It has been ten years since Intel introduced quad-core processors into its mainstream product range. It was expected that six-core parts would hit the segment a few years after, however due to process improvements, microarchitecture gains, cost, and a lack of competition, the top-end mainstream processor is still a quad-core a decade later. That changes today.

Launching today are Intel's new 8^th Generation Coffee Lake CPUs, with the Core i5 and Core i7 parts having six distinct physical cores. In this review we're covering the top SKU, the Core i7-8700K, along with looking at numbers from the Core i5-8400.

Coffee Lake Hits Primetime

There are a number of interesting elements to this launch to be excited about, and a number of factors that raise even further questions, which we will go in to.

To start, the processor stack that Intel is making available today consists of six desktop processors that all fall under the ‘8^th Generation’ nomenclature, and are built under the codename ‘Coffee Lake’ to designate the microarchitecture and manufacturing process combination.

  

All these new processors are desktop parts, meaning they are socketed processors for use in appropriate motherboards featuring the Z370 chipset. Technically these processors use the LGA1151 socket, which is also used by the 6^th Generation and 7^th Generation processors with the Z170 and Z270 chipsets. However due to differences in the pin-layout of these two sets of processors, 8^th Gen will only work in Z370 boards and there is no level of cross compatibility. We will discuss this later.

Intel 8th Generation 'Coffee Lake' Desktop Processors
	i7-8700K	i7-8700	i5-8600K	i5-8400	i3-8350K	i3-8100
Cores	6C / 12T		6C / 6T		4C / 4T
Base Frequency	3.7 GHz	3.2 GHz	3.6 GHz	2.8 GHz	4.0 GHz	3.6 GHz
Turbo Boost 2.0	4.7 GHz	4.6 GHz	4.3 GHz	4.0 GHz	-	-
L3 Cache	12 MB		9 MB		8 MB	6 MB
DRAM Support	DDR4-2666				DDR4-2400
Integrated Graphics	GT2: 24 EUs			GT2: 23 EUs
IGP Base Freq	350 MHz			350 MHz
IGP Turbo	1.20 GHz		1.15 GHz	1.05 GHz	1.15 GHz	1.10 GHz
PCIe Lanes (CPU)	16			16
PCIe Lanes (Z370)	< 24			< 24
TDP	95 W	65 W	95 W	65 W	91 W	65 W
Price (tray)	$359	$303	$257	$182	$168	$117
Price (Newegg) Sale until 10/12	$380	$315	$260	$190	$180	$120
Price (Amazon)	$N/A	$N/A	$N/A	$N/A	$N/A	$N/A

At the top of the stack are two Core i7 Coffee Lake processors. In previous generations ‘Core i7’ meant that we were discussing quad-core parts with hyperthreading, but for this generation it moves up to a six-core part with hyperthreading. The Core i7-8700K starts at a 3.7 GHz base frequency and is designed to turbo to 4.7 GHz in single threaded workloads, with a thermal design power (TDP) of 95W. The K designation means this processor is unlocked and can be overclocked by adjusting the frequency multiplier, subject to appropriate cooling, applied voltage, and the quality of the chip (Intel only guarantees 4.7 GHz).  The Core i7-8700 is the non-K variant, with lower clocks (3.2 GHz base, 4.6 GHz turbo) and a lower TDP (65W).  Both of these processors use 256 KB of L2 cache per core and 2 MB of L3 cache per core.

Kaby Lake i7-K vs Coffee Lake i7-K
i7-7700K		i7-8700K
4C / 8T	Cores	6C / 12T
4.2 GHz	Base Frequency	3.7 GHz
4.5 GHz	Turbo Boost 2.0	4.7 GHz
8 MB	L3 Cache	12 MB
DDR4-2400	DRAM Support	DDR4-2666
GT2: 24 EUs	Integrated Graphics	GT2: 24 EUs
350 MHz	IGP Base Freq	350 MHz
1.15 GHz	IGP Turbo	1.20 GHz
16	PCIe Lanes (CPU)	16
< 24	PCIe Lanes (Chipset)	< 24
95W	TDP	95 W
$339	Price (tray)	$359
$340	Price (Newegg)	$380
$351	Price (Amazon)	$N/A

When compared to the previous generation, the Core i7-8700K starts at a higher price, but for that price comes more cores and a higher turbo frequency. The Core i7-8700K is a good example of how adding cores works: in order to keep the same power consumption, the overall base frequency has to be lowered to match the presence of extra cores. However, in order to keep the responsiveness higher than the previous generation, the single thread performance is often pushed to a higher multiplier. In almost all situations this counts as a win-win, and makes pushing for the 6-core part, on paper at least, a no-brainer.

Kaby Lake i5-7400 vs Coffee Lake i5-8400
i5-7400		i5-8400
4C / 4T	Cores	6C / 6T
3.0 GHz	Base Frequency	2.8 GHz
3.5 GHz	Turbo Boost 2.0	4.0 GHz
6 MB	L3 Cache	9 MB
DDR4-2400	DRAM Support	DDR4-2666
GT2	Integrated Graphics	GT2: 23 EUs
350 MHz	IGP Base Freq	350 MHz
1.00 GHz	IGP Turbo	1.05 GHz
16	PCIe Lanes (CPU)	16
< 24	PCIe Lanes (Chipset)	< 24
65 W	TDP	65 W
$182	Price (tray)	$182
$190	Price (Newegg)	$190
$185	Price (Amazon)	$N/A

In the middle of the stack are the Core i5 processors, with the new generation matching the ‘same configuration without hyperthreading’ philosophy that followed in the previous generation. The two Core i5 parts operate at lower clockspeeds compared to the Core i7, and perhaps more so than we are previously used to, especially with the Core i5-8400 having a base frequency of 2.8 GHz. Intel sampled us the Core i5-8400 for our review, because it hits an important metric: six cores for under $200. Comparing cache sizes to the Core i7, the new parts have the same L2 configuration at 256 KB per core, but have a reduced L3 at 1.5 MB per core as part of the product segmentation.

Kaby Lake i5-7400 vs Coffee Lake i3-8100
i5-7400		i3-8100
4C / 4T	Cores	4C / 4T
3.0 GHz	Base Frequency	3.6 GHz
3.5 GHz	Turbo Boost 2.0	-
6 MB	L3 Cache	6 MB
DDR4-2400	DRAM Support	DDR4-2400
GT2	Integrated Graphics	GT2: 23 EUs
350 MHz	IGP Base Freq	350 MHz
1.00 GHz	IGP Turbo	1.10 GHz
16	PCIe Lanes (CPU)	16
< 24	PCIe Lanes (Chipset)	< 24
65 W	TDP	65 W
$182	Price (tray)	$117
$190	Price (Newegg)	$120
$185	Price (Amazon)	$N/A

It is interesting to note that in the last generation, Intel had processors with two cores and two threads (2C/2T), two cores with hyperthreading (2C/4T), quad cores with four threads (4C/4T) and quad cores with hyperthreading (4C/8T). This layout had staggered, regular steps. With the move to 6C/12T on the high-end Core i7, and 6C/6T on the mid-range Core i5, Intel completely skips the 4C/8T parts and moves straight to 4C/4T on the Core i3. This is likely because a 4C/8T processor might overtake a 6C/6T part in some multi-threaded tests (it would also explain why moving from a previous 4C/8T Core i7 processor to a 6C/6T Core i5 8^th generation is not always an increase in performance).

However at the bottom of the stack are the 4C/4T Core i3 processors, where Intel is pushing out an overclockable Core i3 processor again. This is a little bit of a surprise: in our testing of the previous generation overclockable Core i3, the fact that it was dual core was a setback in a lot of testing. With the Core i3-K now being quad-core, and overclocking it to try and beat a six-core chip for less money, for certain things like gaming we might see less of a difference between the two. Nonetheless, the Core i3s do retain the policy of no Turbo modes on these parts. Another interesting point is the cache: the i3-8350K has 2 MB of L3 cache per core, whereas the i3-8100 only has 1.5 MB of L3 cache per core.

One of our key items to watch in this segment from the initial announcement is that i3-8100. Here is a quad-core processor for only $117. I suspect that this will hit most of the mainstream computing requirements that the previous generation Core i5 (at $182) used to cater for. On paper at least, it seems Intel might have an interesting task trying to explain why more users are opting for a Core i3 this time around.

Turbo Modes

One of the interesting things to come out of our briefings with Intel was the fact that Intel made a very clear change in policy when it comes to press disclosure. When the question was asked about per-core turbo values for each of the CPUs, Intel made a clear statement first, then a secondary one when quizzed further:

“Intel will no longer provide this information”

"We are only including processor frequencies for base and single-core Turbo in our materials going forward - the reasoning is that turbo frequencies are opportunistic given their dependency on system configuration and workloads"

This change in policy is somewhat concerning and completely unnecessary. The information itself could be easily obtained by actually having the processors and probing the required P-states (assuming the motherboard manufacturer does not play silly tricks), so this comes across as Intel withholding information for arbitrary reasons.

