Intel Core i5-661: Clarkdale Rings The Death Knell Of Core 2

Accelerating Encryption: AES-NI

If you’re an average desktop user, encryption probably isn’t very important to you today. After all, password-protecting everything just creates one extra layer of complexity when you want to actually use your machine, right? But for those with something to hide (and I think that includes all of us to some degree, thank you very much Eric Schmidt), there’s value in being able to protect that information.

All of Intel’s 32nm Westmere-based processors, starting with the dual-core Clarkdale desktop CPUs, include six new SIMD instructions that Intel calls AES-NI (Advanced Encryption Standard New Instructions), which are designed to help consolidate the mathematical operations used in the block cipher algorithm. In conjunction with applications optimized for AES-NI, the new instructions help maintain the security of AES by protecting against side-channel attacks, while alleviating the performance overhead of encrypting and decrypting in software.

Intel sees five different areas where its AES instructions apply: whole disk encryption (via apps like BitLocker, PGP, and TruCrypt), file storage encryption (7-Zip and WinZip are two favorites), conditional access of HD content (pay-to-play; yuck), Internet security, and VoIP communications. We have coverage upcoming putting AES-NI to the test with whole disk encryption, but wanted to at least run the new instructions through their paces in file storage encryption—something we all use in one form or another.

Our first round of tests pit the dual-core Core i5-661 against a number of quad-core models, along with Intel’s Core 2 Duo E8500, in the 9.10 beta of 7-Zip, which is optimized for AES-NI. Surprisingly, the Core 2 Duo actually finished our 334MB Ultra compression routine in less time than the Clarkdale chip.

Of course, we didn’t really have any reference point to compare against, so it was hard to say whether the performance delta was caused by the Core 2 architecture or some shortcoming inherent to Westmere. We nevertheless approached Intel with our findings, and the company let us know that 7-Zip’s compress/decompress algorithm operates in such a way as to cover up any benefit that’d otherwise be realized by AES-NI.

Such a "heavy" algorithm doesn’t help us much here, so we swapped to WinZip 14. Although we recently removed WinZip from our benchmark suite due to its single-threaded nature (and thus, generally slower performance than apps like WinRAR), this is another title optimized for AES-NI.

WinZip 14
Processor Family
Compress 334MB
Decompress 334MB
256-bit AES
Clarkdale (i5-661)
Lynnfield (i5-750)
No Encryption
Clarkdale (i5-661)
Lynnfield (i5-750)

Without the use of encryption, both our Lynnfield- and Clarkdale- CPUs are on even footing and we’re able to assess each CPU’s base performance in WinZip 14. The Core i5-750 is clearly faster in our compression test, finishing 20 seconds before the Core i5-661. However, Turbo Boost kicks in on the decompression, and the Clarkdale chip finishes the task a second quicker.

Enabling 256-bit AES tells the story we’re looking for, though. The gap in compression narrows to 16 seconds. And while the Lynnfield chip, which lacks AES-NI, incurs a six second penalty attributable to encryption, the Clarkdale processor suffers no such slow-down.

With all of that said, it's easy to fire up SiSoftware's Sandra 2010, run the Cryptography test, and witness the massive jump in iAES bandwidth attributable to Intel's new instructions. As you can see, the NSA's SHA-2 hash functions aren't accelerated, and consequently don't enjoy the speed-up seen by AES.

At least for now, the benefits of AES-NI are subtle at best. But, as is the case with any hardware capability reliant on software support, this will likely become a feature that has more of an impact as time goes on—and especially as Intel prepares to launch its Nehalem-EX processors in a couple of months. The tenets of security and encryption are most deeply rooted in the enterprise space, after all.

This thread is closed for comments
    Your comment
  • Zoonie
    Well... I think that takes care of the dreaded "But can it play Crysis?" question regarding its GMA :D :P :P
  • xc0mmiex
    Video on page 1 not working ... "This is a private video..."
  • eklipz330
    can i ask why you teased us at the end with the 4.5ghz OC but didn't include them in the benchmarks? =[ i'm guessing most of use at tom's like to OC... it could be the difference that gets us to buy the i5 661 over the phenom II
  • cangelini
    xc0mmiexVideo on page 1 not working ... "This is a private video..."

    Fixed! Had to keep it private pre-launch :)
  • I really like the improvements Larrabee brought about....not! I do like the fact they are making progress but they really need to skip ahead a few generations or buy out some other company to design a GPU for themselves.
  • gkay09
    ^ Many more reasons to buy AMD Phenoms II X4 in the mid-range segment...
    Only drawback with the AMD CPUs is the power consumption, that I feel can be brought down with slight undervolting...
  • dtemple
    I'm looking to upgrade from my Athlon X2 @ 2.7GHz because I do more with the computer now than I did before - sometimes I'll play a game while my TV tuner is recording from my cable signal, and having more cores would help these multiple tasks run more smoothly.
    I was waiting until the Clarkdale-based i5 launched, thinking it would be a quad-core that was more competitively priced against the Phenom II X4, but it looks like a Phenom II X4 is my only option to get more cores for less money.
    The only good news coming out of this launch is that LGA1156 is not changing for the Clarkdale chips, so it looks to be the most future-proof platform to upgrade to, if one was so inclined. I'm personally going with a Phenom II since I can get one without changing motherboards. This is one of the more disappointing launches in the last year or so.
  • cangelini
    eklipz330can i ask why you teased us at the end with the 4.5ghz OC but didn't include them in the benchmarks? =[ i'm guessing most of use at tom's like to OC... it could be the difference that gets us to buy the i5 661 over the phenom II

