The Clarkdale Experiment: Mea Culpa

by Loyd Case on 5/4/2010 1:57 PM EST


Back to Article

  • fixxxer0 - Tuesday, May 04, 2010 - link

    the table comparing the two systems calls the lynnfield an i7 750. Reply
  • hyvonen - Tuesday, May 04, 2010 - link

    The colors in most graphs indicating multi-threaded/single-threaded scores are reversed. Reply
  • numberoneoppa - Tuesday, May 04, 2010 - link

    :3 Reply
  • Shadowmaster625 - Tuesday, May 04, 2010 - link

    Why even use a chip that has built-in graphics if you're not using them? That in itself makes it a waste. But the lynnfield is a waste too for gamers. An overclocked E6300 or phenom X2 550 would make much more sense. Reply
  • hyvonen - Tuesday, May 04, 2010 - link

    Similarly, if you're building a HTPC rig, why have an overkill graphics card, especially if the CPU (i5-661) already has an HD-capable IGP in it?

    Those power numbers are superhigh. My i5-670 based HTPC rig idles at 22W, with load around 85W.
  • jordanclock - Tuesday, May 04, 2010 - link

    The article states that the machine would be used mainly for PC Gaming. I think this fits well within the definition of a HTPC, as a video game console could just as easily be considered part of a home theater set up. Reply
  • DanNeely - Tuesday, May 04, 2010 - link

    Because Intel's pushed onchip gfx across its midrange line of CPUs. They don't have a dual core Nehalem chip without integrated GFX. Next year when LGA2011 (sandy bridge) replaces LGA 1366 for high end systems and low end core2 chips are replaced with either lower cost LGA1156 (nehalem) or new LGA1155 (sandy bridge) chips they'll have done so across their entire product line.

    Hopefully by then the GPU switching technology being deployed in a few laptops will have been added to desktop drivers as well for even greater power savings at idle.
  • TonyB - Tuesday, May 04, 2010 - link

    If I were gulding an HTPC, I’d drop down to a lower priced CPU, and a graphics card with less power draw (and costing less.) Reply
  • CSMR - Tuesday, May 04, 2010 - link

    And an HTPC doesn't benefit from a discrete graphics card. Reply
  • Taft12 - Wednesday, May 05, 2010 - link

    Indeed a discrete graphics card is a hindrance to an HTPC in terms of power usage and heat generation. Reply
  • GeorgeH - Tuesday, May 04, 2010 - link

    It’s nice to see you test these systems, but the numbers and analysis you present are completely useless; here are two reasons why:

    From the article: “When we keep the resolution and detil levels low (tessellation is off in the low resolution test), the CPU differences are noticeable. Once we dial up the graphics pain, though, the difference is negligible.” At both resolutions the difference is about 3%; how can 3% be both noticeable and negligible at the same time?

    How repeatable is 195.15 FPS – can you really report 5 significant figures here? From the article: “The numbers vary slightly, but the pattern doesn’t change.” Varying numbers are incredibly important to establishing the relevance of a pattern; for all I know 195.15 is a high outlier and 143.1 is a low outlier. You might be reporting the mean of multiple runs with significant figures appropriate to their standard deviation, but the overall impression of the article is that you ran the benches once and reported whatever number got spit out, with verification that it indeed should have been “bigger” or “smaller” than the number spit out by the other system by running the benchmarks again.

    Combining those two problems, I’m forced to conclude that any numbers and analysis you report here are worthless. That’s unfortunate because they probably aren’t, it’s just the style of the report and failure to indicate more clearly what your testing methodology is that unfairly gives that impression.
  • tno - Tuesday, May 04, 2010 - link

    I agree, completely, and this brings me to the biggest worry I've had over the content on AT for the last year or so. When it was Gary and Anand, there were some hiccups, either with style or content in many of the early articles. But before too long they both got very good at what they do and the result was for a while though throughput wasn't high it was of high quality, consistently. As the staff has grown, however, some of the new blood is really good at analysis and great create models for comparing various pieces of technology but don't write very well. Other staff members, Loyd inclusive, seem to have a great grasp of style and even their analysis sounds good, yet clearly here there are some content errors that lessen the impact of the piece.

    Anand, you have become a master at providing excellent content with impeccable style. Your new writers are all capable, but I think it might be time for a little writing and statistical analysis boot camp.