Nonetheless, we were able to obtain the per-core turbo ratios for each of the new processors for our motherboard. Given Intel's statement above, it seems to suggest that each motherboard might have different values for these, with no Intel guidelines given.

For the most part, there is nothing out of the ordinary here. Intel uses the base frequency as a guaranteed base under abnormal environmental circumstances and heavy code (AVX2), although in most circumstances even the all-core turbo ratio will be higher than the base frequency.

The odd-one-out is actually the Core i5-8400. It is being shipped with a low base frequency, at 2.8 GHz, but the all-core turbo ratio is 3.8 GHz. Shipping with such a low base frequency is perhaps masking the performance of this part: it should be, on paper at least, only a whisker or two behind the Core i5-8600K.

It is noticeable that the two Core i7 parts both have an all-core turbo of 4.3 GHz, which is only ever matched by the single threaded turbo of the Core i5-8600K. Not only is moving up from the Core i5 to the Core i7 doubling the threads, but the frequency gain is another addition in performance. The Core i5-8600K has a tray price of $257, while the Core i7-8700 is at $303. Overclocking is lost but the threads are doubled, the available turbo frequencies are improved, the cache goes up, and the TDP goes down.

 

CPU A, $250. CPU B, $300.
CPU A has overclocking.
CPU B has double threads, +20% frequency at stock, +33% L3 cache, 1/3 less TDP, but no OC

— Ian Cutress (@IanCutress) October 5, 2017

 

I’ve been running a little Twitter poll on this. It looks like the Core i7-8700 gets the nod almost every time.

This Review: Initial Impressions

For this review today, we are focusing on our preliminary testing of the Core i7-8700K. Intel sampled us both the Core i7-8700K and the Core i5-8400.

These chips only arrived three days before launch. They would have arrived sooner, but I was out of the country on a pre-booked business trip and the courier decided to redeliver as late as possible when I returned. So despite some initial motherboard teething issues (again!), we were able to run our CPU suites and GTX 1080 testing on both chips. We will follow up with data on the other GPUs in the meantime, likely in dedicated CPU reviews, where we’ll include overclocking performance and workstation analysis.

So my apologies go out to our regular readers, especially those that have been expecting the usual gargantuan AnandTech reviews. Time and travel are cruel mistresses, and regular scheduled programming should recommence shortly. 2017 has been the most exciting year in a long while for these quick-fire CPU launches, but also the toughest: whereas previously we would be able to line up a couple of rounds of extra testing, this year has been one launch after another.

Silicon and Process Nodes: 14++

Despite being somewhat reserved in our pre-briefing, and initially blanket labeling the process node for these chips as ‘14nm’, we can confirm that Intel’s newest ‘14++’ manufacturing process is being used for these 8^th Generation processors. This becomes Intel’s third crack at a 14nm process, following on from Broadwell though Skylake (14), Kaby Lake (14+), and now Coffee Lake (14++).

With the 8^th Generation of processors, Intel is moving away from having the generation correlate to both the process node and microarchitecture. As Intel’s plans to shrink its process nodes have become elongated, Intel has decided that it will use multiple process nodes and microarchitectures across a single generation of products to ensure that every update cycle has a process node and microarchitecture that Intel feels best suits that market. A lot of this is down to product maturity, yields, and progress on the manufacturing side.

Intel's Core Architecture Cadence (8/20)
Core Generation	Microarchitecture	Process Node	Release Year
2nd	Sandy Bridge	32nm	2011
3rd	Ivy Bridge	22nm	2012
4th	Haswell	22nm	2013
5th	Broadwell	14nm	2014
6th	Skylake	14nm	2015
7th	Kaby Lake	14nm+	2016
8th	Kaby Lake Refresh Coffee Lake Cannon Lake	14nm+ 14nm++ 10nm	2017 2017 2018?
9th	Ice Lake? ...	10nm+	2018?
Unknown	Cascade Lake (Server)	?	?

Kaby Lake was advertised as using a 14+ node with slightly relaxed manufacturing parameters and a new FinFET profile. This was to allow for higher frequencies and better overclocking, although nothing was fundamentally changed in the core manufacturing parameters. With Coffee Lake at least, the minimum gate pitch has increased from 70nm for 84nm, with all other features being equal.

Increased gate pitch moves transistors further apart, forcing a lower current density. This allows for higher leakage transistors, meaning higher peak power and higher frequency at the expense of die area and idle power.

Normally Intel aims to improve their process every generation, however this seems like a step ‘back’ in some of the metrics in order to gain performance. The truth of the matter is that back in 2015, we were expecting Intel to be selling 10nm processors en-masse by now. As delays have crept into that timeline, the 14++ note is holding over until 10nm is on track. Intel has already stated that 10+ is likely to be the first node on the desktop, which given the track record on 14+ and 14++ might be a relaxed version of 10 in order to hit performance/power/yield targets, with some minor updates. Conceptually, Intel seems to be drifting towards seperate low-power and high-performance process nodes, with the former coming first.

Of course, changing the fin pitch is expected to increase the die area. With thanks to HEKPC (via Videocardz), we can already see a six-core i7-8700K silicon die compared to a quad-core i7-7700K.

The die area of the Coffee Lake 6+2 design (six cores and GT2 graphics) sits at ~151 mm², compared to the ~125 mm² for Kaby Lake 4+2 processor: a 26mm² increase. This increase is mainly due to the two cores, however there is a minor adjustment in the integrated grpahics as well to support HDCP 2.2, not to mention any unpublished changes Intel has made to their designs between Kaby Lake and Coffee Lake.

The following calculations are built on assumptions and contain a margin of error

With the silicon floor plan, we can calculate that the CPU cores (plus cache) account for 47.3% of the die, or 71.35 mm². Divided by six gives a value of 11.9 mm² per core, which means that it takes 23.8 mm² of die area for two cores. Out of the 26mm² increase then, 91.5% of it is for the CPU area, and the rest is likely accounting for the change in the gate pitch across the whole processor. 

The Coffee Lake 4+2 die would then be expected to be around ~127 mm², making a 2mm² increase over the equivalent Kaby Lake 4+2, although this is well within the margin of error for measuring these processors. We are expecting to see some overclockers delid the quad-core processors soon after launch.

In previous Intel silicon designs, when Intel was ramping up its integrated graphics, we were surpassing 50% of the die area being dedicated to graphics. In this 6+2 design, the GPU area accounts for only 30.2% of the floor plan as provided, which is 45.6 mm² of the full die.

Memory Support on Coffee Lake

With a new processor generation comes an update to memory support. There is always a small amount of confusion here about what Intel calls ‘official memory support’ and what the processors can actually run. Intel’s official memory support is typically a guarantee, saying that in all circumstances, with all processors, this memory speed should work. However motherboard manufacturers might offer speeds over 50% higher in their specification sheets, which Intel technically counts as an overclock.

This is usually seen as Intel processors having a lot of headroom to be conservative, avoid RMAs, and maintain stability. In most cases this is usually a good thing: there are only a few niche scenarios where super high-speed memory can equate to tangible performance gains* but they do exist.

*Based on previous experience, but pending a memory scaling review

For our testing at least, our philosophy is that we test at the CPU manufacturers’ recommended setting. If there is a performance gain to be had from slightly faster memory, then it pays dividends to set that as the limit for official memory support. This way, there is no argument on what the rated performance of the processor is.

For the new generation, Intel is supporting DDR4-2666 for the six-core parts and DDR4-2400 for the quad-core parts, in both 1DPC (one DIMM per channel) and 2DPC modes. This should make it relatively simple, compared to AMD’s memory support differing on DPC and type of memory.

It gets simple until we talk about AIO designs using the processors, which typically require SODIMM memory. For these parts, for both quad-core and hex-core, Intel is supporting DDR4-2400 at 1DPC and DDR4-2133 at 2DPC. LPDDR3 support is dropped entirely. The reason for supporting a reduced memory frequency in an AIO environment with SODIMMs is because these motherboards typically run their traces as chained between the memory slots, rather than a T-Topology which helps with timing synchronization. Intel has made the T-Topology part of the specification for desktop motherboards, but not for AIO or integrated ones, which explains the difference in DRAM speed support.

These supported frequencies follow JEDEC official sub-timings. Familiar system builders will be used to DDR4-2133 at a CAS Latency of 15, but as we increase the speed of the modules, the latency increases to compensate:

Intel’s official sub-timing support at DDR4-2666 is 19-19-19. Outside of enterprise modules, that memory does not really exist, because memory manufacturers can seem to mint DDR4-2666 16-17-17 modules fairly easily, and these processors are typically fine with those sub-timings. CPU manufacturers typically only state ‘supported frequency at JEDEC sub-timings’ and do not go into sub-timing discussions, because most users care more about the memory frequency. If time permits, it would be interesting to see just how much of a performance deficit the official JEDEC sub-timings provide compared to what memory is actually on sale.

