Quad Core with Hyperthreading versus Quad Core

Back in April we launched our first set of benchmarks relating to which CPU we should choose for gaming.  To that list we now add results from several Intel CPUs, including the vital data point of the quad core i5-4670K, some other Haswell CPUs, the new extreme i7-4960X processor and some vintage Nehalem CPUs we could not get hold of for the first round of results.

Many thanks go to GIGABYTE for the loan of the Haswell+Nehalem CPUs for this update and for use of an X58A-UD9.

The i5-4670K provides a salient data point in our testing – the question is always asked about whether having more cores makes a difference.  Hyperthreading allows the processor to simulate extra cores, though sometimes at the expense of single thread speed of the secondary logical threads.  The i5-4670K also lands on the budget side of the equation if we are talking pricing, currently retailing for $240 compared to the i7-4770K which is at $340.  It is often suggested that the i5 overclockable equivalent should offer similar performance, and our inquisitive minds at AnandTech always want to set the important questions straight in our testing.

This Update

Alongside the i5-4670K, this update also tests an i5-4430, which at the time of testing is Intel’s slowest quad core part from the initial Haswell release.  We are also waiting for the dual core parts to reach our testbeds so we can run our tests.  We are also testing the ultimate high end processor, the newly released i7-4960X, offering six hyperthreaded cores at a 4.0 GHz turbo frequency.  On the back of our Crystalwell testing, the CPU results from the i7-4750HQ are included, and at the request of some of our readers, I was also able to source a pair of Haswell Xeons for testing – the E3-1280 v3 and the E3-1285 v3.  The difference between these two chips is solely the presence of the IGP on the 1285, which causes the official TDP to be raised by two watts.  For users who need neither overclocking nor an IGP, the E3-1280 v3 is a potential choice with a slightly higher clock speed and all the benefits of a Xeon and with a $50 price difference.

Due to the time it takes to test any CPU for this article, it was near on impossible to go through all previous generations of processors from both AMD and Intel, let alone a wide variety to show where clock speeds and cache levels are important.  However for this Intel update, three 1366 CPUs managed to pass my way for a few weeks.  The top selling i7-920 is part of this trio, along with the i7-950 which acted as a slightly more expensive upgrade and the full-fat i7-990X which is the modern equivalent of the i7-4960X in terms of busting a wallet buckle or two.  The first two in that list are quad cores with hyperthreading, whereas the i7-990X sits as a hexa-core.  Clearly Nehalem (and Westmere) suffer an IPC disadvantage when it comes to Sandy, Ivy and Haswell, but it is important to test where such a ‘performance platform’ sits in the grand scheme of things.

WHERE IS THE AMD?!?

Next update!  I currently several AMD CPUs in to test (Richland, Trinity, even a Sempron or two and a Llano) and have requested at least a half dozen more from various sources (Piledriver dual/quad module, Athlon II X4) as well as a CPU or two from AM2/AM2+.  The Intel testing landed in my office first for testing, and it made sense to split them up into two separate articles.  But rest assured, I hope that FX-6xxx, FX-4xxx and A10-6xxx numbers will be on their way soon.  Of course, the FX-9590 and counterpart is also on my list as and when we can get hold of a media sample.

Your Games are Old and do not Consider Multiplayer!

This is not an uncommon criticism with this article and the format it takes.  In order to be honest with my results, I have chosen titles which have ceased to be boosted by regular driver updates.  Due to the level of testing (one CPU can be 20+ hours including setup, CPU tests and GPU tests) we need a stable platform for comparison.  I go into detail on the next page on our testing procedure, but one important aspect for our testing is consistency and repeatability.  Almost no MP scenario can offer this, while at the same time maintain a throughput of testing to at least remain partially relevant.

My next big update for games and drivers will be in 2014, hopefully with a GPU update.  I hope this will entail more thorough testing (minimum FPS + average FPS), along with updates from our 580s to something powerful and PCIe 3.0 on the NVIDIA side.  We are currently looking at Bioshock Infinite/Tomb Raider as possible avenues, and a couple of other titles look interesting. 

Format Of This Article

On the next couple of pages, I will start by going through the reasons for this article.  Many of the reasons are the same as the previous Haswell Update, but for consistency and clarity it makes sense to at least repeat them for new readers coming to read the results.

I will also list in detail our hardware for this review, including CPUs, motherboards, GPUs and memory.  Then we will move to the actual hardware setups, with CPU speeds and memory timings detailed. 

Also important to note are the motherboards being used – for completeness I have tested several CPUs in two different motherboards because of GPU lane allocations.  We are living in an age where PCIe switches and additional chips are used to expand GPU lane layouts, so much so that there are up to 20 different configurations for Z77/Z87 motherboards alone.  Sometimes the lane allocation makes a difference, and it can make a large difference using three or more GPUs (x8/x4/x4 vs. x16/x8/x8 with PLX), even with the added latency sometimes associated with the PCIe switches.  Our testing over time will include the majority of the PCIe lane allocations on modern setups – for our first article we are looking at the major ones we are likely to come across.

The results pages will start with a basic CPU analysis, running through my regular motherboard tests on the CPU.  This should give us a feel for how much power each CPU has in dealing with mathematics and real world tests, both for integer operations (important on Bulldozer/Piledriver/Radeon) and floating point operations (where Intel/NVIDIA seem to perform best).