  • dfonseca - Tuesday, May 04, 2010 - link


    This article by Loyd is a great example of this problem. It is well-worded and pleasant to read, but entirely inconsistent with other AT articles - with the exception of those written by Loyd.

    Articles with this kind of content (hardware configuration benchmarking) abound in AT, and they roughly follow the same pattern with regards to what data is gathered, how it's presented, chart formatting, etc. Reading AT would be a better experience if the articles followed on that formula, or improved on it (with a strong focus on continuity).
  • futrtrubl - Tuesday, May 04, 2010 - link

    Speaking of charts I think he grouped his bars badly. He's comparing systems so he should group by test/setting not by CPU so it's easier to compare.

    Also, he is inconsistent in referring to the chips, sometimes by model number and sometimes by codename. I don't know which is which and while I can look it up I shouldn't have to translate it in my head every time they are mentioned.
  • anactoraaron - Tuesday, May 04, 2010 - link

    But the biggest thing with these numbers is the HDD difference. Having a 250gb SSD vs anything other than another SSD will throw these numbers off... Putting in a SSD for the i5-750 will likely add ~10% more to all numbers across the board for it. I just can't help but think how much better the i5 750 would have been with a SSD. Anand himself no longer does any benchmarking amongst cpu's now without a SSD since it takes away variables a platter HDD may cause.

    I second the boot camp idea.
  • alphacheez - Tuesday, May 04, 2010 - link

    This shows that the i5-750 seems to have more room to grow as demands will increase in the future.

    The 750 should be able to keep up with the next generation of games while the 661 might run out of steam and leave you CPU-bound.

    I think the colors on the Cinebench and video encoding graphs are/were backwards. The higher Cinebench score should correspond with the multi-CPU test and I'd expect the 1080p wmv to h.264 encode to take longer than the avi to mp4 (iPod) encode.

    I'd be interested to hear others experience with Clarkdale-based HTPCs as far as video playback, encoding, power usage, and noise.

    The systems examined in this write-up are pretty high-powered compared to what might be in a typical HTPC. A Radeon 5770 should be enough to power games at 1920x1080 (HDTV) resolutions and really put the kibosh on power usage.
  • jasperjones - Wednesday, May 05, 2010 - link

    agreed, the legend in cinebench seems incorrect. Reply
  • Jaguar36 - Tuesday, May 04, 2010 - link

    Could you check the power usage without the Radeon in the system? Since I leave my PC on 24/7 I really want to know how much power the card uses at idle compared to the IG. Reply
  • justinegg - Tuesday, May 04, 2010 - link

    How much of a difference could PCI-Express and other chipset bottlenecks affected these gaming benchmarks?

    Would the i5 -750's numbers be closer to the 661's if it were in the H55 board?
  • jonup - Tuesday, May 04, 2010 - link

    I am not an expert, but per my discussions with several reviewers H55 performance is similar if not identical to P55.
    As for the performance difference between 750 and 661, it could be due to the memory latencies on top of the L3 size.
  • doron1 - Tuesday, May 04, 2010 - link

    There is a huge disparity between the advertised results in this article's Far Cry 2 and Toms Hardware's ones, in there there is practically no difference between six (!!) different cpu configurations (including some overclocked results) and the gpu used is the same hd5850..

    See for yourself

    Hope you get this cleared up as I'm kinda confused here..
  • FATCamaro - Tuesday, May 04, 2010 - link

    Mistake definitely. He has messed up somewhere, but given his amateurish level it is hard to predict where. Reply
  • nubie - Tuesday, May 04, 2010 - link

    I am quite confused, I thought the difference between a large system and a small system was solely the motherboard, so perhaps benching them with an identical CPU would have made more sense.

    You can get a smaller PC and still use a full size ATX motherboard and graphics card (nearly twice as tall, but also about 1/4 the width)

    In fact the GT3 case comes with the PSU and is only $10 dearer than the case you chose, knocking a lot off your budget. The only concession I see is that you must use a laptop-style optical drive. This is made up with the ability to run dual secondary storage drives, so you could have a small (read inexpensive) SSD for the system and a large standard drive for media/games.

