Mixed Random Performance

Our test of mixed random reads and writes covers mixes varying from pure reads to pure writes at 10% increments. Each mix is tested for up to 1 minute or 32GB of data transferred. The test is conducted with a queue depth of 4, and is limited to a 64GB span of the drive. In between each mix, the drive is given idle time of up to one minute so that the overall duty cycle is 50%.

Mixed 4kB Random Read/Write

The Optane SSDs put even Samsung's best NVMe SSDs to shame on the mixed random I/O test. The 800p is a little more than half as fast as the 900p, which is plenty to put it far out of reach of the flash-based SSDs.

Mixed 4kB Random Read/Write (Power Efficiency)

The Optane SSD 800p takes first place for power efficiency on the mixed random I/O test, with the 58GB model having a slight advantage over the 118GB due to the lower power consumption of operating half as many 3D XPoint dies. The flash-based SSDs come close to matching the efficiency of the Optane SSD 900p, but are far behind the 800p.

With no write buffering, the Optane SSDs show a steady decline in performance as the proportion of writes increases, with no spike in performance at the end as is typical of flash-based SSDs with aggressive write combining. The 800p shows a more pronounced reduction in performance than the 900p, while the 900p's power consumption climbs more.

Mixed Sequential Performance

Our test of mixed sequential reads and writes differs from the mixed random I/O test by performing 128kB sequential accesses rather than 4kB accesses at random locations, and the sequential test is conducted at queue depth 1. The range of mixes tested is the same, and the timing and limits on data transfers are also the same as above.

Mixed 128kB Sequential Read/Write

With only a PCIe x2 interface and sequential write speeds that only use a fraction of that bandwidth, the Optane SSD 800p is actually performing pretty well on the mixed sequential I/O test. The 800p has the same average performance as Samsung's fastest TLC SSD, and offers more than two thirds the performance of the Samsung 960 PRO.

Mixed 128kB Sequential Read/Write (Power Efficiency)

The power efficiency of the Intel Optane SSD 800p is second only to that of the Samsung 960 PRO. The 800p's efficiency score is far above the 900p and the low-end NVMe SSDs.

As with the mixed random I/O test, the Intel Optane SSD 800p shows a steady decline inn performance as more writes are added to the mix. The decline is steeper than the one shown by the 900p. Power consumption increases very slightly over the course of the test but still stays within the rated maximum.

Sequential Performance Power Management
Comments Locked

116 Comments

View All Comments

  • Reflex - Thursday, March 8, 2018 - link

    I'm sorry you know how many are rushing out to buy a product that isn't available yet? I don't personally expect large volumes since at the current capacities it isn't in the sweet spot for consumers in price/perf, but its offering solid performance that bests NAND in almost every consumer scenario, in some cases significantly while consuming less overall power. That's a win. As production ramps, costs will come down.

    And only the literacy challenged have chosen to read Intel's claims about 3DXPoint's potential as claims about its first generation products. Right now its constrained by a number of things beyond the memory itself, such as PCIe bus speed.
  • iter - Friday, March 9, 2018 - link

    And I am sorry don't possess common sense.

    Of course I am not talking about how the 800p sells, only a complete idiot could take this out of my comments. I am talking about the non-existent demand for it in the enterprise, which the introduction of the 800p is another testament to.

    If intel was able to sell it at high enterprise margins they wouldn't be forcing it in the consumer world where it is pointless. Intel is not keep on losing money, and as overpriced as it is even as a consumer product, it is tremendously cheaper than what they can ask for it at the enterprise market. Instead they are marketing it to frigging games... which is 100% laughable.

    And of course, I don't expect anyone save for silly fanboys with rich mommies to buy it in the consumer world. because it can offer absolutely nothing for the price premium it comes at. No intelligent human being would pick a 118 gb 800p to a decent 256 gb nvme or 512 gb ssd drive. None whatsoever.

    Constrained by PCIe? It doesn't even come close to that. Neither in terms of bandwidth nor latency. But believe whatever it takes to reinforce your fake worldview.
  • Luckz - Wednesday, April 25, 2018 - link

    Is there actually a point to 256 gb NVMe though? I mean, performance of the small 960 Evo sucks balls compared to the bigger ones. Why go NVMe when you can have a nice SATA drive with much more capacity and not even much worse perf?
  • Adramtech - Saturday, March 10, 2018 - link

    iter, Lehi fabs are 100% dedicated to Xpoint and no longer NAND. They wouldn't commit billions to that if they didn't have a path outlined for improvement and scaling.
  • patrickjp93 - Saturday, March 10, 2018 - link

    Are you kidding? AWS Memcached, Lambda, and DynamoDB have their caching layers and indexing stored in Optane.
  • eddman - Saturday, March 10, 2018 - link

    We just found ddriver's long lost twin brother.
  • Alexvrb - Saturday, March 10, 2018 - link

    Cloning tech gone wrong.
  • Reflex - Saturday, March 10, 2018 - link

    It's not his twin, it's just his new account. This place had a much better community during the too brief time he was gone.
  • patrickjp93 - Saturday, March 10, 2018 - link

    3DXP is being made on the 90nm node right now. What did you expect? It's a vastly cheaper research node for something so complex.

    And the performance is stunningly better than everything else Samsung has EXCEPT for high Queue Depth sequential performance. All real world testing shows the 960Pro getting smashed.
  • Reflex - Saturday, March 10, 2018 - link

    Didn't you hear the memo that because this first gen product isn't as good as the theoretical max performance discussed three years ago its all a big fail? /sarcasm

Log in

Don't have an account? Sign up now