The i7-7700K, launched today, is Intel's fastest ever consumer grade processor. Using Intel’s third set of processors at 14nm, using the new 14+ variant, we get processors with a better frequency / voltage curve that translates into more performance, better efficiency, and the potential to push the silicon further and harder. Here is our review. 

Meet Kaby Lake, and 4.5 GHz Out-of-the-Box

The i7-7700K is part of Intel's 7th Generation of Core CPUs, which often goes by its internal code name 'Kaby Lake'. The Kaby Lake family, as of today's launch, stretches from 91W on the mainstream desktop down to 4.5W for notebook processors, all using the same underlying technology in different core and integrated graphics configurations. The i7-7700K is the top part of this processor family, featuring four cores with hyperthreading, a 4.2 GHz base frequency, a 4.5 GHz turbo frequency, a couple of new tricks and all for $303 list (so about $330 retail). 

 

As a processor with the letter K in it, in Intel's lingo this means the i7-7700K is an unlocked processor. Users with enough nous to understand the relationship between frequency, voltage, temperature and stability can take this processor above (or below) its standard operating frequency to get more performance without spending more money. The upshot of pushing the processor in this way is usually a higher power consumption, something that PC enthusiasts usually have to spare, and in the wrong hands a broken CPU through overclocking is worth the same as sand. There are two other K processors in the Kaby Lake family, the i5-7600K and the i3-7350K, which both have separate reviews as part of our launch coverage. 

Intel Kaby Lake S SKUs
	Cores/ Threads	Base/ Turbo	IGP	L3	eDRAM	TDP	Cost
i7-7700K	4/8	4.2/4.5	HD 630	8 MB	-	91 W	$305
i7-7700	4/8	3.6/4.2	HD 630	8 MB	-	65 W	$272
i7-7700T	4/8	2.9/3.8	HD 630	8 MB	-	35 W	$272
i5-7600K	4/4	3.8/4.2	HD 630	6 MB	-	91 W	$217
i5-7600	4/4	3.5/4.1	HD 630	6 MB	-	65 W	$199
i5-7600T	4/4	2.8/3.7	HD 630	6 MB	-	35 W	$199
i5-7500	4/4	3.4/3.8	HD 630	6 MB	-	65 W	$179
i5-7500T	4/4	2.7/3.3	HD 630	6 MB	-	35 W	$179
i5-7400	4/4	3.0/3.5	HD 630	6 MB	-	65 W	$170
i5-7400T	4/4	2.4/3.0	HD 630	6 MB	-	35 W	$170
i3-7350K	2/4	4.2	HD 630	4 MB	-	60 W	$157
i3-7320	2/4	4.1	HD 630	4 MB	-	51 W	$139
i3-7300	2/4	4.0	HD 630	4 MB	-	51 W	$129
i3-7300T	2/4	3.5	HD 630	4 MB	-	35 W	$129
i3-7100	2/4	3.9	HD 630	3 MB	-	51 W	$109
i3-7100T	2/4	3.4	HD 630	3 MB	-	35 W	$109

Intel calls the desktop like of processors the S series, and Kaby Lake-S (or KBL-S) ranges from a dual core low power 35W i3-7100T to the high-end 91W i7-7700K. The idea here is to offer many different parts at different price points to cater for customer needs, such as performance, power, cost and feature set. With every launch Intel tries to entice users to upgrade from their older system (citing hundreds of millions of daily PCs being 3+ years old), and so having new features is key to having better performance too. 

With the high-end i7-7700K, being the top processor, the main draw is typically performance and overclockability. This review aims to take us through both of these, and the reasons why. 

 
Intel Core i7-7700K (Kaby Lake) and Core i7-6700K (Skylake)

Comparing it to the previous generation high-end i7-6700K Skylake processor, we get the same configuration of cache hierarchy. The main difference between the two will be support for DDR4-2400 on the Kaby Lake rather than DDR4-2133, updated integrated graphics, a new generation of Speed Shift, AVX Offset support, and support for Intel’s ‘Optane Memory’.

Typically with each new generation of Intel CPUs brings about a fundamental increase in performance through the rate of instructions per cycle/clock (IPC) that the processor can go through. That being said, Intel has stated (and we've confirmed through testing) that Skylake and Kaby Lake are identical for IPC. As a result, the i7-7700K attempts to take the performance crown through frequency alone. The i7-6700K runs as 4.0 GHz base and 4.2 GHz turbo, while the i7-7700K runs at 4.2 GHz base and 4.5 GHz turbo. We quantify what this means in this review.

Speed Shift v2

For the i7-6700K family, Skylake, Intel introduced Speed Shift (v1). This was a feature that, at a high level, gave control of the voltage/frequency curve from the operating system to the processor. Using a series of internal metrics, such as instruction analysis and frequency, the CPU would automatically adjust the voltage and frequency of the processor as required. This afforded two major benefits: one, with the CPU in control it has access to many more points on the curve compared to the OS which is limited to specific P-states on the processor.