    That system doesn't really nail any desirable system build metric (It should be able to hit one for >$2k). The common saying is size, performance, price, pick 2. This loses on being small (you can build using a case of half the volume with a full ATX Motherboard). Performance wise it is stuck using a different chip with concessions to performance made in the name of integrated graphics (I guess this is technically Intel's fault, they haven't released a performance version of these processors, and I assume you can put the faster chip in the small PC build?). That leaves the cost of the system. Too much. I would budget about $800 for a mini-gaming system, and it would hit nearly the same performance, enough that you wouldn't notice in-game between the two systems.

    This leaves the same taste in my mouth as Tim Allen's ~$60k front-wheel drive Cadillac with 400-hp, lukewarm, but I can appreciate parts of it intellectually.

    (I realize it is supposed to be a "quiet" system, sort of. I think there may be a way to design your own case with a single central fan cooling the PSU/GPU/CPU quite nicely. That may be more my personal interest/taste than the builder of this system.)
  • ClagMaster - Tuesday, May 04, 2010 - link

    Nice experiment that held no surprises for me.

    The i5 750 with four real cores and 8 MB of L3 cache is hard to beat for $190.

    For gaming or media multi-threaded applications the i5 750 is going to beat the i5 661. Four real cores is better than two real cores and two make-believe cores. Memory latency is much better on the i5 750 because of the on-die memory controller. I think this helps performance significantly despite the lower clock frequency. The memory controller on the i5 661 is on the graphics unit which has to operate even if it’s not providing graphics processing. So is the PCIe controller for a discrete graphics card. That’s why the power consumption of the i5 661 at 87W for two cores is relatively higher than the 95W for four cores of the i5 750. Hyperthreading is much "hyped" with gains perhaps 10%.

    The i5 750 or i7 860 is my first choice for a mainstream gaming rig if I were to build one today – hands down. I would build this on a Gigabyte GA-P55A-UD3P Mobo, 8GB of G.SKILL ECO DDR3 1600 (1.35V), a DIAMOND 5850PE51G Radeon HD 5850 1GB graphics card and a couple of Western Digital Caviar Black WD1002FAEX 1TB harddrives.

    For Home theater or Office PC where I need only 2 CPUs, the AMD Athlon II 250 ($60) with a 890G motherboard ($130) is a much better value and adequate performance than a i5 661 ($210) on a H57 motherboard ($120). The 890G provide better graphics. The SB850 provides native SATA 6G with PCIe 2.0 connectivity while the H55/H57 provides SATA 6G with PCIe 1.0 connectivity.
  • ClagMaster - Tuesday, May 04, 2010 - link

    One other thing.

    If Intel really wanted to make me happy with Clarksdale, they should get rid of that worthless GPU and replace the freed real estate with a four-core 32nm processor operating at 3.2 Ghz as an i5 750 replacement. Then the memory controller and PCIe controller would have much less latency and this processor should be able to operate at 65W.
  • Jalek99 - Tuesday, May 04, 2010 - link

    Too many variable in play. Wouldn't the ASUS board support the other processor, making a true test of the different CPU's and not the bus performance of the boards among other things? Reply
  • vol7ron - Tuesday, May 04, 2010 - link

    I like the article and the idea.

    My biggest problem is that the motherboards and HD can play a huuuuge role in benchmarks. You wouldn't think HDs would, since once the data is loaded into memory, you'd think it'd be insignificant, but it isn't.

    Motherboards, on the other hand, are known to have a devastating impact on results. Especially when it comes to accessing RAM. Even at stock timings and settings, motherboard manufacturers have been known to optimize data access paths, to give off a sense of "turbo."

    It's tough to say that neither of the above would be influential in the benchmarks, especially when the CPUs are similar.
  • jonup - Tuesday, May 04, 2010 - link

    Most MBs on the same chipset (H55 and P55 perform very close) perform similarly. There are synthetic mamory variances that usually do not materialize into real world performance.
    Only time MBs on the same chipset perform differently is when the manufacturers decide to OC at default settings. But the reviewer should have made a note if that was the case - it only takes running CPU-Z to notice that the CPU is OCed by 50-60MHz.
  • Jalek99 - Wednesday, May 05, 2010 - link

    But why leave those variables in play? From what you're saying, you could bench an ASUS against a PC-Chips board and expect the same results. Maybe you could, but it seems a minor thing to swap processors to isolate one variable. Reply
  • vol7ron - Wednesday, May 05, 2010 - link

    I've seen the same chipset with almost the same cpu-z settings (speeds, timings, proc) result in very different benchmarks.