Differences from Coffee Lake to Kaby Lake

Physical Design: Pin Outs

The platform for the new Coffee Lake systems is going to look and feel very similar to the 6^th and 7^th Generation platform, with some minor differences, but this could lead to a lot of confusion.

Intel has made it very clear that Coffee Lake processors will work only in Z370 motherboards, and not in the previous generation Z270 motherboards. This despite the fact that both generations of boards share the same socket design due to how the pins are used. In Intel’s 8^th Gen datasheet posted online, a full pin-out is provided, showing that there is indeed a difference between the new Coffee Lake processors and the older Kaby Lake processors, and what those specific differences are.

 
Coffee Lake (left), Kaby Lake (right) - not to scale
Image from David Schor, Wikichip

With the new CPUs, more pins are converted from RSVD (reserved) to VCC (power) and VSS (ground), specifically, there are 18 more power pins and 14 more ground pins, with a slight rearrangement in how the pins are provided. Most of the changes can be seen just above the central blank area to the left, where grey RSVD areas are now red.

In any regular generational change, the pin-out adjustment is to be expected. This is usually accompanied by a change in the socket, such as from one flavor of LGA115x to another flavor of LGA115x, in order to avoid any confusion as to what processors work in what motherboards. These sockets might have been physically similar, such as the socket 775 and socket 771 processors, but notched differently to avoid misplacing a CPU into the wrong socket. But this difference does not exist for Coffee Lake.

Physical Design: Notches

So the pin-outs for Coffee Lake and Kaby Lake are different, especially with the support for hex-core processors, but that is not a big story. What is a big story is as the physical socket being identical to the last platform: both use LGA1151. To compound the issue, both sets of processors have the same notches in the same places on their packages, making it very easy to place the wrong CPU in the wrong motherboard. Notches are typically used to physically restrict which processors go into which motherboards. Intel decided there was no need to differentiate this time around.

Whoever at Intel thought this was a good idea needs to reevaluate their decisions. If the new CPU was labelled as LGA1153, still had 1151 pins but slightly different notches, this wouldn’t be an issue because users would not be able to misplace (and potentially damage) their new CPUs by placing them in the wrong motherboards.

Integrated Graphics

Blowing up specialized sand aside, there is going to be a few differences in the capabilities of each platform. The new processors will support HDCP2.2 on both DisplayPort and HDMI, although an external LSPCon is still needed for HDMI 2.0.

The video outputs for Coffee Lake will be similar to that on Kaby Lake, with three display pipes supported for motherboard manufacturers to configure as needed.

The full decode/encode support is listed below.

Perhaps surprisingly, Intel did not explicitly mention the state of the integrated graphics in the new set of processors during our pre-briefing. This is odd, especially given the amount of time spent praising the virtues of previous generations of the graphics. Due to the early announcement of the processors last week, more details have emerged.

All the six processors being made available today will have Intel’s UHD Graphics 630. This is basically identical to the previous generation's HD Graphics 630, except the name is now UHD, which we suppose is for marketing purposes now that UHD content and displays are more ubiquitous when the naming first started. The other change is HDCP2.2 support.

We were told that there are performance improvements with the new graphics package, mainly from an updated driver stack but also increased frequencies. All the parts will have an idle frequency of 350 MHz, and boost up to the following frequencies:

Intel 8th Generation 'Coffee Lake' Desktop Processors
	i7-8700K	i7-8700	i5-8600K	i5-8400	i3-8350K	i3-8100
Integrated Graphics	GT2: 24 EUs			GT2: 23 EUs
IGP Base Freq	350 MHz			350 MHz
IGP Turbo	1.20 GHz	1.20 GHz	1.15 GHz	1.05 GHz	1.15 GHz	1.10 GHz

In the case of the Core i7-8700K, this is a 50 MHz jump over the previous generation.

The Intel Z370 Chipset

From a high level, the Z370 chipset is identical to the Z270 chipset. The connectivity is the same, the number of supported PCIe 3.0 lanes is the same, the available bifurcation is the same, the controller support is the same: it is the same chipset under a new name, to help identify the new motherboards that support Intel’s 8^th Generation processors compared to the previous chipset for the previous generation of processors.

From the chipset directly we get 20-24 PCIe 3.0 lanes, six SATA 6 Gbps ports with support for RAID 0/1/5/10, a total of 14 USB ports (either 2.0 or 3.0, up to a maximum of ten of USB 3.0), and support for network controllers, support for Thunderbolt 3, and support for Intel’s Optane memory as a boot drive. It’s critical that we say ‘support’ here, because the diagram above from Intel is misleading: Intel is not supporting Thunderbolt directly from the chipset, and motherboard manufacturers will have to include a Thunderbolt 3 controller in order to do so.

So on the face of it, the chipset is not too different. What will be different is on the motherboard-as-a-whole side.

Intel vs AMD: The Start of Core Wars

This year has seen a number of CPU releases from both Intel and AMD. AMD’s resurgence with a high-performing x86 core, combined with their performance-per-dollar strategy, has started to make inroads into the markets that AMD lost during its Bulldozer architecture era. When Intel was offering 10 cores for $1700, AMD started offering 8 cores of almost similar performance for $329, marking a significant shift in what the ‘right price’ for a processor should be.

We collated all the tray prices for the recent processor launches for easy comparison, using the launch price of each product. Exact pricing today may differ due to retailers or sales – we have confirmed that these are still the official MSRPs for these processors.

Kaby Lake i7-K vs Coffee Lake i7-K (MSRP)
AMD		Coffee Lake	Kaby Lake	Skylake-X
	$1199+			i9-7980XE i9-7960X i9-7940X i9-7920X
TR 1950X	$999			i9-7900X
TR 1920X	$799
	$599			i9-7820X
TR 1900X	$549
R7 1800X	$499
R7 1700X	$390-$400			i7-7800X
	$359	i7-8700K
	$340-$350		i7-7740X i7-7700K
R7 1700	$329
	$303	i7-8700	i7-7700
	$257	i5-8600K
R5 1600X	$240-$250		i5-7640X i5-7600K
R5 1600	$219		i5-7600
R5 1500X	$180-$190	i5-8400	i5-7400
R5 1400	$169	i3-8350K	i3-7350K
	$149		i3-7320
	$138		i3-7300
R3 1300X	$129
	$117	i3-8100	i3-7100
R3 1200	$109
	$86		G4620
	$64		G4560

Almost every Coffee Lake processor is identical in price to its Kaby Lake predecessor. The main deviations are the K processors, with the Core i7-8700K being +$20 over the i7-7700K, and the i5-8600K being +$15 over the i5-7600K. There is still competition in every segment.

The Competition: Red Mist (AMD)

AMD’s Ryzen and Threadripper parts occupy anywhere from almost $100 for a base quad core design up to $999 for sixteen cores with simultaneous multithreading. It is widely expected that Intel will have a standard instructions-per-clock advantage with its processors, but also Intel is running its processors north of 4.0 GHz for the most part, while AMD is limited by its manufacturing process to 4.0 GHz at best. 

If we do a straightforward price breakdown, the Core i7-8700K ($359) sits almost equally between the Ryzen 7 1700X ($399) and Ryzen 7 1700 ($329). Here this would be a battle of sixteen Zen threads compared to 12 Coffee Lake threads, with the IPC and frequency advantage heavily on Intel’s side. It will be interesting to see where the Core i7-8700 ($303) sits in performance per dollar compared to the Ryzen 7 1700.

The Core i5-8600K ($257) has a nearer neighbor for company: the Ryzen 5 1600X ($248). Before today, this battle was between a quad-core, quad-thread Core i5 against a 12-thread AMD Ryzen chip. With Intel moving the Core i5 parts to having six full cores, albeit without hyperthreading but with a high frequency, it is going to be an interesting battle between the two at this price.

The Core i5-8400 ($182) and Core i3-8350K ($169) sit near the Ryzen 5 1500X ($189) and the Ryzen 5 1400 ($169) respectively. The difference between the Ryzen 5 1500X and the Core i3-8350K would be interesting, given the extreme thread deficit (12 threads vs 4) between the two.

The Competition: Friendly Fire (Intel)

Intel cannot escape competing with itself. Having played with six-core chips in the high-end desktop space, there was ultimately going to be a time when the mainstream platform would start to overlap with the high-end desktop and potentially consume some sales.

As mentioned above, for most of the 8^th Generation Coffee Lake processors, the new parts are simple swap-ins for the old ones. The only ones that have a difference of opinion are going to be the overclockable K models.

