Drive Properties & SSD Toolbox
4. Synthetic Benchmarks – ATTO & Anvil Storage Utilities
5. Synthetic Benchmarks – CrystalDiskMark & AS SSD
6. Benchmarks (OS) - Vantage, PCMark 7, PCMark 8 & SYSmark 2014 SE
7. Benchmarks (Secondary) - IOPS, Response & Transfer Rate
8. Benchmarks – 70/30 Mixed Workload & Sustained Sequential Write
9. Maxed-Out Performance (MOP)
10. Final Thoughts

TweakTown's Rating: 87%

The Bottom Line

Plextor's M8Se delivers an excellent user experience and the AIC version looks fantastic.

Introduction, Drive Specifications, Pricing & Availability

101

Back when we tested Plextor's first NVMe SSD, the M8PeY, we came away impressed. The M8PeY is an MLC-based NVMe SSD that is powered by Toshiba 15nm planar MLC flash and Marvell's 88SS1093 Gen3x 4 NVMe controller codenamed Eldora. What impressed us so much about this SSD was its low QD random performance as well as its low QD sequential read performance. The M8PeY we tested also had at the time, the best heat sink design we had ever seen on an SSD. Additionally, it came with some serious bling via a row of red LED's that flash with the drive activity.

Plextor's M8Pe was launched just before the current flash shortage hit industry wide. With the ongoing flash shortage, Plextor decided to move to more available high-performance 15nm Toshiba planar TLC flash, and launch a new SSD called the M8Se. The M8Se is basically the same drive as the M8Pe except it sports a TLC flash array instead of an MLC flash array.

The M8Se pairs Marvell's 88SS1093 Gen3 x4 NVMe controller with high-grade 15nm Toshiba planar TLC flash and Plextor's own in-house firmware. Plextor's custom firmware incorporates SLC buffer technology called PlexNitro. PlexNitro accelerates performance, increases endurance and does so without impacting the drive's capacity.

Typically, we are not very fond of planar TLC flash and didn't expect the M8Se would deliver compelling performance, but we were wrong. We figured the M8SeY would have to rely on its award-winning design aesthetics to sell. Not so, this sleek AIC SSD packs a serious punch, and in some benchmarks, it delivers even better performance than its MLC-based predecessor.

101

As you can see from the above photos, the AIC version of the M8Se, the M8SeY, looks like a stealth fighter ready to do battle. It also brings the bling with a row of blue LED's that react to disk activity. Plextor improved the thermal performance of the "Y" versions massive solid aluminum heat sink by incorporating swoop-shaped fins into the new design. Plextor says their new design improves thermal dissipation by 30% over the M8PeY's heat sink.

Plextor's newest NVMe SSD has the looks and packs a punch as well. Let's get into the review, and we will show you exactly how potent the M8Se can be.

Specifications

101

Plextor's M8Se Series is available in four capacities and three different versions - the M8SeY (AIC with heat sink), the M8SeG (M.2 with heat sink) and the M8SeGN (M.2 only). Available capacities: 128GB, 256GB, 512GB and 1024GB.

• Sequential Read: up to 2,450 MB/s
• Sequential Write: up to 1,000 MB/s
• Max 4K Random Read Speed: up to 210,000 IOPS
• Max 4K Random Write Speed: up to 175,000 IOPS
• Endurance: up to 640 TBW
• MTBF: 1.5 Million Hours
• Warranty: 3-Year Limited Warranty
• PlexNitro SLC caching
• LDPC
• SMART
• TRIM
• Garbage Collection

M8SeY 512GB MSRP = $279. M8SeGN 256GB MSRP = $130

Availability: The M8Se is selling now at both Amazon and Newegg.

Features

Looking at the above factory spec sheet reveals that there is no performance difference between the M8SeY and the more affordable M8SeGN models. Something that immediately caught our attention is the double dose of LPDDR3 that all the models have onboard. Typically, we see a 1MB to 1GB DRAM to NAND ratio, but the M8Se gives us a double dose with a minimum of 2MB to 1GB DRAM to NAND ratio. Undoubtedly this is where some of the M8Se's punch is coming from.