We will then move to each of our four gaming titles in turn, in our six different GPU configurations.  As mentioned in the next page, in GPU limited scenarios it may seem odd if a sub-$100 CPU is higher than one north of $300, but we hope to explain the tide of results as we go.

This will be an ongoing project here at AnandTech, and over time we can add more CPUs, indepth testing, perhaps even show an extreme four-way setup should that be available to us.  The only danger is that on a driver or game change, it takes another chunk of time to get data!  Any suggestions of course are greatly appreciated – drop me an email at ian@anandtech.com

The Importance of Data
POST A COMMENT

137 Comments

View All Comments

  • Democrab - Friday, October 04, 2013 - link

    It's not really representative of most games, everyone knows it's highly CPU limited...Most games are GPU limited as proven by this, yet a lot of people seem unaware of that. Reply
  • Spoelie - Thursday, October 03, 2013 - link

    Another choice I was considering for gaming: the i5 3350p.

    This is the cheapest i5 available on this side of the pond and still Ivy, so it allows the 4 bin overclocking. Since haswell, intel does not allow any overclocking anymore for non-K parts.

    In addition, Z77 motherboards are quite a bit cheaper than Z87 for the moment.

    So for a 30$+ cheaper than the 4430, you get 3.7/3.6/3.6/3.5ghz Ivy vs 3.2/3.0ghz Haswell.

    The platform isn't that upgradeable but with Intel moving to 2-year cadences for desktop upgrades, the performance should stay relevant for at least 4 years...
    Reply
  • mrdude - Thursday, October 03, 2013 - link

    Amazing article, Ian. Thanks a ton.

    It's shocking to see how well the dual core Intel parts and the two-module AMD chips fare, even at 1440p with a single GPU. With respect to single-GPU gaming, opting to pull some $ out of the CPU/MB fund in order to buy a better GPU is certainly more advisable.

    Those who invested in the X58/1366 platform certainly got their money's worth. Frankly, even buying a secondhand 1366 platform is a good idea if it's cheaper than a new quad-core 1155/1150 + mobo. Going from an SSD running on 3GB/s to 6GB/s really isn't noticeable. I've done this twice on two separate platforms and the only difference I've seen is with respect to bootup speed.

    You also have to figure that this graph will change with the newer generation of console ports. I have an inclining that 2/4 threads might stumble a bit with some more demanding titles. We might even see AVX play a more significant role as well
    Reply
  • cbrownx88 - Thursday, October 03, 2013 - link

    BF4 is gonna bump me from X58 I believe... way more CPU bound than BF3 (1920x1200@4.2ghz) Reply
  • snouter - Wednesday, October 30, 2013 - link

    BF4 makes my 4930k work more than I thought it would. Reply
  • BOMBOVA - Friday, October 04, 2013 - link

    i am reviving my x58 MSI board, with Syba sata 3 controller, and i really notice a difference on my long video editing files. that was my whole point of modding up. Cheers. good discussion Reply
  • chizow - Thursday, October 03, 2013 - link

    I really appreciated what this article tried to accomplish, and I think it does shed some light on some aspects of what you were trying to test...but someone at AnandTech couldn't throw you a bone and get you a pair of higher-end GPUs to test? 580s are a bit long in the tooth to garner any meaningful results. Maybe Gigabyte could have kicked a pair of 680s to you?

    Also, it would have been nice to see some Battlefield 3 results, since it is widely touted as a title that scales extremely well with both CPU (and shows big differences with HT) and GPU, especially in MultiPlayer, and will be especially relevant in the next few months as Battlefield 4 launches.
    Reply
  • dusk007 - Thursday, October 03, 2013 - link

    I find testing for CPU performance is not a strong suit of reviewers. The test has lots of data but it is missing the situations that gamers end up in which do require CPU performance.

    Starcraft 2. Just run a replay of an 8 player map at 4x-8x speed and most dual core notebooks practically break down.
    Total War set unit size to epic and run some huge battle. That is where this games is great but it drains cpu resources like crazy.

    Shooters or racing games are examples where the CPU has to do nothing but feed the GPU which is really the least CPU intensive stuff. Mulitplayer adds quite a bit of overhead but it is still not something if you play you need to worry much about your CPU.
    When testing CPU performance kick all those shooters to the curve and focus on RTS games with huge unit sizes.
    It is the minimum frames at these games that require CPU performance. The situations where it gets annoying that in the biggest battles the CPU cannot keep up. Starcraft 2 on medium runs on almost any GPU but it can bring slower CPU quickly to its limits.
    Reply
  • IanCutress - Thursday, October 03, 2013 - link

    COH2 is planned for our next benchmark update to cover the RTS side. I know Rome II is also a possibility, assuming we can get a good benchmark together. As I mentioned, if possible I'd like to batch file it up so I can work on other things rather than moderate a 5 minute benchmark (x4 for repetitions for a single number, x4-8 for GPU configs to complete a CPU analysis, x25+ CPUs for scope).

    If you have any other suggestions for the 2014 update, please let me know - email address is in the article (or click on my name at the top).
    Ian
    Reply
  • anubis44 - Saturday, October 05, 2013 - link

    "COH2 is planned for our next benchmark update to cover the RTS side."

    Excellent. This is one of my most-played games. In addition, I wouldn't be surprised if subsequent patches for this game didn't noticeably improve it's multi-threaded performance, so having older results will be nice to have once these patches are released in order to track the improvements.
    Reply

Log in

Don't have an account? Sign up now