Straight off the bat it looks like that the new Coffee Lake processors are going to consume both of the quad-core Kaby Lake-X parts. There is a +$10 price difference for the Six-Core Coffee Lake CPUs, but that $10 gets an extra two cores, cheaper motherboards, an easier to understand ecosystem, and if you need it, integrated graphics. On paper it is a no-brainer – quad-core HEDT processors should be dead now.

Comparing the six-core Skylake-X i7 parts to the Coffee Lake-K parts is going to be interesting. Here’s a straight specification comparison.

Skylake i7-7800X vs Coffee Lake i7-8700K
Skylake-X i7-7800X		Coffee Lake-S i7-8700K
6C / 12T	Cores	6C / 12T
3.5 GHz	Base Frequency	3.7 GHz
4.0 GHz	Turbo Boost 2.0	4.7 GHz
1 MB/core	L2 Cache	256 KB/core
8.25 MB	L3 Cache	12 MB
Quad Channel	DRAM Channels	Dual Channel
DDR4-2400	DRAM Support	DDR4-2666
-	Integrated Graphics	GT2: 24 EUs
-	IGP Base Freq	350 MHz
-	IGP Turbo	1.20 GHz
28	PCIe Lanes (CPU)	16
< 24	PCIe Lanes (Chipset)	< 24
140W	TDP	95 W
$383	Price (tray)	$359
$380	Price (Newegg)	$380
$363	Price (Amazon)	$N/A
$200-$600	Motherboard Price	$100-$400

The main two in contention are the Core i7-8700K ($359) and the Core i7-7800X ($389). For a difference of $30, the Skylake-X chip is two generations behind and slower on frequency, but offers quad-channel memory and 28 PCIe lanes for more PCIe coprocessors. While the Coffee Lake will almost certainly win in terms of raw processor performance, features such as DRAM support and PCIe lanes are not to be thrown away lightly. If you absolutely need > 64 GB of memory, or more than two add-in cards, you have no choice but to look at the Skylake-X platform.

Key Comparisons to Look Out For

In the next series of pages, we will go through our benchmark suite. While we have only had time to run through a limited number of tests with the Core i7-8700K and the Core i5-8400, there are two battles worth keeping an eye on:

• Core i7-8700K vs Core i7-7800X
• Core i5-8400 vs Ryzen 5 1500X

Hopefully we will get the other components in for review, in particular the Core i7-8700 and Core i3-8100, both of which will be interesting to plot in performance-per-dollar graphs.

Power Consumption

For our regular readers, the topic of power consumption has been an interesting one as of late. For the most part, Intel’s consumer processors have been under their expected power consumption, but the recent Skylake-X processors seem to have put that notion out to sea, with numbers almost 20% above what is expected at full load.

The Thermal Design Power (TDP) of a processor is the capability required to adequately cool that processor - while it is not the exact power consumption, is a rough indication of how much power a processor is likely to consume. Higher cooling requirements give to a higher TDP, which naturally fit into a chip that consumes more power. Our last review of consumer processors, the Kaby Lake 7^th Generation chips, showed that the Core i7-7700K consumed pretty much exactly the TDP of the chip, while the Core i5 processors came in under their TDP rating by a large margin. The Coffee Lake processors follow this trend

The Core i7-8700K has a TDP of 95W, but consumes 86.2W at full load, of which the cores account for 78.6W. The rest of the power is consumed mostly by the uncore and the memory controller.

The Core i5-8400 is rated at 65W, and consumes only 49.3W at full load, of which 41.7W is from the cores. That leaves 7.6W on the table for the uncore and memory controller, which is almost identical to that of the Core i7-8700K, showing the similarity in design.

Test Bed and Setup

As per our processor testing policy, we take a premium category motherboard suitable for the socket, and equip the system with a suitable amount of memory running at the manufacturer's 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 i7-8700K (6C/12T, 95W, 3.8 GHz) Intel Core i5-8400 (6C/6T, 65W, 2.8 GHz)
Motherboards	GIGABYTE Z370 Gaming 7
Cooling	Silverstone Argon AR10-115XS
Power Supply	Corsair AX760i PSU
Memory	Corsair Vengeance Pro DDR4-2666 4x8 GB
Video Cards	MSI GTX 1080 Gaming 8GB
Hard Drive	Crucial MX200 1TB
Optical Drive	LG GH22NS50
Case	Open Test Bed
Operating System	Windows 10 Pro 64-bit

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 Sapphire for providing us with several of their AMD GPUs. We met with Sapphire back at Computex 2016 and discussed a platform for our future testing on AMD GPUs with their hardware for several upcoming projects. As a result, they were able to sample us the latest silicon that AMD has to offer. At the top of the list was a pair of Sapphire Nitro R9 Fury 4GB GPUs, based on the first generation of HBM technology and AMD’s Fiji platform. As the first consumer GPU to use HDM, the R9 Fury is a key moment in graphics history, and this Nitro cards come with 3584 SPs running at 1050 MHz on the GPU with 4GB of 4096-bit HBM memory at 1000 MHz.

Further Reading: AnandTech’s Sapphire Nitro R9 Fury Review

Following the Fury, Sapphire also supplied a pair of their latest Nitro RX 480 8GB cards to represent AMD’s current performance silicon on 14nm (as of March 2017). The move to 14nm yielded significant power consumption improvements for AMD, which combined with the latest version of GCN helped bring the target of a VR-ready graphics card as close to $200 as possible. The Sapphire Nitro RX 480 8GB OC graphics card is designed to be a premium member of the RX 480 family, having a full set of 8GB of GDDR5 memory at 6 Gbps with 2304 SPs at 1208/1342 MHz engine clocks.

Further Reading: AnandTech’s AMD RX 480 Review

With the R9 Fury and RX 480 assigned to our gaming tests, Sapphire also passed on a pair of RX 460s to be used as our CPU testing cards. The amount of GPU power available can have a direct effect on CPU performance, especially if the CPU has to spend all its time dealing with the GPU display. The RX 460 is a nice card to have here, as it is powerful yet low on power consumption and does not require any additional power connectors. The Sapphire Nitro RX 460 2GB still follows on from the Nitro philosophy, and in this case is designed to provide power at a low price point. Its 896 SPs run at 1090/1216 MHz frequencies, and it is paired with 2GB of GDDR5 at an effective 7000 MHz.

We must also say thank you to MSI for providing us with their GTX 1080 Gaming X 8GB GPUs. Despite the size of AnandTech, securing high-end graphics cards for CPU gaming tests is rather difficult. MSI stepped up to the plate in good fashion and high spirits with a pair of their high-end graphics. The MSI GTX 1080 Gaming X 8GB graphics card is their premium air cooled product, sitting below the water cooled Seahawk but above the Aero and Armor versions. The card is large with twin Torx fans, a custom PCB design, Zero-Frozr technology, enhanced PWM and a big backplate to assist with cooling.  The card uses a GP104-400 silicon die from a 16nm TSMC process, contains 2560 CUDA cores, and can run up to 1847 MHz in OC mode (or 1607-1733 MHz in Silent mode). The memory interface is 8GB of GDDR5X, running at 10010 MHz. For a good amount of time, the GTX 1080 was the card at the king of the hill.

Further Reading: AnandTech’s NVIDIA GTX 1080 Founders Edition Review

Thank you to ASUS for providing us with their GTX 1060 6GB Strix GPU. To complete the high/low cases for both AMD and NVIDIA GPUs, we looked towards the GTX 1060 6GB cards to balance price and performance while giving a hefty crack at >1080p gaming in a single graphics card. ASUS lended a hand here, supplying a Strix variant of the GTX 1060. This card is even longer than our GTX 1080, with three fans and LEDs crammed under the hood. STRIX is now ASUS’ lower cost gaming brand behind ROG, and the Strix 1060 sits at nearly half a 1080, with 1280 CUDA cores but running at 1506 MHz base frequency up to 1746 MHz in OC mode. The 6 GB of GDDR5 runs at a healthy 8008 MHz across a 192-bit memory interface.

Further Reading: AnandTech’s ASUS GTX 1060 6GB STRIX 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 Corsair for providing us with an AX860i PSU. The AX860i commands a 860W rating at 50C with 80 PLUS certification. This allows for a minimum 89-92% efficiency at 115V and 90-94% at 230V. The AX860i is completely modular, running the larger 200mm design, with a dual ball bearing 140mm fan to assist high-performance use. The AX860i is designed to be a workhorse, with plenty of PCIe connectors for suitable GPU setups. The AX860i 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 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.

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

2017 CPU Benchmarks

For our review, we are implementing our fresh CPU testing benchmark suite, using new scripts developed specifically for this testing. This means that with a fresh OS install, we can configure the OS to be more consistent, install the new benchmarks, maintain version consistency without random updates and start running the tests in under 5 minutes. After that it's a one button press to start an 8-10hr test (with a high-performance core) with nearly 100 relevant data points in the benchmarks given below. The tests cover a wide range of segments, some of which will be familiar but some of the tests are new to benchmarking in general, but still highly relevant for the markets they come from.

