Sign in with
Sign up | Sign in

Benchmark Results: PCMark 7

Core i5-3570K, -3550, -3550S, And -3570T: Ivy Bridge Efficiency
By

It turns out that PCMark yields some of the most interesting results—and not necessarily in a good way.

If you flip back to the twelfth page of Intel Core i7-3770K Review: A Small Step Up For Ivy Bridge, you’ll notice that the Core i7-3770K scores here are higher than in that story. Moreover, the Core i5-3570K blows away the Core i7-2700K in this story and the launch coverage as well. What. The. Heck. Right? We were using a flippin’ GeForce GTX 680 for the launch, and basic HD Graphics 4000 here. You mean to tell me that, according to PCMark, the system with integrated graphics is better?

Let’s step through the sub-tests for more detail. We did some digging on this and have answers.

Alright. Productivity comes first, including Storage, Web browsing/decrypting, and Text editing components. Sandy Bridge winds up behind four different Ivy Bridge-based setups, three of which are Core i5s, and two of which employ HD Graphics 2500. It’s frankly difficult to imagine that this would reflect real-world performance, and we’ll keep these numbers in mind as we start firing up our own workloads.

Here’s where things start to get really wonky (though the oddest results are yet to come). Although the Creativity suite includes Storage, Image manipulation, and Video transcoding workloads, there’s a clear step down from HD Graphics 4000-, 3000-, and 2500-equipped CPUs.

Naturally, our first question was to Futuremark: is PCMark benefiting from Quick Sync? The company’s response: yes, using Microsoft’s Media Foundation transforms, hardware acceleration is utilized. Futuremark does not make public the weightings for each piece of the test, but it seems unlikely that one Quick Sync-enabled Ivy Bridge chip with HD Graphics 2500 should score less than half of a Quick Sync-enabled Ivy Bridge chip with HD Graphics 4000, particularly when transcoding is only one of three variables.

The Entertainment test is broader; it includes Video playback, Storage, Graphics, and Web browsing. All of these integrated graphics engines support DirectX 10, at least, so none of the tests are getting dropped. And yet, there’s still a huge gap between the top and bottom, clearly segmented by HD Graphics 4000, 3000, and 2500. We’ll simply have to accept that Graphics (gaming) and Video playback are the biggest determinants of performance in this one.

Futuremark uses three pieces for its Computation suite: Video transcoding (downscaling), Video transcoding (high-quality), and Image manipulation. Not only does the test consequently suggest that the HD Graphics 4000-equipped processors are more than five times faster than the ones with HD Graphics 2500, but, again flipping back to Intel Core i7-3770K Review: A Small Step Up For Ivy Bridge, the benchmark puts a Core i5 almost four times above a Core i7-3960X-based machine with a GeForce GTX 680.

Bottom line: because PCMark is a black box, there’s no way to see how heavily Futuremark weighs video transcoding in its sub-tests. But judging by the disparity between Sandy Bridge and Ivy Bridge, the importance placed on Quick Sync is way too high. Will this benchmark show up again in the future? Probably, but more selectively, now that we know any fixed-function transcode acceleration can throw off its results so blatantly.

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 75 comments.
This thread is closed for comments
Top Comments
  • 19 Hide
    jimmysmitty , May 22, 2012 6:15 AM
    Outlander_04The performance of a Llano chip is included in the article to compare its performance so it not just about intel cpu's . The intels were not as good in gaming in the integrated graphics so a graphics card was added so they'd look better there too . Its an unfair comparison and shows intel bias IMO


    Actually a lot of sites have shown just what Chris is talking about. Even a dual core Pentium with a HD6670 beats the top end Llano piece (a quad core) even with CFX of the IGP with a HD6570. Llano is great for some things but overall in DT its only a low end entry level product and is much weaker per core and per clock than Intels CPUs.

    What Chris did was pulled the same charts from his first IB review and added in the HD2500 (the new low end Intel IGP) for comparison.

    If someone cannot take this information and realize that its just for comparison and that its not to show anything better, then thats their problem. If this was a Llano article, or the Trinity article when it comes out, you better believe Chris will do everything to check ever performance aspect. But its not. Its an article to see if the T and S models are worth it.

    Overll, llano is overrate in my book. We have barley sold any at my work place. Just doesn't have the pulling power like a CPU and discrete GPU does.
  • 18 Hide
    cangelini , May 22, 2012 5:24 AM
    Outlander_04In the real world gaming section you got a great big graph for the 3770k by adding a discreet graphics card . Why didn't you try a Llano system with an identical graphics card? Afraid the second tier AMD product would kick sand in intels face?

    Because this is a story about the Intel chips. To the contrary, though, the AMD-based platform is more likely to bottleneck a discrete graphics card than the Intel one. AMD's strength is in the integrated graphics right now.
  • 17 Hide
    zyzz , May 22, 2012 4:25 AM
    Good article. I think I will get the 3570K over 2500K.
Other Comments
  • 17 Hide
    zyzz , May 22, 2012 4:25 AM
    Good article. I think I will get the 3570K over 2500K.
  • 6 Hide
    erraticfocus , May 22, 2012 4:34 AM
    nice work in sorting out the facts and reminding us about the history and change from the lower power offerings in the intel stable..

  • 7 Hide
    amdfangirl , May 22, 2012 4:42 AM
    Does Intel allow underclocking and undervolting on H-series boards? If so, S and T series are pretty redundant.
  • 18 Hide
    cangelini , May 22, 2012 5:24 AM
    Outlander_04In the real world gaming section you got a great big graph for the 3770k by adding a discreet graphics card . Why didn't you try a Llano system with an identical graphics card? Afraid the second tier AMD product would kick sand in intels face?