The second benefit is the speed of transition. A processor that can ramp up to a high frequency quickly and then drop down as needed can get through instructions quicker but also save power. Imagine driving a car, and having to wait 60 seconds to change a gear – it’s that sort of analogy.

What Speed Shift v2 does in the i7-7700K and the Kaby Lake family, compared to v1 in Skylake, is manage those transitions to higher frequency faster. Before Speed Shift, transitions from idle to peak turbo were on the order of 100 milliseconds, and Speed Shift v1 took that to 30 milliseconds (with a good base established within 15). Speed Shift v2 means that peak performance from idle now happens in 10-15 milliseconds total. This means that interactions with the OS, such as touch, or actions that rely on low latency, can occur within a couple of frames on a 60 Hz display.

The benefit of Speed Shift lies a lot in touch devices, which perhaps doesn’t affect the i7-7700K in this review, but also in web interactions. A lot of web work is stop and start, such as scrolling or javascript functions.

There is one caveat however – Speed Shift currently only works in Windows 10. It requires a driver which is automatically in the OS (v2 doesn’t need a new driver, it’s more a hardware update), but this limitation does mean that Linux and macOS do not benefit from it. I would be hard pressed to not imagine that Apple and Intel were not working on a macOS driver, but as yet we have not had confirmation that one exists.

Optane Memory Support

The latest memory technology to hit prime time is Intel and Micron’s 3D XPoint. This is a non-volatile form of data storage that is bit addressable and can be used as DRAM or storage. Despite being at least a decade in the making, and being formally announced in 2014, it is still yet to show up commercially as it is still being developed. Intel plans to create 3D XPoint DRAM that is slightly slower than normal DRAM but both denser (more of it) and non-volatile (keeps the data after power loss, saves power altogether), as well as 3D XPoint Storage that is faster than standard NAND flash, and more configurable. It the scheme of things, we expect the storage based products to hit the market first.

Intel, as far as we can tell, is set to release two main classes of product: Optane DRAM to be pin-compatible with DDR4 and require Optane DRAM enabled processors, and Optane SSDs which should work with any PCIe storage interface. ‘Optane Memory’ however, is something a little different. Based on pre-briefings, Optane Memory is certainly not Optane SSD we were told, but rather a storage cache for mechanical hard-drives. We’ve had this before with NAND flash drives, using Intel’s Rapid Storage Technology, and it seems that Kaby Lake and 200-series chipsets will support a new version of RST for PCIe-based storage. But because this is caching drive, such as the 16GB Optane Memory drives in Lenovo’s upcoming notebooks, and not Optane SSD, might lead us to believe that ‘Optane Memory’ drives are not designed to be directly user addressable.

All that being said, Intel has stated that Optane Memory standalone drives should hit the market nearer Q3 for general consumer use, which is more in-line with what we might expect to see with Optane SSDs in the enterprise space.

More about Kaby Lake

For readers that want a more in-depth take on Kaby Lake as a platform, we have a dedicated article full of information for you. We also have other articles in our Kaby Lake bonanza for launch day. 

Other articles include:

Intel Launches 7^th Generation Kaby Lake (Overview and Core Improvements)
The Intel Core i7-7700K Review: The New Out-of-the-box Performance Champion
The Intel Core i5-7600K Review: The More Amenable Mainstream Performer
The Intel Core i3-7350K Review: When a Core i3 Nearly Matches the Core i7-2600K

Upcoming (we’re at CES and didn’t have time to finish these yet):

Calculating Generational IPC Changes from Sandy Bridge to Kaby Lake
Intel Core i7-7700K, i5-7600K and i3-7350K Overclocking: Hitting 5.0 GHz on AIR
Intel Launches 200-Series Chipset Breakdown: Z270, H270, B250, Q250, C232
Intel Z270 Motherboard Preview: A Quick Look at 80+ Motherboards

Test Bed and Setup

As with every CPU launch, there are a number of different directions to take the review. We have dedicated articles comparing the IPC of the new Kaby Lake line of CPUs, as well as a look into overclocking performance as a whole. We have had almost every desktop-class CPU family since Sandy Bridge tested in our benchmark suite, although only the latest have been retested. Due to timing, we were able to test all three of the new Kaby Lake-K processors, and retest the several Skylake processors, however we do have some CPU data for comparison for Haswell, Ivy Bridge, and Sandy Bridge. It will interesting to see how the CPU performance out-of-the box has adjusted over the last five generations.