Our new CPU tests go through six main areas. We cover the Web (we've got an un-updateable version of Chrome 56), general system tests (opening tricky PDFs, emulation, brain simulation, AI, 2D image to 3D model conversion), rendering (ray tracing, modeling), encoding (compression, AES, h264 and HEVC), office based tests (PCMark and others), and our legacy tests, throwbacks from another generation of bad code but interesting to compare.

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

A side note on OS preparation. As we're using Windows 10, there's a large opportunity for something to come in and disrupt our testing. So our default strategy is multiple: disable the ability to update as much as possible, disable Windows Defender, uninstall OneDrive, disable Cortana as much as possible, implement the high performance mode in the power options, and disable the internal platform clock which can drift away from being accurate if the base frequency drifts (and thus the timing ends up inaccurate).

New Tests

PCMark10 – We had several requests to include PCMark10 in our new testing suite. Normally we wait until a new benchmark has most of the problems ironed out, however our initial performance scaling metrics show that PCMark10 is basically there already. The extended suite covers ‘Essential, Productivity and Creativity’ benchmarks such as GIMP, Blender, video editing, conferencing, complex spreadsheets and other tests. We use the subtest values as well as the gaming physics result.

Agisoft PhotoScan 1.3.3 – Again, requests to use a more updated version of Photoscan were also coming through the inbox. Over the older version, Photoscan includes various throughput enhancements to each of the core points of the algorithm. Agisoft also gave us a new larger set of more detailed test images to generate our 3D models, giving a longer benchmark (but results are not comparable to the old data). We’ve run this benchmark on about a dozen CPUs ready for this review.

Strategic AI - For our test we use the in-game Civilization 6 AI benchmark with a few custom modifications. Civilization is one of the most popular strategy video games on the market, heralded for its ability for extended gameplay and for users to suddenly lose 8 hours in a day because they want to play ‘one more turn’. A strenuous setting would involve a large map with 20 AI players on the most difficult settings, leading to a turn time (waiting for the AI players to all move in one turn) to exceed several minutes on a mid-range system. Note that a Civilization game can easily run for over 500 turns and be played over several months due to the level of engagement and complexity.

Web Tests on Chrome 56

Sunspider 1.0.2
Mozilla Kraken 1.1
Google Octane 2.0
WebXPRT15

System Tests

Strategic AI
PDF Opening
FCAT
3DPM v2.1
Dolphin v5.0
DigiCortex v1.20
Agisoft PhotoScan v1.3.3

Rendering Tests

Corona 1.3
Blender 2.78
LuxMark v3.1 CPU C++
LuxMark v3.1 CPU OpenCL
POV-Ray 3.7.1b4
Cinebench R15 ST
Cinebench R15 MT

Encoding Tests

7-Zip 9.2
WinRAR 5.40
AES Encoding (TrueCrypt 7.2)
HandBrake v1.0.2 x264 LQ
HandBrake v1.0.2 x264-HQ
HandBrake v1.0.2 HEVC-4K

Office / Professional

PCMark 8
PCMark 10
Chromium Compile (v56)
SYSmark 2014 SE (not in this early review)

Legacy Tests

3DPM v1 ST / MT
x264 HD 3 Pass 1, Pass 2
Cinebench R11.5 ST / MT
Cinebench R10 ST / MT

2017 GPU

For our new set of GPU tests, we wanted to think big. There are a lot of users in the ecosystem that prioritize gaming above all else, especially when it comes to choosing the correct CPU. If there's a chance to save $50 and get a better graphics card for no loss in performance, then this is the route that gamers would prefer to tread. The angle here though is tough - lots of games have different requirements and cause different stresses on a system, with various graphics cards having different reactions to the code flow of a game. Then users also have different resolutions and different perceptions of what feels 'normal'. This all amounts to more degrees of freedom than we could hope to test in a lifetime, only for the data to become irrelevant in a few months when a new game or new GPU comes into the mix. Just for good measure, let us add in DirectX 12 titles that make it easier to use more CPU cores in a game to enhance fidelity.

Our original list of nine games planned in February quickly became six, due to the lack of professional-grade controls on Ubisoft titles. If you want to see For Honor, Steep or Ghost Recon: Wildlands benchmarked on AnandTech, point Ubisoft Annecy or Ubisoft Montreal in my direction. While these games have in-game benchmarks worth using, unfortunately they do not provide enough frame-by-frame detail to the end user, despite using it internally to produce the data the user eventually sees (and it typically ends up obfuscated by another layer as well). I would instead perhaps choose to automate these benchmarks via inputs, however the extremely variable loading time is a strong barrier to this.

So we have the following benchmarks as part of our 4/2 script, automated to the point of a one-button run and out pops the results four hours later, per GPU. Also listed are the resolutions and settings used.

• Civilization 6 (1080p Ultra, 4K Ultra)
• Ashes of the Singularity: Escalation* (1080p Extreme, 4K Extreme)
• Shadow of Mordor (1080p Ultra, 4K Ultra)
• Rise of the Tomb Raider #1 - GeoValley (1080p High, 4K Medium)
• Rise of the Tomb Raider #2 - Prophets (1080p High, 4K Medium)
• Rise of the Tomb Raider #3 - Mountain (1080p High, 4K Medium)
• Rocket League (1080p Ultra, 4K Ultra)
• Grand Theft Auto V (1080p Very High, 4K High)

For each of the GPUs in our testing, these games (at each resolution/setting combination) are run four times each, with outliers discarded. Average frame rates, 99th percentiles and 'Time Under x FPS' data is sorted, and the raw data is archived.

The four GPUs we've managed to obtain for these tests are:

• MSI GTX 1080 Gaming X 8G*
• ASUS GTX 1060 Strix 6G
• Sapphire Nitro R9 Fury 4GB
• Sapphire Nitro RX 480 8GB

In our testing script, we save a couple of special things for the GTX 1080 here. The following tests are also added:

• Civilization 6 (8K Ultra, 16K Lowest)

This benchmark, with a little coercion, are able to be run beyond the specifications of the monitor being used, allowing for 'future' testing of GPUs at 8K and 16K with some amusing results. We are only running these tests on the GTX 1080, because there's no point watching a slideshow more than once.

*Due to the timing of this review, we have only had a chance to run some CPU Gaming tests on the GTX 1080.

Benchmarking Performance: CPU System Tests

Our first set of tests is our general system tests. These set of tests are meant to emulate more about what people usually do on a system, like opening large files or processing small stacks of data. This is a bit different to our office testing, which uses more industry standard benchmarks, and a few of the benchmarks here are relatively new and different.

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

Strategic AI

One of the hot button topics this year (and for the next few years, no doubt) is how technology is shifting to using artificial intelligence and purpose built AI hardware to perform better analysis in low power environments. AI is not relatively new as a concept, as we have had it for over 50 years. What is new is the movement to neural network based training and inference: moving from ‘if this then that’ sort of AI to convolutional networks that can perform fractional analysis of all the parameters.

Unfortunately the movement of the neural-network ecosystem is fast paced right now, especially in software. Every few months or so, announcements are made on new software frameworks, improvements in accuracy, or fundamental paradigm shifts in how these networks should be calculated for accuracy, power, performance, and what the underlying hardware should support in order to do so. There is no situational AI benchmarking tools using network topologies that will remain relevant in 2-4 months, let alone an 18-24 month processor benchmark cycle. So to that end our AI test becomes the best of the rest: strategic AI in the latest video games.

For our test we use the in-game Civilization 6 AI benchmark with a few custom modifications. Civilization is one of the most popular strategy video games on the market, heralded for its ability for extended gameplay and for users to suddenly lose 8 hours in a day because they want to play ‘one more turn’. A strenuous setting would involve a large map with 20 AI players on the most difficult settings, leading to a turn time (waiting for the AI players to all move in one turn) to exceed several minutes on a mid-range system. Note that a Civilization game can easily run for over 500 turns and be played over several months due to the level of engagement and complexity.

Before the benchmark is run, we change the game settings for medium visual complexity at a 1920x1080 resolution while using a GTX 1080 graphics card, such that any rendered graphics are not interfering with the benchmark measurements. Our benchmark run uses a command line method to call the built-in AI benchmark, which features 8 AI players on a medium size map but in a late game scenario with most of the map discovered, each civilization in the throes of modern warfare. We set the benchmark to play for 15 turns, and output the per-turn time, which is then read into the script with the geometric mean calculated. This benchmark is newer than most of the others, so we only have a few data points so far:

Our Strategic AI test is new to the scene, and it looks like there is at least an asymptotic result wken you have a 'good enough' processor.