Features include Plextor's exclusive TrueSpeed and TrueProtect technologies. TrueSpeed technology keeps long-term SSD performance at like-new speeds after periods of use and when the SSD is nearly full.

TrueProtect technology is a multi-layered error checking mechanism automatically executed by the firmware. TrueProtect keeps data access error-free. PlexNitro accelerates data transfers using SLC caching technology that does not impact capacity. Additionally, data accuracy is ensured by Marvell's latest third generation LDPC bit correction which also provides extended endurance flash endurance.

Drive Details

Plextor M8SeY 512GB M.2 with AIC PCIe NVMe SSD

101

The front face of the packaging is blue and white themed. There is a wave pattern on it that is similar to the pattern found on the drive's heat sink. The drive's capacity is advertised as its limited 3-year warranty, NVMe interface, formfactor, and exclusive features.

101

The back of the packaging lists factory performance specs for each capacity.

101

Inside of the colorful outer packaging is a heavy-duty flip-top cardboard box.

101

Opening the inner box reveals the drive is well protected by a thickly molded plastic carrier tray.

101

The drive ships with a half-length mounting bracket as well as a pre-attached full-length bracket, a mounting screw, and a quick install guide.

101

The front half of the drive features a solid aluminum heat sink. The black heat sink is full size and covers the entire AIC adapter card.

101

The back half of the SSD is just the back half of the AIC adapter. The black color will meld well with any color scheme.

101

Removing the heat sink voids the warranty and reveals the M.2 x 2280 SSD that is mounted to the drive's AIC adapter card. Looking at the underside of the solid aluminum heat sink, we find a thermal pad that makes contact with all of the heat generating components of the single-sided M.2 SSD.

101

A close-in view of the drive's M.2 x 2280 single-sided SSD. This side of the SSD houses the drive's Marvell 88SS1093 NVMe controller, a low-power DDR3 Nanya DRAM package, and two 256GB Toshiba 15nm planar TLC flash packages.

101

No components are housed on the back half of the PCB.

Plextor M8SeGN 256GB M.2 PCIe NVMe SSD

101

The front face of the packaging is blue and white themed. The drive's capacity is advertised as is its limited 3-year warranty, NVMe interface, formfactor, and exclusive features.

101

The back of the packaging lists factory performance specs for each capacity.

101

Inside of the colorful box is a clear plastic clam-shell container the protects the drive from shipping damage.

101

A close-in view of the M8Se single-sided SSD. This side of the SSD houses the drive's Marvell 88SS1093 NVMe controller, a low-power DDR3 Nanya DRAM package, and two 128GB Toshiba 15nm planar TLC flash packages. The flash packages are covered by a manufacturer label.

101

This side of the drive's dark green PCB is devoid of components.

Test System Setup, Drive Properties & SSD Toolbox

Jon's Consumer PCIe SSD Intel Review Test System Specifications

• Motherboard: ASRock OC Formula Z170 - Buy from Amazon / Read our review
• CPU: Intel Core i7 6700K @ 4.7GHz - Buy from Amazon / Read our review
• Cooler: Swiftech H2O-320 Edge - Buy from Amazon / Read our review
• Memory: Corsair Vengeance LPX DDR4 16GB 3200MHz - Buy from Amazon
• Video Card: Onboard Video
• Case: IN WIN X-Frame - Buy from Amazon / Read our review
• Power Supply: Seasonic Platinum 1000 Watt Modular - Buy from Amazon / Read our review
• OS: Microsoft Windows 10 Professional 64-bit - Buy from Amazon
• Drivers: MS Win 10 NVMe driver

We would like to thank ASRock, Crucial, Intel, Corsair, RamCity, IN WIN, and Seasonic for making our test system possible.

Drive Properties

Plextor M8SeY 512GB AIC PCIe NVMe SSD OS Disk 75% Full

101

Plextor M8SeGN 256GB M.2 PCIe NVMe SSD OS Disk 75% Full

101

The majority of our testing is performed with our test drive as our boot volume. Our boot volume is 75% full for all OS Disk "C" drive testing to replicate a typical consumer OS volume implementation. We feel that most of you will be utilizing your SSDs for your boot volume and that presenting you with results from an OS volume is more relevant than presenting you with empty secondary volume results.