As per our testing policy, we take each CPU and place it in a suitable high-end motherboard and equip the system with a suitable amount of memory running at the processor maximum supported frequency. This is also typically run at JEDEC subtimings where possible. It is noted that some users are not keen on this policy, stating that sometimes the maximum supported frequency is quite low, or faster memory is available at a similar price, or that the JEDEC speeds can be prohibitive for performance. While these comments make sense, ultimately very few users apply memory profiles (either XMP or other) as they require interaction with the BIOS, and most users will fall back on JEDEC supported speeds - this includes home users as well as industry who might want to shave off a cent or two from the cost or stay within the margins set by the manufacturer. Where possible, we will extend out testing to include faster memory modules either at the same time as the review or a later date.

Test Setup
Processor	Intel Core i7-7700K (Retail Stepping), 91W, $303 4 Cores, 8 Threads, 4.2 GHz (4.5 GHz Turbo)
Motherboards	ASRock Z270 Extreme4 MSI Z270 Gaming M7
Cooling	Cooler Master Nepton 140XL
Power Supply	OCZ 1250W Gold ZX Series Corsair AX1200i Platinum PSU
Memory	Corsair DDR4-2400 C15 2x8 GB 1.2V or G.Skill Ripjaws 4 DDR4-2400 C15 2x8 GB 1.2V
Memory Settings	JEDEC @ 2400
Video Cards	ASUS GTX 980 Strix 4GB MSI R9 290X Gaming 8GB MSI GTX 770 Lightning 2GB (1150/1202 Boost) MSI R9 285 Gaming 2G ASUS R7 240 2GB
Hard Drive	Crucial MX200 1TB
Optical Drive	LG GH22NS50
Case	Open Test Bed
Operating System	Windows 7 64-bit SP1

Readers of our reviews will have noted the trend in modern motherboards to implement a form of MultiCore Enhancement / Acceleration / Turbo (read our report here) on their motherboards. This does several things, including better benchmark results at stock settings (not entirely needed if overclocking is an end-user goal) at the expense of heat and temperature. It also gives an essence an automatic overclock which may be against what the user wants. Our testing methodology is ‘out-of-the-box’, with the latest public BIOS installed and XMP enabled, and thus subject to the whims of this feature. It is ultimately up to the motherboard manufacturer to take this risk – and manufacturers taking risks in the setup is something they do on every product (think C-state settings, USB priority, DPC Latency / monitoring priority, overriding memory sub-timings at JEDEC). Processor speed change is part of that risk, and ultimately if no overclocking is planned, some motherboards will affect how fast that shiny new processor goes and can be an important factor in the system build.

Many thanks to...

We must thank the following companies for kindly providing hardware for our multiple test beds. Some of this hardware is not in this test bed specifically, but is used in other testing.

Thank you to AMD for providing us with the R9 290X 4GB GPUs. These are MSI branded 'Gaming' models, featuring MSI's Twin Frozr IV dual-fan cooler design and military class components. Bundled with the cards is MSI Afterburner for additional overclocking, as well as MSI's Gaming App for easy frequency tuning.

The R9 290X is a second generation GCN card from AMD, under the Hawaii XT codename, and uses their largest Sea Islands GPU die at 6.2 billion transistors at 438mm2 built at TSMC using a 28nm process. For the R9 290X, that means 2816 streaming processors with 64 ROPs using a 512-bit memory bus to GDDR5 (4GB in this case). The official power rating for the R9 290X is 250W.

The MSI R9 290X Gaming 4G runs the core at 1000 MHz to 1040 MHz depending on what mode it is in (Silent, Gaming or OC), and the memory at 5 GHz. Displays supported include one DisplayPort, one HDMI 1.4a, and two dual-link DVI-D connectors.

Further Reading: AnandTech's AMD R9 290X Review

Thank you to ASUS for providing us with GTX 980 Strix GPUs. At the time of release, the STRIX brand from ASUS was aimed at silent running, or to use the marketing term: '0dB Silent Gaming'. This enables the card to disable the fans when the GPU is dealing with low loads well within temperature specifications. These cards equip the GTX 980 silicon with ASUS' Direct CU II cooler and 10-phase digital VRMs, aimed at high-efficiency conversion. Along with the card, ASUS bundles GPU Tweak software for overclocking and streaming assistance.

The GTX 980 uses NVIDIA's GM204 silicon die, built upon their Maxwell architecture. This die is 5.2 billion transistors for a die size of 298 mm², built on TMSC's 28nm process. A GTX 980 uses the full GM204 core, with 2048 CUDA Cores and 64 ROPs with a 256-bit memory bus to GDDR5. The official power rating for the GTX 980 is 165W.

The ASUS GTX 980 Strix 4GB (or the full name of STRIX-GTX980-DC2OC-4GD5) runs a reasonable overclock over a reference GTX 980 card, with frequencies in the range of 1178-1279 MHz. The memory runs at stock, in this case 7010 MHz. Video outputs include three DisplayPort connectors, one HDMI 2.0 connector and a DVI-I.

