A Custom Form Factor PCIe SSD

In the old days, increasing maximum bandwidth supported by your PATA/SATA interface was always ceremonial at first. Hard drives were rarely quick enough to need more than they were given to begin with, and only after generations of platter density increases would you see transfer rate barriers broken. Then came SSDs.

Not only do solid state drives offer amazingly low access latency, but you can hit amazingly high bandwidth figures by striping accesses across multiple NAND Flash die. A 256GB SSD can be made up of 32 independent NAND die, clustered into 8 discrete packages. A good controller will be able to have reads/writes in flight to over half of those die in parallel. The result is a setup that can quickly exceed the maximum bandwidth that SATA can offer. Today that number is roughly 500MB/s for 6Gbps SATA, which even value consumer SSDs are able to hit without trying too hard. Rather than wait for another rev of the SATA spec, SSD controller makers started eyeing native PCIe based controllers as an alternative.

You can view a traditional SSD controller as having two sides: one that talks to the array of NAND flash, and one that talks to the host system’s SATA controller. The SATA side has been limiting max sequential transfers for a while now at roughly 550MB/s. The SATA interface will talk to the host’s SATA interface, which inevitably sits on a PCIe bus. You can remove the middle man by sticking a native PCIe controller on the SSD controller. With SATA out of the way, you can now easily scale bandwidth by simply adding PCIe lanes. The first generation of consumer PCIe SSDs will use PCIe 2.0, since that’s what’s abundant/inexpensive and power efficient on modern platforms. Each PCIe lane is good for 500MB/s, bidirectional (1GB/s total). Apple’s implementation uses two PCIe 2.0 lanes, for a total of 1GB/s of bandwidth in each direction (2GB/s aggregate).

The move to a PCIe 2.0 x2 interface completely eliminates the host side bottleneck. As I pointed out in my initial look at the new MacBook Air, my review sample’s 256GB SSD had no problems delivering almost 800MB/s in peak sequential reads/writes. Do keep in mind that you’ll likely see slower results on the 128GB drive.

Users have spotted both Samsung and SanDisk based PCIe SSDs in the 2013 MacBook Airs. Thankfully Apple doesn’t occlude the controller maker too much in its drive names. An SM prefix denotes Samsung:

My review sample featured a Samsung controller. There’s very little I know about the new Samsung controller, other than it is a native PCIe solution that still leverages AHCI (this isn't NVMe). Within days of Apple launching the new MBAs, Samsung announced its first consumer PCIe SSD controller: the XP941. I can only assume the XP941 is at least somewhat related to what’s in the new MBA.

The Samsung controller is paired with a 512MB DDR3 DRAM and 8 Samsung 10nm-class (10nm - 20nm process node) MLC NAND devices. 

New PCIe SSD (top) vs. 2012 MBA SATA SSD (bottom) - Courtesy iFixit

Despite moving to PCIe, Apple continues to use its own proprietary form factor and interface for the SSD. This isn’t an M.2 drive. The M.2 spec wasn’t far enough along in time for Apple to use it this generation unfortunately. The overall drive is smaller than the previous design, partially enabled by Samsung’s smaller NAND packages.

Absolutely Insane Battery Life PCIe SSD Performance
Comments Locked

233 Comments

View All Comments

  • lilo777 - Monday, June 24, 2013 - link

    It would help if you disproved something that was so wrong in my post. Perhaps people using OSX in their names are simply incapable of recognizing any Apple bias?
  • akdj - Thursday, June 27, 2013 - link

    In the ultra book market... and this price point....there aren't a lot of excellent choices right now for displays. If you step up to $1500-$1800...yes, one or two of the UltraBook vendors are selling 1080p IPS panels. At this price though...in the 'true' UltraBook sense of the word....go shopping at Best Buy sometime. Take a look at what Dell, Toshiba, Samsung and others are offering....again @ $1099. Asus is honestly the only one, in my opinion...that you can buy odd the shelf that competes. Period. You're right...it's time we get a 'better' panel. Perhaps 2014 will bring IGZO technology and production up to speed...IPS prices drop a bit...and Apple decides to equip a higher quality display. I'm all for it. But the current displays don't suck. They're excellent for what they are and at the current 'price point' you can't get that killer high rez panel from Sony. As well...at this size 11"), unless you double the resolution and pixel double as in the rMBP...raising the default resolution too much and text, icons, etc become to small. I'm always amazed at how much real estate I actually DO have on my 11" Air (2011)....in apps with 'full screen' capability....and until I bought the rMBP 15" last summer...I only used 17" MBPs!
  • TheinsanegamerN - Sunday, June 30, 2013 - link

    everyone overlooks something else with the 13 inch air's display...it's 16:10. which is amazing. i'd gladly take this over 16:9 anyday. wish more oems would go back to 16:10. and having seen the screen, and with a bias against macs...i kinda want one of the new airs.
  • darwinosx - Monday, June 24, 2013 - link

    The display is not glossy. Read the article you are commenting on.
  • lilo777 - Monday, June 24, 2013 - link

    You do not need to read the article to know that all Apple displays are glossy. It seems you do not even know what matte display looks like.
  • Sm0kes - Monday, June 24, 2013 - link

    Apple's Macbook Air lineup, while not as "glossy" in appearance as the Retina Macbook Pro's do still have a glossy coating. As a long time hater of glossy displays on notebooks, I have no issue with my Air.
  • amrs - Tuesday, July 23, 2013 - link

    No WWAN either. I think I'll upgrade my Thinkpad X201 to an X240s when those come out if it's any good. With matte display and 3G/4G inside too. Just the basics for mobile usage really.
  • Strulf - Monday, June 24, 2013 - link

    1920 x 1200 certainly would be nice. I want to upgrade my 2009 MBA but I'm gonna watch for the next revision - hopefully with a higher resolution then.
  • thinkpanda - Monday, June 24, 2013 - link

    I would like to share a few experience regarding to WiFi performance.

    I am using late 2011 MBP 13", which should support 3x3 802.11n. I connect home devices with Asus RT-AC66U router. I have a home server of Ubuntu Server 12.04 LTS, with Realtek 8168 GB Ethernet chip connected to the router. The home server has netatalk service installed to support AFP so that I mount the home server storage from MBP using AFP.

    When I copy file from server to my local SSD (just by dragging the file at Finder), I get file transfer rate of 39MB/s! This is not even an AC network, just N network.

    So I am curious that is it the server size TCP windows size settings affect the performance, and the OS X as client device is not affect at all ?
  • mikk - Monday, June 24, 2013 - link

    "It’s hilarious that Intel refused to give out die photos for anything other than quad-core Haswell GT2, citing competitive concerns, yet at Apple’s WWDC launch of the new MacBook Airs we got to see the first die shot of a dual-core Haswell GT3"

    Anand you are plain wrong here. Bad job! ULT GT3 photos are available from Intel since weeks!!!

    http://download.intel.com/newsroom/kits//core/4thg...
    http://download.intel.com/newsroom/kits//core/4thg...

Log in

Don't have an account? Sign up now