AES-NI: Much Faster Encryption & Bitlocker Performance

Westmere (and thus Clarkdale) adds some new instructions to x86, although the big expansion comes with AVX and Sandy Bridge next year. Westmere gets six new encryption/decryption instructions. The group of instructions accelerate AES (Advanced Encryption Standard) and are thus referred to as AES-NI.

Many businesses require that all corporate PCs have the contents of their hard drives encrypted through the use of software like Bitlocker that comes with Microsoft Windows 7. These sorts of applications can be accelerated by AES-NI and to show the potential benefit I dug up a test I did while preparing for one of our SSD articles several months ago.

If you turn on Bitlocker in Windows 7 there's an immediate and measurable impact to performance. Disk performance generally drops by a noticeable amount and actual application usage performance drops by a smaller amount. Every write to the disk has to be encrypted first so there's some obvious CPU overhead. Clarkdale should reduce that overhead significantly as the common encryption operations are now hardware accelerated.

To test this I ran three tests. I first ran PCMark Vantage's HDD suite on my Windows 7 testbed SSD (an OCZ Summit) on a Core i5 661, then encrypted the drive using Bitlocker and ran the same test on the same processor. For the last test I swapped out the i5 661 for a Lynnfield based Core i5 750 (no AES-NI) and re-ran the HDD test. The results below were quite promising:

Processor PCMark Vantage HDD % of Unencrypted Performance
Clarkdale - Unencrypted 16713  
Clarkdale - Bitlocker Encryption 13785 82.5%
Lynnfield - Bitlocker Encryption 11744 70.3%

 

There's a definite benefit to Clarkdale's AES-NI instructions. There's still a performance hit from enabling Bitlocker, but it's not nearly as great as on Lynnfield and other architectures that don't have AES-NI support. With a smaller decrease in I/O performance from enabling full disk encryption, there's also a smaller hit to application performance as well. This is huge for corporate desktops/notebooks.

Most of those machines aren't quad-core encoding monsters; they use dual-core processors. The upgrade from Core 2 seems like it'd be worth it, or at least AES-NI will probably keep AMD out of the running for consideration.

Intel HD Graphics: A Lot Better ASUS Saves the Day: Simulated Core i3s & The Test
POST A COMMENT

93 Comments

View All Comments

  • SydneyBlue120d - Tuesday, February 09, 2010 - link

    The Intel G9650 doesn't exist, what You're referring is Intel G6950
    http://ark.intel.com/Product.aspx?id=43230">http://ark.intel.com/Product.aspx?id=43230
    Reply
  • puterfx - Wednesday, February 03, 2010 - link

    I've been building systems since the late 90's, mostly for others, and I'm always the last to get a decent system so I decided it was about time for me. I'm running an e6600 on a 3 yr old Intel board w/ 2g of DDR2 RAM and was wondering about the differences between C 2 quad, i3-540, i5-750 or i7-820. I priced out 3 different setups with Gigabyte boards (EP45, H57 & P55 - USB3 ver.) combined with Q8400/9300/9400 on EP45, i3-540,i5-750 and i7-820 on the H57 & P55 and 4 Gb DDR3 RAM (Crucial, Geil, Kingston)so , basically, I had 9 combinations. Excluding the i7, the price range for these builds was about $429 - $487, and I could probably do better if I tried but I was amazed that they were that close (the i7 adds another $100 but not that much improvement in performance that I can see).

    Looking at your charts, I think I can justify going with the i5-750. I have a decent video card for the occassional gaming that works pretty good for me now (I'll apply the $100 from above to a better card later) but I do a lot of spreadsheets and some photoshop and autocad so I think I'll see a better improvement there.

    Thanks again for all your articles. Very well written, understandable and thorough.
    Reply
  • KingAlexander - Saturday, January 30, 2010 - link

    I too am puzzled by the i7 870 scoring so low on the World of Warcraft chart -- it stood out to me immediately when I first read the article. I was a little surprised to not see it mentioned.

    It was suggested in another comment that this was due to the game having an issue with hyperthreading, but if that was the case shouldn't the i7 920 also have scored significantly lower than it did?
    Reply
  • Bloodx - Monday, January 25, 2010 - link

    It should be noted that this new intel system does not work
    at 1080p/24 correct. The nvidia 9400 chipset works at 1080p/24.
    So i've traded audio for skipping.
    HTPC is no better off. Sad.
    Reply
  • geok1ng - Sunday, January 10, 2010 - link

    Previous Intel IGPs managed achieve less terrible numbers in game by cheating- they didn't render all the polygons and textures. So for good measure i require side by side screenshots of the "new, better, faster and cheaper" Intel IGP.

    The idea of an Intel IGP that simply isn't horrible is SOO strange that a true review would have to go the race: benchmarks, screenshots, minimum playable settings for various games and screenshots. Something the articles on HardOCP.
    Reply
  • snakyjake - Wednesday, January 06, 2010 - link

    Why isn't the i7-860 tested in the section "Windows 7 Application Performance"?

    Without the i7-860 in the Windows 7 test section, this review is pointless.
    Reply
  • NeBlackCat - Wednesday, January 06, 2010 - link

    I was hoping to build a new always-on home server around one of these. Power miserly IGP and idle operation (for when it's only firewalling and routing) but plenty of grunt in reserve for occasional video encoding, compiling and running virtual machines.

    Looks like they missed the mark for this application, and I couldn't even adopt now and wait for the real deal CPU later, as the socket is a dead end.

    IMHO only the HTPC crowd have a reason to be excited here, but there are lots of other (cheaper) ways to get low power 1080p too.
    Reply
  • ruetheday - Friday, January 08, 2010 - link

    Let's wait and see - There are products coming which will do gpu assisted transcoding that might shift things in Clarkdale's favor. Reply
  • bongbong - Tuesday, January 05, 2010 - link

    I know for a fact that the athlon II x3s and x4s have to overclock like crazy in games to reach the same performance delta as their phenom II x3 and x4 brethren
    (coz of the 6mb cache and many games are dependent on cache)
    Ive seen gaming benchmarks on anandtech where the x3 720 matched the x4 965 when they are both overclocked to 3.8ghz.
    I was able to buy an x3 720 for only a 110 usd recently.
    So why isnt it in the benchmark comparisons?


    Reply
  • JohnMD1022 - Tuesday, January 05, 2010 - link

    $150 from microcenter. Reply

Log in

Don't have an account? Sign up now