Further Reading: AnandTech's NVIDIA GTX 980 Review

Thank you to Cooler Master for providing us with Nepton 140XL CLCs. The Nepton 140XL is Cooler Master's largest 'single' space radiator liquid cooler, and combines with dual 140mm 'JetFlo' fans designed for high performance, from 0.7-3.5mm H2O static pressure. The pump is also designed to be faster, more efficient, and uses thicker pipes to assist cooling with a rated pump noise below 25 dBA. The Nepton 140XL comes with mounting support for all major sockets, as far back as FM1, AM2 and 775.

Further Reading: AnandTech's Cooler Master Nepton 140XL Review

Thank you to Corsair for providing us with an AX1200i PSU. The AX1200i was the first power supply to offer digital control and management via Corsair's Link system, but under the hood it commands a 1200W rating at 50C with 80 PLUS Platinum certification. This allows for a minimum 89-92% efficiency at 115V and 90-94% at 230V. The AX1200i is completely modular, running the larger 200mm design, with a dual ball bearing 140mm fan to assist high-performance use. The AX1200i is designed to be a workhorse, with up to 8 PCIe connectors for suitable four-way GPU setups. The AX1200i also comes with a Zero RPM mode for the fan, which due to the design allows the fan to be switched off when the power supply is under 30% load.

Further Reading: AnandTech's Corsair AX1500i Power Supply Review

Thank you to Crucial for providing us with MX200 SSDs. Crucial stepped up to the plate as our benchmark list grows larger with newer benchmarks and titles, and the 1TB MX200 units are strong performers. Based on Marvell's 88SS9189 controller and using Micron's 16nm 128Gbit MLC flash, these are 7mm high, 2.5-inch drives rated for 100K random read IOPs and 555/500 MB/s sequential read and write speeds. The 1TB models we are using here support TCG Opal 2.0 and IEEE-1667 (eDrive) encryption and have a 320TB rated endurance with a three-year warranty.

Further Reading: AnandTech's Crucial MX200 (250 GB, 500 GB & 1TB) Review

Thank you to G.Skill for providing us with memory. G.Skill has been a long-time supporter of AnandTech over the years, for testing beyond our CPU and motherboard memory reviews. We've reported on their high capacity and high-frequency kits, and every year at Computex G.Skill holds a world overclocking tournament with liquid nitrogen right on the show floor. One of the most recent deliveries from G.Skill was their 4x16 GB DDR4-3200 C14 Kit, which we are planning for an upcoming review.

Further Reading: AnandTech's Memory Scaling on Haswell Review, with G.Skill DDR3-3000

Thank you to Corsair for providing us with memory. Similarly, Corsair (along with PSUs) is also a long-time supporter of AnandTech. Being one of the first vendors with 16GB modules for DDR4 was a big deal, and now Corsair is re-implementing LEDs back on its memory after a long hiatus along with supporting specific projects such as ASUS ROG versions of the Dominator Platinum range. We're currently looking at our review pipeline to see when our next DRAM round-up will be, and Corsair is poised to participate.

Further Reading: AnandTech's Memory Scaling on Haswell-E Review

Office Performance

The dynamics of CPU Turbo modes, both Intel and AMD, can cause concern during environments with a variable threaded workload. There is also an added issue of the motherboard remaining consistent, depending on how the motherboard manufacturer wants to add in their own boosting technologies over the ones that Intel would prefer they used. In order to remain consistent, we implement an OS-level unique high performance mode on all the CPUs we test which should override any motherboard manufacturer performance mode.

All of our benchmark results can also be found in our benchmark engine, Bench.

Dolphin Benchmark: link

Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU. Results are given in minutes, where the Wii itself scores 17.53 minutes.

As shown by the data, the i7-7700K takes the top spot. At stock it edges out an overclocked Core i7-4790K at 4.7 GHz, which is no mean feat. Dolphin is all about high frequency and IPC, which the i7-7700K has the best of both.

WinRAR 5.0.1: link

Our WinRAR test from 2013 is updated to the latest version of WinRAR at the start of 2014. We compress a set of 2867 files across 320 folders totaling 1.52 GB in size – 95% of these files are small typical website files, and the rest (90% of the size) are small 30 second 720p videos.

WinRAR is more geared towards a variable threaded environment but also memory speed. While two channels of DDR4-2400 does well for the Core i7-7700K, to the point where it beats the 6-core i7-5930K, anything with eDRAM (i7-5775C) and the higher end quad channel processors with up to 10 cores do win out. But at $1700 for 10-core, the Kaby Lake CPU does well – the only processor that beats it in its price range is that eDRAM-based i7 part.

3D Particle Movement v2

3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins the day. This is the second variant of this benchmark, fixing for false sharing in the first version, and lending itself to better multithreaded performance.