    Because this is a story about the Intel chips. To the contrary, though, the AMD-based platform is more likely to bottleneck a discrete graphics card than the Intel one. AMD's strength is in the integrated graphics right now.
  • 19 Hide
    jimmysmitty , May 22, 2012 6:15 AM
    Outlander_04The performance of a Llano chip is included in the article to compare its performance so it not just about intel cpu's . The intels were not as good in gaming in the integrated graphics so a graphics card was added so they'd look better there too . Its an unfair comparison and shows intel bias IMO


    Actually a lot of sites have shown just what Chris is talking about. Even a dual core Pentium with a HD6670 beats the top end Llano piece (a quad core) even with CFX of the IGP with a HD6570. Llano is great for some things but overall in DT its only a low end entry level product and is much weaker per core and per clock than Intels CPUs.

    What Chris did was pulled the same charts from his first IB review and added in the HD2500 (the new low end Intel IGP) for comparison.

    If someone cannot take this information and realize that its just for comparison and that its not to show anything better, then thats their problem. If this was a Llano article, or the Trinity article when it comes out, you better believe Chris will do everything to check ever performance aspect. But its not. Its an article to see if the T and S models are worth it.

    Overll, llano is overrate in my book. We have barley sold any at my work place. Just doesn't have the pulling power like a CPU and discrete GPU does.
  • 12 Hide
    GhosT94 , May 22, 2012 6:32 AM
    should have compared the Core i5-3570K vs the Core i5-2500K
  • 6 Hide
    ojas , May 22, 2012 6:53 AM
    I was wondering, would you be able to test a Llano in a dual GPU config vs the -T model i5 with the same card, and with another efficient higher end card like 7870 or 670 (with the i5 as the CPU)?

    I'm thinking in terms of a HTPC/"Super-Console". Low power, high gaming+A/V performance, quiet, 'instant'-on.

    If you guys get the time to, of course. :) 
  • 4 Hide
    silverblue , May 22, 2012 7:26 AM
    Outlander_04If you are going to show the performance of an intel cpu with a graphics card then any reasonable comparison would also show the AMD cpu with the same graphics card .

    I must admit, with a low to mid end card, Llano wouldn't really cause any bottlenecking issues, however it wouldn't be reasonable to expect Llano to perform the same or better than SB or IB i3s and i5s using the same card for most games. SB and IV are just faster even if Llano had a higher clock, period.
  • 5 Hide
    Yargnit , May 22, 2012 7:30 AM
    If the goal of the low power models is HTPC's and the like they should really have given them HD4000 instead of just HD2500 so they would be less likely to need a discrete GPU that negates the power saving benefits of a low power SKU.

    In instances where he HD4000 has enough GPU power, but the HD2500 does not, the 3570k will offer a lower total system power option than either of the t/s options once you factor in adding a GPU that meets your needs.

    If you jut bought a 3570k and undervoled it, which IB seems very good at, the results wouldn't even be close.
  • -2 Hide
    xtreme5 , May 22, 2012 8:13 AM
    i5 3570k ulitmate gaming chip.
  • -1 Hide
    K-beam , May 22, 2012 10:17 AM
    Those processors may be the only ones that you could get into your min-ITS board. For example, Foxconn H61S mini-ITX will only accept
  • 2 Hide
    K-beam , May 22, 2012 10:22 AM
    Sorry, the post got cut.
    Those processors may be the only ones that you could get into your mini-ITX board. For example, Foxconn H61S mini-ITX will only accept less than 65W CPUs http://www.cpu-upgrade.com/mb-Foxconn/H61S.html
    However, seeing that the 77W CPUs top power draw is practically the same as 3550S, I wonder whether they will not fit in those mini-ITX boards.
  • 3 Hide
    mavikt , May 22, 2012 10:52 AM
    Chris AngeliniI also have data for the -2550K, but I’m working on a surprise with that information.


    That was a teaser from the original Intel Core i7-3770K Review: A Small Step Up For Ivy Bridge.
    What happened? Was this it?
    I'm still very curious!
  • 2 Hide
    Sakkura , May 22, 2012 12:09 PM
    Why does TH focus on the i7-3770k and the -S and -T i5's, rather than the i5-3570k, i5-3570, i5-3550 etc. that appeal more to gamers?
  • 2 Hide
    Sonny73N , May 22, 2012 12:13 PM
    If I build a new rig today, I'd still go with SB. Simply because Intel had replaced the fluxless solder with some kind of thermal paste inside these 3rd gen chips. No wonder IB has heat issue despite their lower TDP compared to SB.

    Thermal paste is only usefull when used to fill in air gaps between heat conductive materials so it can disipate more heat than air can. But replace metal with the paste? Look like someone tried to make more profit here by cutting down production cost. Next Bridge, please!
  • 0 Hide
    suddenstop , May 22, 2012 12:13 PM
    I think this article has some flaws, especially due to pcmark. It would have been better to add the same chips with a discrete graphics card to the test. Sandy and Ivy are a lot different on graphics, but not so much so otherwise. We already know hd graphics in the new chips is better.

    What I want to know, is take the i5 k series chips. Ivy starts out more efficient, but as you overclock them, due to voltage jumps on ivy - does sandy become more efficient at some point.
Display more comments