Choosing a Gaming CPU October 2013: i7-4960X, i5-4670K, Nehalem and Intel Update
by Ian Cutress on October 3, 2013 10:05 AM EST
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.
Facebook
Twitter
RSS
137 Comments
View All Comments
BOMBOVA - Sunday, October 6, 2013 - link
a low cost raid controller yes, 64kb, 128kb, show the merit of raid 0, at 6 Gbs each, i was doubtful myself, but took the test of the device, for i need better video editing performance, at least it works :) now we have to watch out for the 12Gbs devices coming soon, imo for games, not much notice of improvement to be seen, but in big data transfers, sata 3 improvements, can be had for low costs. gl, trying it out, borrow a card to try, if you can, Cheers.BOMBOVA - Saturday, October 26, 2013 - link
fact is you can set to 32 K blocks, or 64K, 'only" , but is a true Marvel controller chip, in the Syba, and is on the PCI e buss. , Control M, sets the chipset, works rite off, is quick, but, there is a hint, that the lanes are only 5 Gbit second, still is a fine patch upgrade, on low cost 6Gbit second ssd's i am in for 2x120 ssd's and controller for 250,R-Type - Friday, October 4, 2013 - link
Results are typical for a variety of games where the resolution is set to 1920 x 1200. Games include Dirt 3, Civilization V, Guild Wars 2, Mechwarrior Living Legends, Diablo 3, Starcraft 2, etc.augiem - Friday, October 4, 2013 - link
I'm really kind of shocked to see how well Nehalem stands up still in many benchmarks. If you adjust the i7 920 benchmarks to make up for the difference in frequency between it and the 4770K, it's not half bad. I used the difference between the i7-920 and i7-950 to determine how the benchmark scaled on Nehalem. If it was close enough to linearly (+/- 1%), I considered it. I saw a 6% - 40% performance advantage for Haswell across the CPU tests, which is actually smaller than I expected for an almost 6 year old chip. (Obviously this includes differences in the platforms too.) Striking that even in 6 years the speed hasn't even doubled.I'm still on an i7-920@3.6, so this was very relevant to me. If it were 40% across the board, it might be more compelling, but quite a few were more like 15%, 20%, etc. Now I understand Haswell is going to OC a lot further than this one, so in that way you could get the performance diff up there.
I'm just dumbfounded that this Nehalem has lasted me 4.5 years already and it still doesn't feel slow. On the one hand its great value for the money, but on the other hand its a little disappointing to see performance curve drop off like it has over the past 6 years.
That would be a fun project. Make a graph showing average CPU performance increases over the last 30 years.
Genericuser1234 - Saturday, October 5, 2013 - link
As interesting these chips are for getting maximum performance from the high w parts. Will you do an article about the low TDP parts that are the true masterpieces Intel makes. I live in Denmark and energy cost more and more. My PC is running almost nonstop and I am curious how well these chips perform in a gaming environment. How far behind are they on performance and what kind of power cost on a year based on an average workload / idle time are we talking about you could save. I find the low power chips to be Intel's true stars. Do more with less. Maybe even throw in a power house chip from 2 years ago for comparison. That would be an interesting articleagent_x007 - Saturday, October 5, 2013 - link
Congrats to those who did testing part.Can't wait to see AMD added.
Too bad Pentium XE 955/965 (ie. Presler B1/C1 @ 3,46/3,73GHz) didn't "cut it" for this comparson :(
Hyper Threading and "Last of Netburst" legacy could be interesting in comparison with low end, fully-intergated setups, like VIA Nano or AMD Fusion.
+ There is also a possibility that todays multithreaded programs would better utilize the 4 threads of this kind of CPU, maybe to the point of matching Core 2 Duo's...
Either way, to sum it up in two words : GREAT WORK.
khanov - Saturday, October 5, 2013 - link
A good article, and nice to see an update now that new CPU's are out.Wouldn't it be nice if you could have all the benefits of X79 for multi GPU configurations, but without the added cost over Z87? Well actually you can, if you take in to account the quad-core LGA2011 CPUs.
The i7-4820K is no more expensive than the i7-4770K, and motherboard costs are very similar too. So people seriously considering 3 or 4 GPUs might be very interested in this option, to gain the benefits of extra PCIe lane allocation without the extra cost of a hex core CPU.
Ian, would you please consider adding i7-3820 and/or i7-4820K to the next update? It would be nice to see how well, or how badly, they fare against the competition.
MarcHFR - Sunday, October 6, 2013 - link
Hi all,Sorry but i don't understand this review. What's the point of recommanding different CPU on the only basis of single/dual/tri/quad GPU ?
First, the GPU power is not related to the number of GPU only, with 2x660 you get lower performance than 1x780, but if i read the conclusion for 2x660 you recommand FX-8350 but A8-5600K for 1x780 ?
Second, for example with only a 7970 with a small CPU or a big CPU you get exactly the same performance on Sleeping Dogs 2560*1440 max settings. But what kind of player will keep a setting that offer 28 fps on such a carde ? None ! They will lower the graphic settings related to the GPU only to a point that they will get a higher framerate, like the 80 fps you get with three card.
Whatever the number/power of the GPU, as soon as it's not a lower-end card, the CPU needed to get playable framerate is the same with a GTX 660 or 2xGTX 780 as soon as you don't use graphics settings related to the GPU that lower the framerate that can be sustained by the GPU under the framerate that can be sustained by the CPU.
You can recommand different CPU to get more than 40/60/80/120 fps in some games (but good luck since integrated benchmark are generally not using the most CPU bound scene), but recommand different CPU for single/dual/tri/quad GPU seems a non-sense for me.
Majesticii - Sunday, October 6, 2013 - link
Damn. How can you call this a CPU comparisson with data like this. The games are run at such extreme values that in no way they represent the impact of a CPU. Sleeping dogs is just 4 graphs with 28fps, how can any respected researcher show this data without severe shame. To add insult to injury, the vast majority seems to think this is how CPU tests are done and call it a nice review. Literally my heart sank as i read through these comments. Noone (except a few ignored), not even the reviewers has a clue what they're on about. This way of CPU-reviewing in games needs to stop. This isn't just uninformative, it's worse; It's completely misleading. Test games at 800x600 low settings, and pay no mind to those people calling for "real-world benchmarks". Stay true to what's real, instead of appealing to the community.3Ball - Monday, October 7, 2013 - link
Forgive me if this is pointed out in the article and I have missed it, but it is worth pointing out. Battlefield 4 will use up to 8 cores/threads. My i7-860 @ 4.0ghz with hyperthreading is outperforming a friends Ivy bridge (3570k) at 4.4ghz without hyperthreading, so much so that my frames are better using a GTX680 against his GTX780.This could be the product of the "beta", but I do believe it is a sign of things to come. The new consoles are most likely going to influence multithreaded performance greatly considering the lower sinlge thread performance present in the systems.
I have been planning on rebuilding with haswell early next year and was planning on getting a 4670k, but have now changed that decision to going with a 4770k due to this experience. Just my two cents. Cheers!