3DPMv2 is still new, so we don’t have too many results for it so far, but it hits the top of the mainstream processor stack as was perhaps to be expected. It scores almost double an FX-8370, showing how far Intel’s mainstream has come from AMD’s old CPUs, but the Core i7-7700K matches up to just over double the Core i3-7350K, as it has double the cores/threads and slightly more frequency.

SYSMark 2014

Engineered by BAPco (to which Intel is a consortium member), this set of tests are designed to be an office/data/media/financial range of tests using common well-known CAD, image editing, web browsing and other tools to put out a score, where a score of 1000 is attributed to an old Core i3 using a mechanical harddrive. Here we report the overall score, however the test breakdowns can be found in Bench.

Because SYSMark is a variety of tests that rely on response and throughput, the Core i7-7700K hits the mix just right and scores higher than even a 10-core Core i7 Extreme part launched last year, as well as a highly overclocked Devil’s Canyon. Aside from the Core i5, the 7700K does well in price/performance here.

Web Benchmarks

On the lower end processors, general usability is a big factor of experience, especially as we move into the HTML5 era of web browsing.  For our web benchmarks, we take well known tests with Chrome as installed by SYSMark as a consistent browser.

Mozilla Kraken 1.1

Google Octane v2

Professional Performance: Windows

Agisoft Photoscan – 2D to 3D Image Manipulation: link

Agisoft Photoscan creates 3D models from 2D images, a process which is very computationally expensive. The algorithm is split into four distinct phases, and different phases of the model reconstruction require either fast memory, fast IPC, more cores, or even OpenCL compute devices to hand. Agisoft supplied us with a special version of the software to script the process, where we take 50 images of a stately home and convert it into a medium quality model. This benchmark typically takes around 15-20 minutes on a high end PC on the CPU alone, with GPUs reducing the time.

Here we report the overall time to complete the test – sub-test results can be found in Bench.

Here’s another instance where a stock Core i7-7700K can overcome an overclocked Devil’s Canyon. Agisoft spends a good time of its workload using cache heavy threads, showing that large core parts do really well, however the i7-7700K is on par with the six-core Core i7-3960X, showing that extra IPC and frequency can make up for a core or two.

Cinebench R15

Cinebench is a benchmark based around Cinema 4D, and is fairly well known among enthusiasts for stressing the CPU for a provided workload. Results are given as a score, where higher is better.

While Cinebench R15 is more a synthetic, it remains a popular test to measure professional performance and is free to use. For single threaded performance, the Core i7-7700K hits the top of the pile. With the Skylake and Kaby Lake parts both at 4.8 GHz, there’s almost nothing between them, showing the identical IPC. In multithreaded mode the 7700K is on top of all the mainstream processors as expected, and when overclocked can mix it up with some of the extreme processors as well.

HandBrake v0.9.9: link

For HandBrake, we take two videos (a 2h20 640x266 DVD rip and a 10min double UHD 3840x4320 animation short) and convert them to x264 format in an MP4 container.  Results are given in terms of the frames per second processed, and HandBrake uses as many threads as possible.

The LQ video emphasizes IPC due to its low cache overhead, meaning that the i7-7700K wins again, and when overclocked, performs the same as the 6700K at the same frequency.

The higher resolution video however means that cores with frequency dominate. The i7-7700K stands above processors such as the i7-5820K, the i7-4930K and the i7-3960X, which is no small feat. But if you really want performance here, the big boys are still top performers (if you can afford them).

Hybrid x265

Hybrid is a new benchmark, where we take a 4K 1500 frame video and convert it into an x265 format without audio. Results are given in frames per second.

Our Hybrid test is somewhat similar to the HandBrake HQ test, showing the i7-7700K sitting tall as the mainstream champion.

Legacy Tests

At AnandTech, I’ve taken somewhat of a dim view to pure synthetic tests, as they fail to be relatable. Nonetheless, our benchmark database spans to a time when that is all we had! We take a few of these tests for a pin with the latest hardware.

Cinebench R10

The R10 version of Cinebench is one of our oldest benchmarks, with data going back more than a few generations. The benchmark is similar to that of the newest R15 version, albeit with a simpler render target and a different strategy for multithreading.

For a few years I was under the impression that CineBench’s workload was not amenable to more IPC increases, as we hovered around 7000 pts with new microarchitectures not making much of a difference. Being high frequency the i7-7700K pulls out a lead here, but it’s worth noting that Kaby Lake as a whole scores well, perhaps indicating that other features (such as frequency speed changing) can help.

The multithreaded test gives different results, as this test typically prefers many cores. Rather than the new Cinebench tests dividing the scene up into over a hundred pieces (depends on threads), CB10 purely divides the scene into exactly how many threads are present. If a thread finishes early, it will try and cut the work of another thread in half. This sort of approach to multithreading has a different approach to frequency, cores and IPC, hence why R11.5 and R15 do bigger separations with core workloads.