PDF Opening

First up is a self-penned test using a monstrous PDF we once received in advance of attending an event. While the PDF was only a single page, it had so many high-quality layers embedded it was taking north of 15 seconds to open and to gain control on the mid-range notebook I was using at the time. This put it as a great candidate for our 'let's open an obnoxious PDF' test. Here we use Adobe Reader DC, and disable all the update functionality within. The benchmark sets the screen to 1080p, opens the PDF to in fit-to-screen mode, and measures the time from sending the command to open the PDF until it is fully displayed and the user can take control of the software again. The test is repeated ten times, and the average time taken. Results are in milliseconds.

Single thread frequency usualy works well for PDF Opening, although as we add on more high performance cores it becomes more difficult for the system to pin that individual thread to a single core and get the full turbo boost - if anything flares up on any other core then it brings the frequencies down. I suspect that is what is happening here and the next couple of thests where the i7-8700K sits behind the i7-7700K and i7-7740X.

FCAT Processing: link

One of the more interesting workloads that has crossed our desks in recent quarters is FCAT - the tool we use to measure stuttering in gaming due to dropped or runt frames. The FCAT process requires enabling a color-based overlay onto a game, recording the gameplay, and then parsing the video file through the analysis software. The software is mostly single-threaded, however because the video is basically in a raw format, the file size is large and requires moving a lot of data around. For our test, we take a 90-second clip of the Rise of the Tomb Raider benchmark running on a GTX 980 Ti at 1440p, which comes in around 21 GB, and measure the time it takes to process through the visual analysis tool.

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 ray traces 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.

3D Movement Algorithm Test v2.1: link

This is the latest version of the self-penned 3DPM benchmark. The goal of 3DPM is to simulate semi-optimized scientific algorithms taken directly from my doctorate thesis. Version 2.1 improves over 2.0 by passing the main particle structs by reference rather than by value, and decreasing the amount of double->float->double recasts the compiler was adding in. It affords a ~25% speed-up over v2.0, which means new data.

DigiCortex v1.20: link

Despite being a couple of years old, the DigiCortex software is a pet project for the visualization of neuron and synapse activity in the brain. The software comes with a variety of benchmark modes, and we take the small benchmark which runs a 32k neuron/1.8B synapse simulation. The results on the output are given as a fraction of whether the system can simulate in real-time, so anything above a value of one is suitable for real-time work. The benchmark offers a 'no firing synapse' mode, which in essence detects DRAM and bus speed, however we take the firing mode which adds CPU work with every firing.

DigiCortex can take advantage of the extra cores, paired with the faster DDR4-2666 memory. The Ryzen 7 chips still sit at the top here however.

Agisoft Photoscan 1.3.3: link

Photoscan stays in our benchmark suite from the previous version, however now we are running on Windows 10 so features such as Speed Shift on the latest processors come into play. The concept of Photoscan is translating many 2D images into a 3D model - so the more detailed the images, and the more you have, the better the model. The algorithm has four stages, some single threaded and some multi-threaded, along with some cache/memory dependency in there as well. For some of the more variable threaded workload, features such as Speed Shift and XFR will be able to take advantage of CPU stalls or downtime, giving sizeable speedups on newer microarchitectures. The 1.3.3 test is relatively new, so has only been run on a few parts so far.

Benchmarking Performance: CPU Rendering Tests

Rendering tests are a long-time favorite of reviewers and benchmarkers, as the code used by rendering packages is usually highly optimized to squeeze every little bit of performance out. Sometimes rendering programs end up being heavily memory dependent as well - when you have that many threads flying about with a ton of data, having low latency memory can be key to everything. Here we take a few of the usual rendering packages under Windows 10, as well as a few new interesting benchmarks.

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

Corona 1.3: link

Corona is a standalone package designed to assist software like 3ds Max and Maya with photorealism via ray tracing. It's simple - shoot rays, get pixels. OK, it's more complicated than that, but the benchmark renders a fixed scene six times and offers results in terms of time and rays per second. The official benchmark tables list user submitted results in terms of time, however I feel rays per second is a better metric (in general, scores where higher is better seem to be easier to explain anyway). Corona likes to pile on the threads, so the results end up being very staggered based on thread count.

With more threads on display, the Core i7-8700K gets ahead of the previous mainstream Core i7 parts. The frequency difference over the Skylake-X processor gives an extra +10% performance, but the 16-thread parts from AMD win out overall.

Blender 2.78: link

For a render that has been around for what seems like ages, Blender is still a highly popular tool. We managed to wrap up a standard workload into the February 5 nightly build of Blender and measure the time it takes to render the first frame of the scene. Being one of the bigger open source tools out there, it means both AMD and Intel work actively to help improve the codebase, for better or for worse on their own/each other's microarchitecture.

Blender seems to separate very nicely into core counts, with six cores from Intel matching eight cores from AMD.

LuxMark v3.1: Link

As a synthetic, LuxMark might come across as somewhat arbitrary as a renderer, given that it's mainly used to test GPUs, but it does offer both an OpenCL and a standard C++ mode. In this instance, aside from seeing the comparison in each coding mode for cores and IPC, we also get to see the difference in performance moving from a C++ based code-stack to an OpenCL one with a CPU as the main host.

POV-Ray 3.7.1b4: link

Another regular benchmark in most suites, POV-Ray is another ray-tracer but has been around for many years. It just so happens that during the run up to AMD's Ryzen launch, the code base started to get active again with developers making changes to the code and pushing out updates. Our version and benchmarking started just before that was happening, but given time we will see where the POV-Ray code ends up and adjust in due course.

Cinebench R15: link

The latest version of CineBench has also become one of those 'used everywhere' benchmarks, particularly as an indicator of single thread performance. High IPC and high frequency gives performance in ST, whereas having good scaling and many cores is where the MT test wins out.

CineBench R15 in single thread mode can take the Core i7-8700K by the horns and drag it to be the best performing chip ever tested.

Benchmarking Performance: CPU Web Tests

One of the issues when running web-based tests is the nature of modern browsers to automatically install updates. This means any sustained period of benchmarking will invariably fall foul of the 'it's updated beyond the state of comparison' rule, especially when browsers will update if you give them half a second to think about it. Despite this, we were able to find a series of commands to create an un-updatable version of Chrome 56 for our 2017 test suite. While this means we might not be on the bleeding edge of the latest browser, it makes the scores between CPUs comparable.

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

SunSpider 1.0.2: link

The oldest web-based benchmark in this portion of our test is SunSpider. This is a very basic javascript algorithm tool, and ends up being more a measure of IPC and latency than anything else, with most high-performance CPUs scoring around about the same. The basic test is looped 10 times and the average taken. We run the basic test 4 times.

Mozilla Kraken 1.1: link

Kraken is another Javascript based benchmark, using the same test harness as SunSpider, but focusing on more stringent real-world use cases and libraries, such as audio processing and image filters. Again, the basic test is looped ten times, and we run the basic test four times.

Google Octane 2.0: link

Along with Mozilla, as Google is a major browser developer, having peak JS performance is typically a critical asset when comparing against the other OS developers. In the same way that SunSpider is a very early JS benchmark, and Kraken is a bit newer, Octane aims to be more relevant to real workloads, especially in power constrained devices such as smartphones and tablets.

WebXPRT 2015: link

While the previous three benchmarks do calculations in the background and represent a score, WebXPRT is designed to be a better interpretation of visual workloads that a professional user might have, such as browser based applications, graphing, image editing, sort/analysis, scientific analysis and financial tools.

Benchmarking Performance: CPU Encoding Tests

One of the interesting elements on modern processors is encoding performance. This includes encryption/decryption, as well as video transcoding from one video format to another. In the encrypt/decrypt scenario, this remains pertinent to on-the-fly encryption of sensitive data - a process by which more modern devices are leaning to for software security. Video transcoding as a tool to adjust the quality, file size and resolution of a video file has boomed in recent years, such as providing the optimum video for devices before consumption, or for game streamers who are wanting to upload the output from their video camera in real-time. As we move into live 3D video, this task will only get more strenuous, and it turns out that the performance of certain algorithms is a function of the input/output of the content.

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

7-Zip 9.2: link

One of the freeware compression tools that offers good scaling performance between processors is 7-Zip. It runs under an open-source licence, is fast, and easy to use tool for power users. We run the benchmark mode via the command line for four loops and take the output score.

WinRAR 5.40: link

For the 2017 test suite, we move to the latest version of WinRAR in our compression test. WinRAR in some quarters is more user friendly that 7-Zip, hence its inclusion. Rather than use a benchmark mode as we did with 7-Zip, here we take a set of files representative of a generic stack (33 video files in 1.37 GB, 2834 smaller website files in 370 folders in 150 MB) of compressible and incompressible formats. The results shown are the time taken to encode the file. Due to DRAM caching, we run the test 10 times and take the average of the last five runs when the benchmark is in a steady state.