    We have another overclocking piece planned--I wanted to get a Core i3, at least, to include :)
  • I would love to see what GTA IV would do do the dual cores in gaming! I do know that its a bear of a game on the CPU and it would truly show off if hyperthreading could actually make a major difference.
  • maximus20895
    Great video once again! Thanks for this and the review itself. Very informative. I really liked the graph on the first page too :)
    good touch on the world of warcraft fraps. although not very playable on high settings is good to know what speeds it actualy gets
  • noob2222
    Would be nice to know if this thing can handle blue ray playback, as some of these would probably be sold as a HTPC. Ya, they put features for it, but does it play or not?

    Last preview I read showed it doing fine in windowed mode, but blowing chunks at full screen playback, dropping to 15fps and lower.
  • dupaman
    Idle power in the 70s for an IGP-based system is a huge failure not a win, though using an 1100W PSU probably deserves a lot of the blame. Systems built on the 780G, 730i, G4x, etc. (similar to this test platform, but use a more appropriate PSU) idle in the 40s.
  • shubham1401
    Nice dual....
    E8500 was beaten badly...

    Wud really like to see what these chips can do once overclocked.
  • thejerk
    Where are the H55 and H57 motherboards priced? So what if the processor is $200 if the motherboard is going to be another $200 on top of it, like P55. I'm not an AMD fanboi, but for less than $300, you can get excellent computing power. Platform cost is where AMD rules, currently.
  • Stardude82
    Very meh at their price points with disappointing idle consumption. Intel is just biding time until AMD's 32 nm process is ready. No reason why they couldn't have a 4 GHz stock chip, load power proves it.

    If you use a E8600 with integrated G45 graphics, I bet you that power consumption will be lower that the 661 (integrated). This GPU-on-package is all just a marketing ploy.

    I really wish you had benchmarks for the low end chips though I doubt IT managers will be running out to replace their fleets of E7500's.
  • liquidsnake718
    same as the p55 but less room for Gpu's.... and newer h55,h57 onboard gpu.... well I guess if you really want to get over all the unneeded jargon and you dont really have a budget just skip this and go X58..... regardless.... even if you have a little extra money to spare and you ARE on a budget, save on the 2nd GPU,monitor, or RAM and get an X58 now!
  • mau1wurf1977
    I think there is a big mistake in the gaming benchmarks...

    Wolfdale is a awesome gaming chip. Its a first to me that the Core 2 Quad is faster in Crysis and all the other games vs. Wolfdale...

    Are you sure it was running at full speed?
  • mau1wurf1977
    I think there is a big mistake in the gaming benchmarks...

    Wolfdale is a awesome gaming chip. Its a first to me that the Core 2 Quad is faster in Crysis and all the other games vs. Wolfdale...

    Are you sure it was running at full speed?
  • mau1wurf1977
    That Yorkfield is 2.66 GHz! No chance in hell it beats the E8500 in gaming...

    I hope this is just a mistake...

    E.g. in Crysis 1920 x 1200 with (breace yourself) 8x AA! No way in hell are these scores correct.

    Did you test the E8500 with a slower video card?
  • HalfHuman
    1100w... why not a 2000w psu or better 5000w. thanks again for making a mockery of the power consumption measurements! i think that the new i5 would do something like 50w idle and below 100w in load if you used the righ psu. i cannot understand why you use these grossly over sized psus are used when doing power measurements.
    above from that i believe the new i5 is doing ok. it would make for a a very nice desktop or httpc. it has the performance and the power consumption. the vid part is not too potent but this was not a goal. the price is a little high. the mobos are a bit on the expensive side. i guess the amd lineup is very good and as somebody suggesed you can undervolt the amd cpus quite a lot. i'm using a antiquated :) x2 4200+. at stock it's 1.1/1.35v (idle/load). i managed to bring it to 0.825/1.15 (idle/load) without much experiments. my point is that you can bring the amd cpus power consumption down quite a lot if you have the knowledge.
  • timbo
    "...Core 2 Quad: sure—it still shows fairly well, and might make a reasonable upgrade..."

    Reasonable? It performs almost identicallly well to the i5 750 in most benchmarks, add in the savings of not having to buy a new mobo & new ram & it is more than a reasonable decision to upgrade the cpu to a core2 quad. The negligible gaming perfomance increase doesn't justify the expenditure to move to lga 1156 with no 6-core upgrade path. 1336 with an eye to six cores maybe.
  • cangelini
    Thought the E8500 numbers were low as well so we re-run a number of the gaming tests to make sure--the scores checked out. I'll rebuild that system right now and double-check.

    Update2: Fixed!
  • HalfHuman
    link to proper power measurements
    the link points to another review that used a proper 400w power supply and did some measurements. 31w/79w (idle load) versus 77w/115w measured by thg. they did use a intel motherboard. guess this is enough of a difference to backup what i said about the 1100w psu. hope you will fix this in the reviews to come.
    other than that i find the thg reviews very useful. keep up the good work!