    I'm not saying that they are unequal in this particular test, but I am saying that this is a variable that should not be overlooked.

    Bottle necks can be created from almost any mechanism of a pc (eg ram, gpu, hd), even the psu could cause a performance impact due to the variation in power efficiency, though this is often minimal. Small things add up, though.

  • zappb - Wednesday, May 05, 2010 - link


    I've been a regular reader of anandtech for over 10 years. This is the first time I've registered.

    Just to say I enjoyed this review (and the previous Clarkdale experiment) and was perfect for my level. The previous Clarkdale experiment article I printed out and brought it to the bathroom to read in work! Ok I'm sure you didn't want to know that.

    Sometimes you just need to throw in a 256 gigabyte SSD, just because you can!,, I would have done this myself.

    Good job and keep up the good work.

  • mathew7 - Wednesday, May 05, 2010 - link

    You say that the power difference is negligible. But I can tell you it's not. I'm not talking about money savings, I'm talking about noise. Especially in a SFF. I bet you did open-bench testing.

    I have a MicroATX cube with E8400 (soon to be replaced with i5), ASrock G43TwinS, ATI 5850 and Corsair HX450W. The PSU is right above the 5850, with the fan covered by the 2-slot profile of the card.

    I play with desktop speakers as I wear glasses and was unable to find a good headphone set.
    When I played Mass Effect 2 (I don't recall if it was before or after underclocking the 5850), I noticed after 30min of gameplay a noisier than usual computer. But how I noticed it? Because every time there was saving or loading involved (including level change) I would hear an rpm lowering. The rpm was being lowered less than 1s after save/load triggering and would get high again less than 1s after it finished the action. The CPU has the big heatsink that would not permit such fast reaction. The GFX card fan was not, as I would place my finger to stop it from spinning and no noise change was heard. So the only remaining "stressed" component was the PSU (do NOT tell me that I have a too weak PSU, because I have NEVER had a system that would consume more than 350W at the UPS).

    So dismissing the Clarkdale because it's slower and the power difference is not justifiable by savings is not a good reccomandation. If you test SFF components, PUT THEM IN A SFF CASE. The combined effect of restricted airflow and higher power draw could put the PSU in a "crank up the fan" situation. So maybe the 661's power advantage is much better seen(or heard) then 750's performance advantage IN A SFF.

    PS: in the system comparison table you wrote "core i7 750".
  • 7Enigma - Wednesday, May 05, 2010 - link

    Saw your post and wanted to comment (hopefully you see it):

    I, like you, wear glasses and headphones were always an annoyance. But with a kid and another on the way the only time I get to play games is at night when said kid is asleep and a booming sub and loud speakers would not be "allowed". So I did a bunch of searching and came up with the highly recommended Seinheiser HD280. I got mine for $80 on a sale and they frequently go on sale at the major e-taliers. Fantastic sound quality and surprisingly comfortable even after extended gaming/listening to music/movies with glasses.

    Check them out, and I hope this helps a fellow 4-eye. :)
  • Finraziel - Friday, May 07, 2010 - link

    While you have a point, I think you'd be better off improving your airflow or for instance choosing a case where the PSU draws its air from outside, or just get a better PSU, rather than choosing a slower yet more expensive part just in case your PSU fan might get a bit antsy. I think your example mostly serves to not underestimate the impact of choosing the correct PSU if you want a silent system.
    Also, don't overlook that the difference in power draw can not possibly be only or even largely from the CPU difference. There's only an 8 watt difference in TDP and while I know TDP does not equate to how much a CPU actually uses, I think it's fair to say that the 750 itself isn't actually consuming over 60 watts more than the 661. Since P55 mainboards don't draw much power either (I have to admit I have no real numbers, but how else would they be able to survive without bigger heatsinks), the biggest difference I would say has to come from the videocard that is allowed to work harder because the 750 can feed it better. So if it really bothers you on a hot day or something, underclock your CPU and videocard and you should get the same effect.
    On a sidenote, I agree on the sennheiser :). I also wear glasses and also have one of the sennheiser models that go completely over your ear and with a soft cushion... Unfortunately I don't know the model nr and am not at home, but it's survived for about 10 years now already I guess, including dragging it along to quite a few lanparties. I absolutely love it, investing in good comfortable headphones is definately worth it I'd say.
  • basket687 - Wednesday, May 05, 2010 - link