AES Encoding

Algorithms using AES coding have spread far and wide as a ubiquitous tool for encryption. Again, this is another CPU limited test, and modern CPUs have special AES pathways to accelerate their performance. We often see scaling in both frequency and cores with this benchmark. We use the latest version of TrueCrypt and run its benchmark mode over 1GB of in-DRAM data. Results shown are the GB/s average of encryption and decryption.

HandBrake v1.0.2 H264 and HEVC: link

As mentioned above, video transcoding (both encode and decode) is a hot topic in performance metrics as more and more content is being created. First consideration is the standard in which the video is encoded, which can be lossless or lossy, trade performance for file-size, trade quality for file-size, or all of the above can increase encoding rates to help accelerate decoding rates. Alongside Google's favorite codec, VP9, there are two others that are taking hold: H264, the older codec, is practically everywhere and is designed to be optimized for 1080p video, and HEVC (or H265) that is aimed to provide the same quality as H264 but at a lower file-size (or better quality for the same size). HEVC is important as 4K is streamed over the air, meaning less bits need to be transferred for the same quality content.

Handbrake is a favored tool for transcoding, and so our test regime takes care of three areas.

Low Quality/Resolution H264: Here we transcode a 640x266 H264 rip of a 2 hour film, and change the encoding from Main profile to High profile, using the very-fast preset.

High Quality/Resolution H264: A similar test, but this time we take a ten-minute double 4K (3840x4320) file running at 60 Hz and transcode from Main to High, using the very-fast preset.

HEVC Test: Using the same video in HQ, we change the resolution and codec of the original video from 4K60 in H264 into 4K60 HEVC.

Benchmarking Performance: CPU Office Tests

The office programs we use for benchmarking aren't specific programs per-se, but industry standard tests that hold weight with professionals. The goal of these tests is to use an array of software and techniques that a typical office user might encounter, such as video conferencing, document editing, architectural modeling, and so on and so forth.

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

Chromium Compile (v56)

Our new compilation test uses Windows 10 Pro, VS Community 2015.3 with the Win10 SDK to compile a nightly build of Chromium. We've fixed the test for a build in late March 2017, and we run a fresh full compile in our test. Compilation is the typical example given of a variable threaded workload - some of the compile and linking is linear, whereas other parts are multithreaded.

For our compile test, it would appear that the extra memory width afforded by the quad-channel memory of Skylake-X can have a direct benefit in compile performance.

PCMark 10

PCMark 10 is the 2017 update to the family favorite, PCMark 8. PCMark 8 has been part of our test bed since the latest update in Q1. For the most part it runs well, although for some processors it doesn’t recognize, some tests will not complete, leading to holes in our benchmark data (there’s also an odd directory quirk in one test that causes issues). The newest version, PCMark 10, is the answer.

The new test is adapted for more 2016/2017 workflows. With the advent of office applications that perform deeper compute tasks, or the wave of online gamers and streamers, the idea behind PCMark 10 is to give a better ‘single number’ result that can provide a comparable metric between systems. Single metrics never tell the whole story, so we’re glad that Futuremark provides a very detailed breakdown of what goes on.

Ganesh’s article on PCMark 10 goes into more detail than I will here, but the ‘Extended Benchmark’ runs through four different sets of tests: Essential, Productivity, Creation and Gaming. Each of these have sub-test results as well, including startup performance, web performance, video conferencing, photo/video editing, spreadsheets, rendering, and physics, which you can find in Bench.

PCMark8: link

Despite originally coming out in 2008/2009, Futuremark has maintained PCMark8 to remain relevant in 2017. On the scale of complicated tasks, PCMark focuses more on the low-to-mid range of professional workloads, making it a good indicator for what people consider 'office' work. We run the benchmark from the commandline in 'conventional' mode, meaning C++ over OpenCL, to remove the graphics card from the equation and focus purely on the CPU. PCMark8 offers Home, Work and Creative workloads, with some software tests shared and others unique to each benchmark set.

Benchmarking Performance: CPU Legacy Tests

Our legacy tests represent benchmarks that were once at the height of their time. Some of these are industry standard synthetics, and we have data going back over 10 years. All of the data here has been rerun on Windows 10, and we plan to go back several generations of components to see how performance has evolved.

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

3D Particle Movement v1

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 in the single thread version, whereas the multithread version has to handle the threads and loves more cores. This is the original version, written in the style of a typical non-computer science student coding up an algorithm for their theoretical problem, and comes without any non-obvious optimizations not already performed by the compiler, such as false sharing.

CineBench 11.5 and 10

Cinebench is a widely known benchmarking tool for measuring performance relative to MAXON's animation software Cinema 4D. Cinebench has been optimized over a decade and focuses on purely CPU horsepower, meaning if there is a discrepancy in pure throughput characteristics, Cinebench is likely to show that discrepancy. Arguably other software doesn't make use of all the tools available, so the real world relevance might purely be academic, but given our large database of data for Cinebench it seems difficult to ignore a small five minute test. We run the modern version 15 in this test, as well as the older 11.5 and 10 due to our back data.

x264 HD 3.0

Similarly, the x264 HD 3.0 package we use here is also kept for historic regressional data. The latest version is 5.0.1, and encodes a 1080p video clip into a high quality x264 file. Version 3.0 only performs the same test on a 720p file, and in most circumstances the software performance hits its limit on high end processors, but still works well for mainstream and low-end. Also, this version only takes a few minutes, whereas the latest can take over 90 minutes to run.

Civilization 6

First up in our CPU gaming tests is Civilization 6. Originally penned by Sid Meier and his team, the Civ series of turn-based strategy games are a cult classic, and many an excuse for an all-nighter trying to get Gandhi to declare war on you due to an integer overflow. Truth be told I never actually played the first version, but every edition from the second to the sixth, including the fourth as voiced by the late Leonard Nimoy, it a game that is easy to pick up, but hard to master.

Benchmarking Civilization has always been somewhat of an oxymoron – for a turn-based strategy game, the frame rate is not necessarily the important thing here and even in the right mood, something as low as 5 frames per second can be enough. With Civilization 6 however, Firaxis went hardcore on visual fidelity, trying to pull you into the game. As a result, Civilization can taxing on graphics and CPUs as we crank up the details, especially in DirectX 12.

Perhaps a more poignant benchmark would be during the late game, when in the older versions of Civilization it could take 20 minutes to cycle around the AI players before the human regained control. The new version of Civilization has an integrated ‘AI Benchmark’, although it is not currently part of our benchmark portfolio yet, due to technical reasons which we are trying to solve. Instead, we run the graphics test, which provides an example of a mid-game setup at our settings.

At both 1920x1080 and 4K resolutions, we run the same settings. Civilization 6 has sliders for MSAA, Performance Impact and Memory Impact. The latter two refer to detail and texture size respectively, and are rated between 0 (lowest) to 5 (extreme). We run our Civ6 benchmark in position four for performance (ultra) and 0 on memory, with MSAA set to 2x.

For reviews where we include 8K and 16K benchmarks (Civ6 allows us to benchmark extreme resolutions on any monitor) on our GTX 1080, we run the 8K tests similar to the 4K tests, but the 16K tests are set to the lowest option for Performance.

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

MSI GTX 1080 Gaming 8G Performance

1080p

4K

8K

16K

Ashes of the Singularity Escalation

Seen as the holy child of DirectX12, Ashes of the Singularity (AoTS, or just Ashes) has been the first title to actively go explore as many of DirectX12s features as it possibly can. Stardock, the developer behind the Nitrous engine which powers the game, has ensured that the real-time strategy title takes advantage of multiple cores and multiple graphics cards, in as many configurations as possible.

As a real-time strategy title, Ashes is all about responsiveness during both wide open shots but also concentrated battles. With DirectX12 at the helm, the ability to implement more draw calls per second allows the engine to work with substantial unit depth and effects that other RTS titles had to rely on combined draw calls to achieve, making some combined unit structures ultimately very rigid.

Stardock clearly understand the importance of an in-game benchmark, ensuring that such a tool was available and capable from day one, especially with all the additional DX12 features used and being able to characterize how they affected the title for the developer was important. The in-game benchmark performs a four-minute fixed seed battle environment with a variety of shots, and outputs a vast amount of data to analyze.

For our benchmark, we run a fixed v2.11 version of the game due to some peculiarities of the splash screen added after the merger with the standalone Escalation expansion, and have an automated tool to call the benchmark on the command line. (Prior to v2.11, the benchmark also supported 8K/16K testing, however v2.11 has odd behavior which nukes this.)

At both 1920x1080 and 4K resolutions, we run the same settings. Ashes has dropdown options for MSAA, Light Quality, Object Quality, Shading Samples, Shadow Quality, Textures, and separate options for the terrain. There are several presents, from Very Low to Extreme: we run our benchmarks at Extreme settings, and take the frame-time output for our average, percentile, and time under analysis.