System settings: Cstates and Speed stepping are both disabled in our systems BIOS. Windows High-Performance power plan is enabled. Windows write caching is enabled, and Windows buffer flushing is disabled. We are utilizing Windows 10 Pro 64-bit OS (Build 14393) for all of our testing except for our MOP (Maxed-Out Performance) benchmarks where we switch to Windows Server 2012 R2 64-bit. Empty Windows 10 benchmark screenshots will also be shown on our MOP page.

Please note: When comparing our results to those of other review sites, look at page 10 Maxed Out Performance-Windows 10 which is done with the disk empty.

Benchmark screenshots will be shown 512GB model first followed by the 256GB model.

Synthetic Benchmarks – ATTO & Anvil Storage Utilities

ATTO

Version and / or Patch Used: 3.05

ATTO is a timeless benchmark used to provide manufacturers with data used for marketing storage products. When evaluating ATTO performance, we focus on the drive's performance curve.

101

101

We are able to exceed factory sequential read/write performance specs for both capacity points.

Sequential Write

101

Graphing the performance curve reveals the 256GB M8SeGN outperforming the 256GB MLC powered M8SeY and of course the Intel 600p. The 512GB M8SeY as expected outperforms all three of those drives. Both test subjects are outperformed by the majority of the drives in our test pool. However, we do see excellent small-file performance delivered by both of our test subjects.

Sequential Read

101

Sequential read performance is important in an OS environment, and the M8Se delivers far better performance than the 3D MLC powered SX8000. Both M8Se variants exceed factory specifications but fall short of the performance delivered by the majority of the drives in our test pool.

Anvil Storage Utilities

Version and / or Patch Used: 1.1.0

Anvil's Storage Utilities is a storage benchmark designed to measure the storage performance of SSDs. The Standard Storage Benchmark performs a series of tests; you can run a full test or just the read or write test, or you can run a single test, i.e., 4k QD16. When evaluating performance with Anvils, we focus on the total score. When evaluating NVMe SSDs, we are typically looking for a minimum total score of over 10K. We place a greater importance on read performance than write performance.

101

101

Scoring

101

In terms of total score, the 512GB M8Se gives us what we are looking for. The 256GB model doesn't get there. Looking at the read score (the score we place the greatest importance on) shows us that the 512GB M8Se outperforms all the drives in our test pool except Samsung's 960 EVO. Comparing the 256GB M8SeGN with the MLC powered M8PeY, we see the M8SeGN delivering better read performance. Very good read performance coming from both of our test subjects.

(Anvil) Read IOPS through Queue Depth Scale

101

101

We are able to greatly exceed factory max 4K read IOPS for the 512GB M8SeY. We don't quite get there with the 256Gb M8SeGN. Keep in mind that this is our system disk and it is 75% full.

101

Random performance is much more important than sequential performance for a system disk. Low queue depth random performance is more important than high queue depth performance. With those two previous statements in mind, the results of this test are quite impressive. This is a big win for Plextor's M8Se.

(Anvil) Write IOPS through Queue Scale

101

101

Both drives easily exceed factory max random write specs even though they are system disks 75% full.

101

Even though both drives are able to exceed factory specs for max 4K IOPS at QD32, they are both swimming at the bottom of our test pool at low queue depths. We would like to see better performance at low queue depths, but with planar TLC flash that's a hard nut to crack.

Synthetic Benchmarks – CrystalDiskMark & AS SSD

CrystalDiskMark

Version and / or Patch Used: 3.0 Technical Preview

CrystalDiskMark is disk benchmark software that allows us to benchmark 4k and 4k queue depths with accuracy. Note: Crystal Disk Mark 3.0 Technical Preview was used for these tests since it offers the ability to measure native command queuing at QD4. When evaluating CDM results, we focus on 4K random performance at QD1 and QD4.

101

101

101

Focusing in on QD1 and QD4 has the M8Se smoking the competing SSDs in our test pool except for Samsung's 960 EVO. Impressive synthetic performance to be sure. Although not the focus of our CDM testing, we will note the exceptional QD1 sequential read performance.