Cinebench R11.5

CB11.5 has been popular for many years as a performance test, using easy to read and compare numbers that aren’t in the 1000s. We run the benchmark in an automated fashion three times in single-thread and multi-thread mode and take the average of the results.

Similar to other tests, the i7-7700K takes the single thread crown, again beating an overclocked Devil’s Canyon i7-4790K, showing the out-of-the-box performance. Again, Kaby Lake as a whole seems to do well here, thanks to 4.2 GHz turbo modes on the i5-7600K and i3-7350K.

7-zip

As an open source compression/decompression tool, 7-zip is easy to test and features a built-in benchmark to measure performance. As a utility, similar to WinRAR, high thread counts, frequency and UPC typically win the day here.

The Core i7-7700K shows the benefits of frequency over a stock i7-6700K, however at the same frequency they perform roughly the same as expected.

POV-Ray

Ray-tracing is a typical multithreaded test, with each ray being a potential thread in its own right ensuring that a workload can scale in complexity easily. This lends itself to cores, frequency and IPC: the more, the better.

AES via TrueCrypt

Despite TrueCrypt no longer being maintained, the final version incorporates a good test to measure different encryption methodologies as well as encryption combinations. When TrueCrypt was in full swing, the introduction of AES accelerated hardware dialed the performance up a notch, however most of the processors (save the Pentiums/Celerons) now support this and get good speed. The built-in TrueCrypt test does a mass encryption on in-memory data, giving results in GB/s.

The encryption benchmark loves both threads and memory bandwidth, so we see the extreme processors pull out large leads due to 6+ cores and four memory channels. However, we see a similar picture as before to the Devil’s Canyon part: an out-of-the-box Core i7-7700K will beat an overclocked Core i7-4790K at 4.7 GHz.

Alien: Isolation

If first person survival mixed with horror is your sort of thing, then Alien: Isolation, based off of the Alien franchise, should be an interesting title. Developed by The Creative Assembly and released in October 2014, Alien: Isolation has won numerous awards from Game Of The Year to several top 10s/25s and Best Horror titles, ratcheting up over a million sales by February 2015. Alien: Isolation uses a custom built engine which includes dynamic sound effects and should be fully multi-core enabled.

In al of our testing, aside from a couple of scores falling at the bottom depending on the CPU/GPU combo, all the CPUs perform similarly.

Total War: Attila

The Total War franchise moves on to Attila, another The Creative Assembly development, and is a stand-alone strategy title set in 395AD where the main story line lets the gamer take control of the leader of the Huns in order to conquer parts of the world. Graphically the game can render hundreds/thousands of units on screen at once, all with their individual actions and can put some of the big cards to task.

For low end graphics, we test at 720p with performance settings, recording the average frame rate. With mid and high range graphics, we test at 1080p with the quality setting. In both circumstances, unlimited video memory is enabled and the in-game scripted benchmark is used.

Grand Theft Auto V

The highly anticipated iteration of the Grand Theft Auto franchise finally hit the shelves on April 14^th 2015, with both AMD and NVIDIA in tow to help optimize the title. GTA doesn’t provide graphical presets, but opens up the options to users and extends the boundaries by pushing even the hardest systems to the limit using Rockstar’s Advanced Game Engine. Whether the user is flying high in the mountains with long draw distances or dealing with assorted trash in the city, when cranked up to maximum it creates stunning visuals but hard work for both the CPU and the GPU.

For our test we have scripted a version of the in-game benchmark, relying only on the final part which combines a flight scene along with an in-city drive-by followed by a tanker explosion. For low-end systems we test at 720p on the lowest settings, whereas mid and high-end graphics play at 1080p with very high settings across the board. We record both the average frame rate and the percentage of frames under 60 FPS (16.6ms).

GRID Autosport

No graphics tests are complete without some input from Codemasters and the EGO engine, which means for this round of testing we point towards GRID: Autosport, the next iteration in the GRID and racing genre. As with our previous racing testing, each update to the engine aims to add in effects, reflections, detail and realism, with Codemasters making ‘authenticity’ a main focal point for this version.

GRID’s benchmark mode is very flexible, and as a result we created a test race using a shortened version of the Red Bull Ring with twelve cars doing two laps. The car is focus starts last and is quite fast, but usually finishes second or third. For low-end graphics we test at 1080p medium settings, whereas mid and high-end graphics get the full 1080p maximum. Both the average and minimum frame rates are recorded.

Shadow of Mordor

The final title in our testing is another battle of system performance with the open world action-adventure title, Shadow of Mordor. Produced by Monolith using the LithTech Jupiter EX engine and numerous detail add-ons, SoM goes for detail and complexity to a large extent, despite having to be cut down from the original plans. The main story itself was written by the same writer as Red Dead Redemption, and it received Zero Punctuation’s Game of The Year in 2014.