    Please clarify how you measured power consumption, did you run a game, a stress test, or something else?
    The difference in power consumption under load is about 65W and this is really more difference than what I would expect between an i5 750 and an i5 661.
    If you measured it by running a game the result can be biased towards the Clarkdale because it is slower and thus imposes less load on the GPU.
  • mathew7 - Thursday, May 06, 2010 - link

    You have to remember that he's comparing SYSTEM load. The 661has 87W TDP with GFX while 750 has 95W TDP without GFX. Since the integrated GFX is not used, the difference is even higher. Also, since the MBs are different, they also have different power consumptions. Reply
  • zipzoomflyhigh - Wednesday, May 05, 2010 - link

    Why use a cpu with integrated video and a H55 and then drop in a HD5850??

    Makes no sense whatsoever. Your paying a premium for a cpu with built in graphics for what?
  • ClagMaster - Wednesday, May 05, 2010 - link

    The Clarksdale is really meant for HTPC and Office PC applications. Here the on-die GPU will be used.

    However for HTPC or Office PC, I believe you would get much better value and good performance with AMD Athlon X2 and 890G motherboard .

    I agree I would have preferred a dual core processor without the GPU. Power consumption would be better.
  • strikeback03 - Thursday, May 06, 2010 - link

    If the GPU isn't being used it won't consume power. And given that these are the only dual-core 32nm processors around I imagine they are still the most power-efficient ones around (short of Atom/CULV, which are far less powerful). Reply
  • BernardP - Wednesday, May 05, 2010 - link

    Intel could reduce prices to a more competitive level and reach users not interested in its integrated graphics by offering the Clarkdale architecture in a lineup of CPU-only chips.

    Give us a CPU-only version of the i5-680 @ 3.6 GHz with 4,0 GHz Turbo and I will be glad to add my own graphics card to build a nice all-around machine for multimedia and casual gaming.
  • kani - Wednesday, May 05, 2010 - link

    I think Lynnfield wins in some bandwidth intensive games because of the on chip pci-e bridge. The newer Clarksdale units lack this (at least to my knowledge) and so loose. I also recall this sort of advantage when the i5 750 came out and was tested vs the older i7 models. Some games like this extra bandwidth, others do not. Reply
  • 7Enigma - Wednesday, May 05, 2010 - link

    I'll be honest. I read this just like any other review (rarely do I look at the author unless I'm going to post a response), and was left shocked at the poor quality.

    I'm not a grammar/spelling/etc. police so I could care less if punctuation is not perfect (probably my post is riddled with errors, sue me). I also don't particularly mind flipping back to previous pages because the descriptions of products are constantly being changed from one sentence to the next (but this is somewhat annoying). I'm also a pretty data oriented person so bland writing doesn't turn me off either. Let's say I'm pretty easy to please.

    It's been beaten to death; we all know that in most modern games everything is GPU limited within reason (celeron to i7 is not within reason). Yes FarCry2 is the exception to the rule and it will be important to see if this trend becomes more common in the future, but for the most part the same article has been hashed out for the last 5 years (probably longer).

    There is virtually nothing beneficial that can be gleaned from the tests run. By having so many variables from the HD, to the mobo, to the CPU, any data generated has no way of being understood. So for the 0.01% of people that have these 2 identical systems in their house congratulations, they can use this article to decide which to game on....
  • hob196 - Thursday, May 06, 2010 - link

    Why do you use 'Lynnfield' and 'Clarkdale' in the article and 'i5' and 'i7' in the graphs, this is really confusing to the casual observer who doesn't know their chip code-names off by heart. Reply
  • ReaM - Tuesday, May 11, 2010 - link

    If you want to keep one of these systems until 2012, then i5 Dual Core will be a waste of money.

    When games will finally use all 4 cores - and most of the upcoming games certainly will, you people will regret buying a Dual Core.

    Clarkdale is a no no no.
  • xrror - Tuesday, June 01, 2010 - link

    In the last paragraph: "If I were gulding an HTPC, I’d drop down to a lower priced CPU,"

    Although I must admit, "gilding" would be WAY more entertaining =D

Log in

Don't have an account? Sign up now