101

Like we saw with Anvil's, random write performance isn't the strong suit of the M8Se.

AS SSD

Version and / or Patch Used: 1.8.5611.39791

AS SSD determines the performance of SSDs. The tool contains four synthetic as well as three practice tests. The synthetic tests are to determine the sequential and random read and write performance of the SSD. We evaluate AS SSD performance in terms of overall score. We are looking for a minimum score of 2,000 when evaluating NVMe SSDs.

101

101

101

AS SSD is a demanding test, and the 512GB M8Se handles it with ease - delivering a score that is up there with some of the best. If we focus on the read score, we again see that the 960 EVO is the only drive in our test pool that is capable of besting the M8Se 512GB. The 256GB model does not fare nearly as well. Overall, it only outperforms the Intel 600p. It does, however, deliver a better-read score than the SX8000.

Benchmarks (OS) - Vantage, PCMark 7, PCMark 8 & SYSmark 2014 SE

Moderate Workload Model

We categorize these tests as indicative of a moderate workload environment.

PCMark Vantage - Hard Disk Tests

Version and / or Patch Used: 1.2.0.0

The reason we like PCMark Vantage is because the recorded traces are played back without system stops. What we see is the raw performance of the drive. This allows us to see a marked difference between scoring that other trace-based benchmarks do not exhibit. An example of a marked difference in scoring on the same drive would be empty vs. filled vs. steady state.

We run Vantage three ways. The first run is with the OS drive 75% full to simulate a lightly used OS volume filled with data to an amount we feel is common for most users. The second run is with the OS volume written into a "Steady State" utilizing SNIA's consumer guidelines. Steady-state testing simulates a drive's performance similar to that of a drive that been subjected to consumer workloads for extensive amounts of time. The third run is a Vantage HDD test with the test drive attached as an empty, lightly used secondary device.

OS Volume 75% Full - Lightly Used

101

101

OS Volume 75% Full - Steady State

101

101

Secondary Volume Empty - FOB

101

101

There's a big difference between an empty drive, one that's 75% full/used, and one that's in a steady state.

101

The important scores to pay attention to are "OS Volume Steady State" and "OS Volume 75% full." These two categories are most important because they are indicative of typical of consumer user states. When a drive is in a steady state, it means garbage collection is running at the same time it's reading/writing.

Focusing in on 75% full and steady-state performance, we see the 512GB M8Se delivering performance that is on par with one of our favorites the MDD BPX. The 256GB M8Se doesn't perform nearly as well, but even so, it does manage to outperform the 600p and the SX8000. The MLC powered M8Se, on the other hand, performs exceptionally well, in fact, it is the winner of this testing.

PCMark 7 - System Storage

Version and / or Patch Used: 1.4.0

We will look to Raw System Storage scoring for evaluation because it's done without system stops and, therefore, allows us to see significant scoring differences between drives. When evaluating NVMe SSDs, we are looking for a minimum score of 11,000

OS Volume 75% Full - Lightly Used

101

101

101

The 512GB M8Se digests this test extremely well, delivering a score that is second only to the RD400. The 256GB model also delivers an excellent score, in-fact it is better than we are getting from Samsung's 960 EVO.

PCMark 8

Version and / or Patch Used: 2.4.304

We use PCMark 8 Storage benchmark to test the performance of SSDs, HDDs, and hybrid drives with traces recorded from Adobe Creative Suite, Microsoft Office, and a selection of popular games. You can test the system drive or any other recognized storage device, including local external drives. Unlike synthetic storage tests, the PCMark 8 Storage benchmark highlights real-world performance differences between storage devices. We focus on the total score first and then storage bandwidth when evaluating PCMark 8 results.

OS Volume 75% Full - Lightly Used

101

101

101

PCMark 8 is the most intensive moderate workload simulation we run. With respect to moderate consumer type workloads, this test is what we consider the best indicator of a drive's performance. The intensive nature of this benchmark doesn't mix very well with the M8Se's planar TLC flash array. The results aren't very good, but they not very bad either. The M8Pe scores about 10 points higher than does the 512GB M8Se. We believe that the length of the test overwhelms the drive's NitroCache and this results in a lower score than we would like to see. The good news is that most consumer workloads don't run for an hour, not even close to that.