For testing purposes, SoM gives a dynamic screen resolution setting, allowing us to render at high resolutions that are then scaled down to the monitor. As a result, we get several tests using the in-game benchmark. For low-end graphics we examine at 720p with low settings, whereas mid and high-end graphics get 1080p Ultra. The top graphics test is also redone at 3840x2160, also with Ultra settings, and we also test two cards at 4K where possible.

4K

In the Words of Jeremy Clarkson: POWEEEERRRRR

As with all the major processor launches in the past few years, performance is nothing without a good efficiency to go with it. Doing more work for less power is a design mantra across all semiconductor firms, and teaching silicon designers to build for power has been a tough job (they all want performance first, naturally). Of course there might be other tradeoffs, such as design complexity or die area, but no-one ever said designing a CPU through to silicon was easy. Most semiconductor companies that ship processors do so with a Thermal Design Power, which has caused some arguments recently based on performance presentations.

Yes, technically the TDP rating is not the power draw. It’s a number given by the manufacturer to the OEM/system designer to ensure that the appropriate thermal cooling mechanism is employed: if you have a 65W TDP piece of silicon, the thermal solution must support at least 65W without going into heat soak.  Both Intel and AMD also have different ways of rating TDP, either as a function of peak output running all the instructions at once, or as an indication of a ‘real-world peak’ rather than a power virus. This is a contentious issue, especially when I’m going to say that while TDP isn’t power, it’s still a pretty good metric of what you should expect to see in terms of power draw in prosumer style scenarios.

So for our power analysis, we do the following: in a system using one reasonable sized memory stick per channel at JEDEC specifications, a good cooler with a single fan, and a GTX 770 installed, we look at the long idle in-Windows power draw, and a mixed AVX power draw given by OCCT (a tool used for stability testing). The difference between the two, with a good power supply that is nice and efficient in the intended range (85%+ from 50W and up), we get a good qualitative comparison between processors. I say qualitative as these numbers aren’t absolute, as these are at-wall VA numbers based on power you are charged for, rather than consumption. I am working with our PSU reviewer, E.Fylladikatis, in order to find the best way to do the latter, especially when working at scale.

Nonetheless, here are our recent results for Kaby Lake at stock frequencies:

What amazes me, if anything, is how close the Core i7 and Core i3 parts are to their TDP in our measurements. Previously, such as with the Core i7-6700K and Core i7-4790K, we saw +20W on our system compared to TDP, but the Core i7-7700K is pretty much bang on at 90W (for a 91W rated part). Similarly, the Core i3-7350K is rated at 60W and we measured it at 55W. The Core i5-7600K is a bit different due to no hyperthreading meaning the AVX units aren’t loaded as much, but more on that in that review.

To clarify, our tests were performed on retail units. No engineering sample trickery here.

With power on the money, this perhaps mean that Intel is getting the voltages of each CPU to where they should be based on the quality of the silicon. In previous generations, Intel would over estimate the voltage needed in order to capture more CPUs within a given yield – however AMD has been demonstrating of late that it is possible to tailor the silicon more based on internal metrics. Either our samples are flukes, or Intel is doing something similar here.

With power consumption in mind, let’s move on to Overclocking, and watch some sand burn a hole in a PCB (hopefully not).

Overclocking

At this point I’ll assume that as an AnandTech reader, you are au fait with the core concepts of overclocking, the reason why people do it, and potentially how to do it yourself. The core enthusiast community always loves something for nothing, so Intel has put its high-end SKUs up as unlocked for people to play with. As a result, we still see a lot of users running a Sandy Bridge i7-2600K heavily overclocked for a daily system, as the performance they get from it is still highly competitive.

Despite that, the i7-7700K has somewhat of an uphill battle. As a part with a 4.5 GHz turbo frequency, if users are expecting a 20-30% increase for a daily system then we will be pushing 5.4-5.8 GHz, which for daily use with recent processors has not happened.

There’s also a new feature worth mentioning before we get into the meat: AVX Offset. We go into this more in our bigger overclocking piece, but the crux is that AVX instructions are power hungry and hurt stability when overclocked. The new Kaby Lake processors come with BIOS options to implement an offset for these instructions in the form of a negative multiplier. As a result, a user can stick on a high main overclock with a reduced AVX frequency for when the odd instruction comes along that would have previously caused the system to crash.

Because of this, we took our overclocking methods in two ways. First, we left the AVX Offset alone, meaning our OCCT mixed-AVX stability test got the full brunt of AVX power and the increased temperature/power reading there in.  We then applied a second set of overclocks with a -10 offset, meaning that at 4.5 GHz the AVX instructions were at 3.5 GHz. This did screw up some of our usual numbers that rely on the AVX part to measure power, but here are our results:

At stock, our Core i7-7700K ran at 1.248 volts at load, drawing 90 watts (the column marked ‘delta’), and saw a temperature of 79C using our 2kg copper cooling.

