Power Consumption

We're introducing a new part of our power consumption testing with this review: measurement of slumber power with host initiated power management (HIPM) and device initiated power management (DIPM) enabled. It turns out that on Intel desktop platforms, even with HIPM and DIPM enabled, SSDs will never go into their lowest power states. In order to get DIPM working, it seems that you need to be on a mobile chipset platform. I modified an ASUS Zenbook UX32VD to allow me to drive power to the drive bay from an external power supply/power measurement rig. I then made sure HIPM+DIPM were enabled, and measured average power with the drive in an idle state. The results are below:

SSD Slumber Power (HIPM+DIPM)

Samsung does amazingly well in this test, with only Intel's first generation X25-M SSD coming anywhere close. The SanDisk drives do alright here, although they're a bit more power hungry than some of the others the differences aren't large enough to meaningfully impact most notebook usage. The important thing to note is just how bad power consumption can get if your drive doesn't properly support HIPM and DIPM. It's when you start getting into the 500mW - 1000mW range that you'll see real impacts to notebook battery life.

Our traditional idle power test is still useful as this is representative of power consumption in an active idle state. The lowest power states do take time to get in/out of, so if you're actively using your machine you may see some time spent in a non-slumber idle state which is effectively the data you see below:

Drive Power Consumption - Idle

Once again, the Extreme II does alright here. Idle power consumption isn't high enough to be a problem for notebook users, it's just not low enough to be as good as Samsung.

Under load the story is a little different. Peak sequential IO power consumption is very Samsung-like, but power consumption with a random write workload is amazingly low. I suspect this is a side effect of whatever SanDisk is doing to keep IO consistency in check.

Drive Power Consumption - Sequential Write

Drive Power Consumption - Random Write

AnandTech Storage Bench 2011 - Light Workload Final Words


View All Comments

  • HardwareDufus - Monday, June 3, 2013 - link

    Amazing. I am using an OCZ Vertex4 256GB drive. Bought it last Nov for about $224. Very happy with it.
    This SanDisk drive is the same price ($229), same capacity (240GB), same format. However, it is performing a full 5% to almost 100% better, depending on block size, random/sequential, read/write activity. Amazing what 7 to 12 months has brought to the SSD market!
  • Vincent - Monday, June 3, 2013 - link

    You wrote: "In our Intel SSD DC S3700 review I introduced a new method of characterizing performance: looking at the latency of individual operations over time"

    In fact this is not what your test does. Your test records IOPS in one-second periods, but does not measure the latency of individual IOs. It would in fact be interesting to see the latency distribution for these drives.
  • Tjalve - Tuesday, June 4, 2013 - link

    Ive done som IO Latency tests based on my own trace-based benchmark if your interested.
    The text is in swedish, but you should be able to understand the graphs. I could make aplot diagram of individual IOs Latency if anyone is interested,
  • kallogan - Tuesday, June 4, 2013 - link

    I still have an indilinx 64GB. Reply
  • dishayu - Tuesday, June 4, 2013 - link

    Is it just me or have the SSD prices stagnated since the past year or so? I bought a 120GB Plextor M5S for $85 in July 2012 and the 128 GB SSDs still seem to hover in the 100-120$ range. Reply
  • sna1970 - Tuesday, June 4, 2013 - link

    Hey Anand , can you please test 6 SSD Raid 0 with the new Haswell Z87 motherboards ?

    we need to make sure we can hit 3G/s , what is the maximum bandwidth of the new chipset ?
  • cbk - Tuesday, June 4, 2013 - link

    This looks awesome, it's almost neck-to-neck to the 840 Pro, at a lower price. Reply
  • jeffrey - Tuesday, June 4, 2013 - link

    Hi Anand,
    Do you plan on covering the OCZ Vertex 450?
  • jeffrey - Tuesday, June 4, 2013 - link

    Press Release:

  • Kristian Vättö - Tuesday, June 4, 2013 - link

    All tests have been run but I guess Haswell and other Computex stuff got on the way. Reply

Log in

Don't have an account? Sign up now