BAPCo SYSmark 2014 SE Application Performance

Version and / or Patch Used: 2.0.0.70

SYSmark 2014 SE is considered the gold standard for testing system performance because it is an application based benchmark. This test gives us the ultimate in real-world results because it utilizes actual applications running on the system, instead of playing back recorded traces. If you want to know what kind of impact a particular SSD will have on your system's overall performance; this test will show you.

Our systems are much more powerful than the calibration system (1000-point baseline) used by BAPCo, so we ran an OCZ TL100 120GB SATA III SSD to establish a comparison point relative to our test systems. We will be running this test going forward, and we will add drives to our chart as we test them.

101

101

101

Surprisingly, the 256GB M8Se outperforms the 512GB model. The 256GB M8se is delivering system performance that is about the same as Samsung's 1TB PM961 which is one of our favorite SSDs. Our takeaway from this testing is something that we have harped on before. We would really like it if Plextor offered a proprietary NVMe driver, performance could be so much better.

Benchmarks (Secondary) - IOPS, Response & Transfer Rate

Iometer – Maximum IOPS

Version and / or Patch Used: Iometer 2014

We use Iometer to measure high queue depth performance. (No Partition)

Max IOPS Read

101

101

Max IOPS Write

101

101

101

We test NVMe SSDs using eight threads at QD32, or QD256. We do this because we want to see what the drive can generate at its maximum attainable queue depth. The M8Se delivers plenty of random read IOPS, but the drive's planar TLC flash array cannot sustain high write IOPS for the 30 seconds that we run the test. This is common to all planar TLC SSDs.

Iometer – Disk Response

Version and / or Patch Used: Iometer 2014

We use Iometer to measure disk response times. Disk response times are measured at an industry accepted standard of 4K QD1 for both write and read. Each test runs twice for 30 seconds consecutively, with a 5-second ramp-up before each test. We partition the drive/array as a secondary device for this testing.

Avg. Write Response

101

101

Avg. Read Response

101

101

101

The results of this testing indicate that we are bypassing the drive's NitroCache and what we are seeing is the native performance of the drive's TLC flash array.

DiskBench – Transfer Rate

Version and / or Patch Used: 2.6.2.0

We use DiskBench to time a 28.6GB block (9,882 files in 1,247 folders) composed primarily of incompressible sequential and random data as it's transferred from our Toshiba RD400 1TB NVME SSD to our test drive. We then read from a 6GB zip file that's part of our 28.6GB data block to determine the test drive's read transfer rate. Our system is restarted prior to the read test to clear any cached data, ensuring an accurate test result.

Write Transfer Rate

101

101

Read Transfer Rate

101

101

101

We recently upgraded our test system to Windows 10 build 14393. With that upgrade, write transfer rates almost doubled. The reason for this, as far as we know, is that CPU power switching modes have been relaxed on the latest version of Windows 10. We included the NVMe drives we've tested to date on this build of Windows 10. If you needed a good reason to upgrade to a newer version of Windows 10; this is a good reason.

As expected, we are seeing very good read transfer results and poor write transfer results. This is to be expected from a planar TLC flash array.

Benchmarks – 70/30 Mixed Workload & Sustained Sequential Write

70/30 Mixed Workload Test (Sledgehammer)

Version and / or Patch Used: Iometer 2014

Heavy Workload Model

This test hammers a drive so hard we've dubbed it "Sledgehammer." Our 70/30 Mixed Workload test is designed to simulate a heavy-duty enthusiast/workstation steady-state environment. We feel that a mix of 70% read/30% write, full random 4K transfers best represents this type of user environment. Our test allows us to see the drive enter into and reach a steady state as the test progresses.

Phase one of the test preconditions the drive for 1 hour with 128K sequential writes at QD32. Phase two of the test runs a 70% read/30% write at QD32, full random 4K transfer workload on the drive for 1 hour. We log and chart (phase two) IOPS data at 5-second intervals for 1 hour (720 data points). 60 data points = 5 minutes.