After this, we put the CPU on a 20x multiplier, set it to 1.000 volt (which didn’t work, so 1.100 volts instead), gave the load-line calibration setting to Level 1 (constant voltage on ASRock boards), and slowly went up in 100 MHz jumps. Every time the POV-Ray/OCCT stability tests failed, the voltage was raised 0.025V.

This gives a few interesting metrics. For a long time, we did not need a voltage increase: 1.100 volts worked as a setting all the way up to 4.2 GHz, which is what we’ve been expecting for a 14nm processor at such a frequency. From there the voltage starts increasing, but at 4.5 GHz we needed more voltage in a manual overclock to achieve stability than the CPU gave itself at stock frequency. So much for overclocking! It wasn’t until that 4.3-4.5 GHz set of results that the CPU started to get warm, as shown by the OCCT temperature values.

At 4.8 GHz, the Core i7-7700K passed POV-Ray with ease, however the 1.400 volts needed at that point were pushing the processor up to 95C during OCCT and its mixed AVX workload. At that point I decided to call an end to it, where the CPU was now drawing 122W from idle to load. The fact that it is only 122W is surprisingly low – I would have thought we would be nearing 160W at this point, other i7 overclockable processors at this level in the past.

The second set of results is with the AVX offset. This afforded stability at 4.8 GHz and 4.9 GHz, however at 5.0 GHz and 1.425 volts the CPU was clearly going into thermal recovery modes, as given by the lower scores in POV-Ray.

Based on what we’ve heard out in the ether, our CPU sample is somewhat average to poor in terms of overclocking performance. Some colleagues at the motherboard manufacturers are seeing 5.0 GHz at 1.3 volts (with AVX offset) although I’m sure they’re not talking in terms of a serious reasonable stability. 

The New Champion

Given that Intel has no competition, it is perhaps easy to roll out a new mainstream performance champion – all they have to do is have more stringent binning techniques (like perhaps AMD with the FX-9000 series) and a few processors with a higher frequency could pop-out. The danger here is that Intel always sells a lot of its top performer – millions. If you have to dump 100 processors to find one that fits the mold of the top SKU, you either have to charge lots for it or reduce the rules.  The only way to get that mix of yield and viability is by improving how the CPU is made. This is what the ‘optimization’ in Kaby Lake is for.

The Core i7-7700K sits at the top of the stack, and performs like it. A number of enthusiasts complained when they launched the Skylake Core i7-6700K with a 4.0/4.2 GHz rating, as this was below the 4.0/4.4 GHz rating of the older Core i7-4790K. At this level, 200-400 MHz has been roughly the difference of a generational IPC upgrade, so users ended up with similar performing chips and the difference was more in the overclocking. However, given the Core i7-7700K comes out of the box with a 4.2/4.5 GHz arrangement, and support for Speed Shift v2, it handily mops the floor with the Devil’s Canyon part, resigning it to history.

In most of our benchmarks, the results are clear: a stock Core i7-7700K beat our overclocked Core i7-4790K in practically every CPU-based test (Our GPU tests showed little change). When overclocked, the i7-7700K just pushed out a bigger lead for only a few more watts. Technically one could argue that because this part and the i7-6700K are equal in IPC, a similar overclock with the i7-6700K achieves the same performance. But the crucial matter here is how lucky a user is with the silicon lottery – based on our testing, the Core i7-7700K CPUs tend to overclock rather nicely (although +300 MHz isn’t that much in the grand scheme of things).

As with previous high-end mainstream (if that sounds like an oxymoron, it is) Core i7 parts, Intel has put a list price of $303 on 1k tray units, which means that at retail we should see it nearer $330 to $350. As far as we can tell, this won’t get a stock cooler, and anyway we’d recommend something else anyway given the recent performance of Intel stock coolers. We can hope that we won’t see the blatant price gouging we saw when the Skylake parts were launched, where it took several months to bring the prices down to MSRP due to stock allocations.

The Core i7-7700K should be available from January 5^th in most major markets.
It’s the new mainstream performance king, if CPU performance is your thing.

As part of our Kaby Lake coverage, we have some other awesome reviews to check out.

Intel Launches 7^th Generation Kaby Lake (Overview and Core Improvements)
The Intel Core i7-7700K Review: The New Out-of-the-box Performance Champion
The Intel Core i5-7600K Review: The More Amenable Mainstream Performer
The Intel Core i3-7350K Review: When a Core i3 Nearly Matches the Core i7-2600K

Upcoming (we’re at CES and didn’t have time to finish these yet):

Calculating Generational IPC Changes from Sandy Bridge to Kaby Lake
Intel Core i7-7700K, i5-7600K and i3-7350K Overclocking: Hitting 5.0 GHz on AIR
Intel Launches 200-Series Chipset Breakdown: Z270, H270, B250, Q250, C232
Intel Z270 Motherboard Preview: A Quick Look at 80+ Motherboards