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

 

MSI GTX 1080 Gaming 8G Performance

1080p

4K

Shadow of Mordor

The next title in our testing is a battle of system performance with the open world action-adventure title, Middle Earth: Shadow of Mordor (SoM for short). Produced by Monolith and using the LithTech Jupiter EX engine and numerous detail add-ons, SoM goes for detail and complexity. 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.

A 2014 game is fairly old to be testing now, however SoM has a stable code and player base, and can still stress a PC down to the ones and zeroes. At the time, SoM was unique, offering a dynamic screen resolution setting allowing users to render at high resolutions that are then scaled down to the monitor. This form of natural oversampling was designed to let the user experience a truer vision of what the developers wanted, assuming you had the graphics hardware to power it but had a sub-4K monitor.

The title has an in-game benchmark, for which we run with an automated script implement the graphics settings, select the benchmark, and parse the frame-time output which is dumped on the drive. The graphics settings include standard options such as Graphical Quality, Lighting, Mesh, Motion Blur, Shadow Quality, Textures, Vegetation Range, Depth of Field, Transparency, and Tessellation. There are standard presets as well.

We run the benchmark at 1080p and a native 4K, using our 4K monitors, at the Ultra preset. Results are averaged across four runs and we report the average frame rate, 99^th percentile frame rate, and time under analysis.

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

 

MSI GTX 1080 Gaming 8G Performance

1080p

4K

Rise of the Tomb Raider

One of the newest games in the gaming benchmark suite is Rise of the Tomb Raider (RoTR), developed by Crystal Dynamics, and the sequel to the popular Tomb Raider which was loved for its automated benchmark mode. But don’t let that fool you: the benchmark mode in RoTR is very much different this time around.

Visually, the previous Tomb Raider pushed realism to the limits with features such as TressFX, and the new RoTR goes one stage further when it comes to graphics fidelity. This leads to an interesting set of requirements in hardware: some sections of the game are typically GPU limited, whereas others with a lot of long-range physics can be CPU limited, depending on how the driver can translate the DirectX 12 workload.

Where the old game had one benchmark scene, the new game has three different scenes with different requirements. These are three scenes designed to be taken from the game, but it has been noted that scenes like 2-Prophet shown in the benchmark can be the most CPU limited elements of that entire level, and the scene shown is only a small portion of that level. Because of this, we report the results for each scene on each graphics card separately.

Graphics options for RoTR are similar to other games in this type, offering some presets or allowing the user to configure texture quality, anisotropic filter levels, shadow quality, soft shadows, occlusion, depth of field, tessellation, reflections, foliage, bloom, and features like PureHair which updates on TressFX in the previous game.

Again, we test at 1920x1080 and 4K using our native 4K displays. At 1080p we run the High preset, while at 4K we use the Medium preset which still takes a sizable hit in frame rate.

It is worth noting that RoTR is a little different to our other benchmarks in that it keeps its graphics settings in the registry rather than a standard ini file, and unlike the previous TR game the benchmark cannot be called from the command-line. Nonetheless we scripted around these issues to automate the benchmark four times and parse the results. From the frame time data, we report the averages, 99^th percentiles, and our time under analysis.

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

#1 Geothermal Valley Spine of the Mountain

MSI GTX 1080 Gaming 8G Performance

1080p

4K

 

#2 Prophet’s Tomb

MSI GTX 1080 Gaming 8G Performance

1080p

4K

 

#3 Spine of the Mountain GeoThermal Valley

MSI GTX 1080 Gaming 8G Performance

1080p

4K

The 8700K did not seem to play nicely with RoTR. We'll go back and check this.

Grand Theft Auto V

The highly anticipated iteration of the Grand Theft Auto franchise 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 under DirectX 11. 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. The in-game benchmark consists of five scenarios: four short panning shots with varying lighting and weather effects, and a fifth action sequence that lasts around 90 seconds. We use only the final part of the benchmark, which combines a flight scene in a jet followed by an inner city drive-by through several intersections followed by ramming a tanker that explodes, causing other cars to explode as well. This is a mix of distance rendering followed by a detailed near-rendering action sequence, and the title thankfully spits out frame time data.

There are no presets for the graphics options on GTA, allowing the user to adjust options such as population density and distance scaling on sliders, but others such as texture/shadow/shader/water quality from Low to Very High. Other options include MSAA, soft shadows, post effects, shadow resolution and extended draw distance options. There is a handy option at the top which shows how much video memory the options are expected to consume, with obvious repercussions if a user requests more video memory than is present on the card (although there’s no obvious indication if you have a low-end GPU with lots of GPU memory, like an R7 240 4GB).

To that end, we run the benchmark at 1920x1080 using an average of Very High on the settings, and also at 4K using High on most of them. We take the average results of four runs, reporting frame rate averages, 99^th percentiles, and our time under analysis.

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

MSI GTX 1080 Gaming 8G Performance

1080p

4K

Intel Coffee Lake Conclusion

It has been a long time coming, but we finally have something bigger than a quad-core processor on Intel’s mainstream platform. Fundamentally it might be the same architecture as the processors preceded it, but after a decade of quad-core Intel parts, it comes as a welcome improvement. Intel sampled us the Core i7-8700K and the Core i5-8400 for this set of initial launch testing, with the goal of offering more high performance cores at more mainstream price points without having to invest in the company's more expensive and otherwise more complex HEDT platforms.

  

The Core i7-8700K

The Core i7-8700K in our testing was designed to be the new halo mainstream processor: many cores and the highest frequencies seen on an Intel part out of the box, with the option of overclocking thrown in. With a peak turbo frequency of 4.7 GHz, in benchmarks that could be stripped down to a single core with no other work going on, the i7-8700K took home the bacon.

The problem here is the same problem we’ve seen with big core parts and Windows 10, however: these large processors can only take so much before having to move threads around, to keep both the frequency high and the energy density low. All it takes is for a minor internal OS blip and single-threaded performance begins to diminish. Windows 10 famously kicks in a few unwanted instruction streams when you are not looking, and as a result the CPU fires up another CPU core and drops to a lower turbo bin. Consequently the average single thread performance seen on the 8700K might be equal or lower than that of the previous generation. It becomes an infuriating problem to debug as a reviewer.

Nonetheless, when software needs to take advantage of the cores, the Core i7-8700K will run through at an all-core turbo frequency of 4.3 GHz, consuming about 86W in the process. The jump up from a quad-core to a hex-core for only a $20 difference will be immediately noticeable in the software that can take advantage of it.

What is interesting to note is that the Core i7-8700K essentially kills the short-lived Kaby Lake-X parts on the X299 high-end desktop platform. Again, for a few extra dollars on the 8700K, a user can save over $100 on the motherboard, get more cores and more performance, and not have the hassle of dealing with a hybrid X299 platform. It does make me wonder why Intel released Kaby Lake-X in the first place, if they knew just how short lived they would be.

When comparing against the Core i7-7800X, a high-end desktop part at a similar price and with the same core count but a lower frequency, it really comes down to what the user needs. Performance easily favors the Core i7-8700K, however that cannot replace the quad-channel memory (up to 128GB) and the 28 PCIe lanes that the Core i7-7800X can support. In most circumstances, especially gaming, the Core i7-8700K will win out.

Intel’s 8^th Generation CPUs: The Ones To Watch

Intel also sampled us the Core i5-8400, showing that six-core processors can cost less than $200. This processor, along with the Core i3-8100, will form the new backbone of general computing when using Intel components: the Core i3-8100 replaces old Core i5 processors for around $120, and enthusiasts who simply want a little more oomph can go with the Core i5-8400 at $190 at retail. It almost comes across as adding 50% cost for adding 50% performance. Personally I think the Core i3-8100, if made widely available, will be a top-selling processor for casual desktop users and gamers who were previously looking for a good performance-per-dollar part.

There is one other comparison to note: the Core i5-8600K and the Core i7-8700. These two parts are $50 apart, however the Core i7-8700 has double the threads, +10% raw frequency, 33% more L3 cache, and 1/3 lower TDP. The Core i5-8600K has overclocking, however going up to the i7 ensures stability, and should offer more raw performance. It will be interesting to get these two in to test, and especially to see if the TDP rating makes a significant performance difference.

Today’s Review Takeaway

We finally have six-core processors on Intel’s mainstream platform, which has driven up the core counts (and frequencies) of the company's low and mid-range processors. For anyone looking at building a system in the last 6-12 months, they should be able to build an equivalent with the latest-generation processor for $50-$100 less. Or spend the same and get a few more cores to play with. The last time we had this situation was a decade ago, and hopefully it won’t take another decade to happen again.

Dedicated reviews for the processors (with more gaming tests) are on the cards. Stay tuned!