101

What we like about this test is that it reflects reality. Everything lines up, as it should. Consumer drives don't outperform Enterprise-Class SSDs that were designed for enterprise workloads. Consumer drives based on old technology are not outperforming modern Performance-Class SSDs, etc.

We were expecting to see wild variability coming from a TLC flash array, but the Eldora controller keeps things nice and tight. The M8Se would greatly benefit from some OP when running heavy sustained workloads. However, we doubt that someone that actually does run heavy sustained workloads would buy an M8Se in the first place. For those types of workloads, Plextor's M8Pe fits the bill nicely. The 512GB M8Se delivers similar performance to OCZ's 256GB RD400, the 256GB M8Se similar performance to the Samsung 960 EVO 250GB.

Sustained Sequential Write

Version and / or Patch Used: Iometer 2014

Heavy Workload Model

We write to the drive for 1 hour with 128K sequential writes at QD32. We log and chart megabytes per second data at 5-second intervals for 1 hour (720 data points). 60 data points = 5 minutes.

101

This test unmasks sequential write performance of TLC flash arrays. The 512GB M8Se sustains writes at 507 MB/s, the 256GB model 304 MB/s. Although relatively low, it is certainly better than we are getting from Intel's 600p. Samsung's 250GB 960 EVO gets similarly pummeled by this test.

Maxed-Out Performance (MOP)

This testing is just to see what the drive is capable of in an FOB (Fresh Out of Box) state under optimal conditions. We are utilizing empty volumes of Windows 10 and Windows Server 2012 R2 64-bit for this testing.

Windows 10 MOP

Plextor M8SeY 512GB AIC PCIe NVMe SSD

101

101

101

101

101

101

Windows 10 MOP

Plextor M8SeGN 256GB M.2 PCIe NVMe SSD

101

101

101

101

101

101

Windows Server 2012 R2 MOP

Plextor M8SeY 512GB AIC PCIe NVMe SSD

101

101

101

101

101

101

101

Windows Server 2012 R2 MOP

Plextor M8SeGN 256GB M.2 PCIe NVMe SSD

101

101

101

101

101

101

101

Final Thoughts

101

Plextor's M8Se is certainly the fastest planar TLC-based SSD to come across our bench. But, that's not saying much in the grand scheme of things. We expected to see far worse performance, but we were pleasantly surprised by what the M8Se was able to deliver. One thing we want to alert our readers to is firmware. If by chance you get your own M8Se and it is sporting 1.00 firmware, immediately update to 1.01 firmware. We found a problem with 1.00 firmware that only manifests itself when the drive is loaded up with data. We alerted Plextor of the issue, they identified it and responded with 1.01 firmware which fixed the issue.

We are very pleased with the synthetic performance that the M8Se delivers. It's low queue depth random read performance is stellar, and that is a very important consideration when considering any SSD for a system disk for consumer applications. Similarly, its low queue depth sequential read performance is a cut above what we typically see from most SSDs.

In terms of overall performance when running moderate workloads, you can expect the M8Se to deliver moderate workload performance that is equivalent to Samsung's popular 250GB 960 EVO. If Plextor were to develop a proprietary NVMe driver, we could expect quite a bit more from the M8Se. We would really like to see Plextor, as well as others, offer a NVMe driver for Windows 8.1-10.

Even though the M8Se doesn't deliver earth-shattering benchmarks, it does deliver an excellent user experience. We were very pleased with the M8Se in that regard. The drive is fast and responsive – giving us the user experience we are looking for from an NVMe SSD. As SSDs go, the M8Se is a mid-level performer and is indeed worthy of your consideration. For those of you that are into looks, the M8SeY has got you covered and then some. We would have to say that the M8SeY is probably the best looking SSD we've seen to date. The drive is fast, runs cool and really delivers the bling when powered on.

The M8Se isn't the fastest, but it is plenty fast enough for the average user and not just by the numbers, but more importantly, by the user experience it delivers. With these things in mind, we have no reservation in awarding Plextor's M8Se NVMe SSD a TweakTown recommendation.

Pros:

• Synthetic Performance
• Sleek Design
• LDPC

Cons:

• No SSD Management Tool Box
• Write Transfer Rate