Mixed Random Read/Write Performance

The mixed random I/O benchmark starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. The queue depth is 3 for the entire test and each subtest lasts for 3 minutes, for a total test duration of 18 minutes. As with the pure random write test, this test is restricted to a 16GB span of the drive, which is empty save for the 16GB test file.

Iometer - Mixed 4KB Random Read/Write

With a relatively low queue depth, this test is mostly about the access latency of the flash itself, and it's no surprise that the heatsink makes no difference to the M8Pe's performance. The M8Pe is slightly faster than the older Intel SSD 750 and Samsung 950 Pro, but is slower than the OCZ RD400 and Samsung 960 Pro.

Iometer - Mixed 4KB Random Read/Write (Power)

Power consumption is again higher than the competition, giving the M8Pe in either configuration a poor efficiency score.

Performance increases relatively slowly as the proportion of writes increases; this is unsurprising given that we've already seen the M8Pe's strengths lie in its read speeds. The spike in performance in the final all-writes phase of the test is respectable and brings the average up to a typical score for this product segment.

Mixed Sequential Read/Write Performance

The mixed sequential access test covers the entire span of the drive and uses a queue depth of one. It starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. Each subtest lasts for 3 minutes, for a total test duration of 18 minutes. The drive is filled before the test starts.

Iometer - Mixed 128KB Sequential Read/Write

The data rates on the mixed sequential I/O test are high enough that thermal throttling becomes a factor, and the presence of a heatsink improves the M8Pe's average by 11%. Performance in either configuration is a bit sub-par for an MLC-based PCIe SSD, but it's still at least twice as fast as any SATA SSD.

Iometer - Mixed 128KB Sequential Read/Write (Power)

Power consumption is again the highest of any M.2 PCIe SSD, and efficiency isn't great.

There appears to be a little bit of thermal throttling during the first phase of this test, but most of it occurs at the end when the workload is all writes.

Sequential Performance ATTO, AS-SSD & Idle Power Consumption
Comments Locked

64 Comments

View All Comments

  • TheinsanegamerN - Wednesday, December 14, 2016 - link

    The add-in PCIE card appears to be the best thing about the SSD. Just looking at how much faster the drive was with the heatsink, makes me want the PCIE card but with a 960 EVO or PRO in it.
  • BrokenCrayons - Wednesday, December 14, 2016 - link

    I'm hoping that PCIE slot storage takes off. Now that we've largely eliminated optical drives and floppies have been dead for ages, it's only a matter of time before we can shed conventional hard drive bays from computers too. Yeah, I know some small form factor systems have already reached that point (which is pretty cool) but it'd be nice to see that become the norm in mainstream systems as well. There's nothing more annoying than a huge, clunkly computer case and once 3.5 and 2.5 inch drives are gone, the only thing holding us back will be graphics adapters.
  • XabanakFanatik - Wednesday, December 14, 2016 - link

    Someone already makes a pretty nice looking heatsink card that looks like it wouldn't block much of the video card above it. I think I'm going to get one for my 960 Pro.

    http://preview.tinyurl.com/h2435pf
  • fanofanand - Wednesday, December 14, 2016 - link

    This review is a terrific reminder of just how bad the 600p sucks. Nice write-up Billy, very informative.
  • Bullwinkle J Moose - Thursday, December 15, 2016 - link

    NoFanOfAnand

    Horrible Review
    Many of you think I'm a Troll but can you answer 3 simple questions from the data provided?

    1. What is the average Read Speed in MB/sec for a 100GB file of Non Compressible Test Data?

    2. What is the average Write Speed in MB/sec for a 100GB file of Non Compressible Test Data?

    3. and most importantly, what is the average Copy and paste speed in MB/sec for a single 100GB non compressible test file when copying and pasting to the same drive?

    Can you answer these simple questions?

    Billy?
  • BrokenCrayons - Thursday, December 15, 2016 - link

    "All of you know I'm a Troll but can you answer 3 stupid questions..."

    Fixed that for you. :3
  • Bullwinkle J Moose - Thursday, December 15, 2016 - link

    Good try Crayon but you're zero for three

    Anyone else wanna try?

    Cmon, isn't there anyone here smarter than a fucking crayon?
  • BrokenCrayons - Thursday, December 15, 2016 - link

    I've gotten far enough under your skin that you're keeping imaginary score to feel better.
  • Holliday75 - Thursday, December 15, 2016 - link

    I don't remember Bullwinkle being such a jerk. He was a nice moose.
  • BrokenCrayons - Thursday, December 15, 2016 - link

    He was a nice moose, but I admit I liked the squirrel with the flying helmet a bit more. :3

Log in

Don't have an account? Sign up now