Random Read Performance

For full details of how we conduct our Iometer tests, please refer to this article.

Iometer - 4KB Random Read

Random read performance is quite average and only Samsung has a notable advantage in this field, which is partly due to 3D V-NAND and its lower latencies. 

Iometer - 4KB Random Read (Power)

Power consumption is on par with the BX100 and even though the BX100 has a slight performance advantage, the SX930 is very power efficient in random reads.

ADATA XPG SX930

Performance scaling could be a little more aggressive especially at QD4 and QD8, but overall random performance appears to be suited for the product.

Random Write Performance

Iometer - 4KB Random Write

Random write performance is mediocre and especially the 480GB SKU could use a boost to be more competitive. Fortunately power consumption is quite low, so the overall efficiency is decent.

Iometer - 4KB Random Write (Power)

Given the pseudo-SLC cache, one would expect performance scaling to be more aggressive from low to high, especially at QD4 and above, but there leaves an element of wanting compared to other high-end drives on the market.

ADATA XPG SX930
AnandTech Storage Bench - Light Sequential Performance
Comments Locked

67 Comments

View All Comments

  • sonny73n - Thursday, July 16, 2015 - link

    LOL @EVO 3-bit NAND...
    I just threw out my 1 year old 840EVO 250GB which was the worst SSD I've ever had. MX200 500GB is in and I wish I could've got this one from the begining instead of the EVO junk.
  • Stochastic - Thursday, July 16, 2015 - link

    Just curious, what problems did you encounter?
  • fokka - Thursday, July 16, 2015 - link

    i guess the same as so many others, which still has no real fix: http://www.anandtech.com/show/8550/samsung-acknowl...
  • Impulses - Thursday, July 16, 2015 - link

    That's not about the 850.
  • Adding-Color - Thursday, July 16, 2015 - link

    What not about the 850? OP was talking about the 840!
  • futrtrubl - Thursday, July 16, 2015 - link

    Actually the OP was talking about something to challenge the EVO, the latest of which is the 850.
  • Samus - Saturday, July 18, 2015 - link

    What proof does anybody have the 850EVO is going to be any difference than the 840EVO with performance degradation. They use the same technology and only the 850PRO get's the binned, lower node 3D VNAND.
  • voicequal - Monday, July 20, 2015 - link

    The 840EVO was on ~19nm NAND. The 850EVO uses 40nm V-NAND which should provide much greater cell integrity needed for TLC operation.
  • sonny73n - Friday, July 17, 2015 - link

    What about the 850? After my experience with that "EVO", Samsung 3-bit TLC NAND in particular, I had lost interest and trust in Samsung. The 830 Pro 128GB I had years ago was excellent though but it took a chunk out of my pocket. So I guess when it comes to value for the money, I should always look somewhere else.
  • bug77 - Friday, July 17, 2015 - link

    Then you don't know that the 850 EVO has *nothing* to do with 840 EVO. Not surprising, otherwise you wouldn't have bought that PoS. The planar TLC is bottom of the barrel, with slow access and probably under 1000 P/E cycles. The 850 EVO uses 3D NAND which alleviates those issues.
    So you see, it really wasn't an 840 EVO problem, it was a planar TLC NAND problem. Many cheap drives still use that.

Log in

Don't have an account? Sign up now