AMD vs Intel: we put the most powerful desktops for designers and artists head-to-head

In a battle of the 16-core-chips, we test AMD's Ryzen Threadripper 1950X against Intel's Core i9-7960X to see which would be best inside your next desktop PC.

Who makes the best 16-core CPU? We asked hardcore computing journalist from sister site PC World to find out. He worked with US-based boutique custom PC builder Falcon Northwest built a pair of nearly-identical rigs that could truly go head to head.

We've gone for 16-core chips as they offers the best mix of clock-speed, cores and price.

Our 16-core Falcon Northwest Talon specs

As Falcon Northwest is famous for, both Talon systems are over-the-top in specs and chassis. Each came equipped with:

  • 128GB of DDR4 RAM
  • Two Nvidia Titan Xp graphics cards in SLI
  • A pair of Samsung 1TB 960 Pro SSDs
  • A 6TB Western Digital hard drive
  • Both feature the same 1,000-watt EVGA Super Nova G3 PSU and the same custom closed-loop cooler system. The number and type of system fans are the same as well.

Although both have the same storage subsystem, there is a slight variance. The pair of Samsung 960 Pro NVMe SSDs in the Intel system are configured as PCIe devices in RAID 0, while the AMD box keeps both Samsung 960 Pro drives as separate drives.

We settled for this variance so as not to hobble the Intel box. After all, at the time we requested the machines in early September, RAID 0 using NVMe drives was available only on the Intel platform (not VROC, but using the X299 chipset) not on AMD's X399. Since then, AMD has introduced support for NVMe RAID.

Looking at the read and write performance of both machines, the difference doesn't seem to matter much. The Intel system has somewhat higher read speeds, while the AMD system has somewhat higher write speeds.

We matched carefully in most other areas. Both CPUs are kept bone stock. At the time of our story, Falcon had qualified 128GB of RAM up to DDR4/3000 speeds for the Intel system, while the highest-clocked RAM on the Threadripper system when using 8 DIMMS was DDR4/2400. We decided to keep both machines at DDR4/2400 to match in price as well as capability.

Other than the CPU and motherboard, the only other big difference is the colour.

The AMD machine is hand-painted in luscious Red Clouds, while the Intel machine is hand-painted in the striking Cobalt Clouds.


This Falcon Northwest Talon features a 16-core Threadripper 1950X, 128GB of RAM, and pair of Titan Xp graphics cards. The paint job is called Red Clouds.

This Falcon Northwest Talon features a 16-core Core i9-7960X, 128GB of RAM, and a pair of Titan Xp graphics card. The paint job is called Cobalt Clouds.

Cinebench R15 Performance

First up is Maxon's Cinebench R15 test. It's a free benchmark based on the rendering engine Maxon uses in its professional Cinema4D app. It's highly multi-threaded and almost entirely a CPU-focused test (though there is a graphics test, too).

The default mode is to test all of the cores at once, as you would when rendering. The Core i9 squeaks by the Threadripper box by a few percentage points.


Cinebench R15 also allows you to tweak the number of threads to test, so we ran it on only a single core. This is where Intel has had an advantage over Zen-based chips, and it shows with the Core i9's 15-percent lead on single-threaded tasks. We'll dive into just where Intel gets this advantage later, but anyone who thinks this isn't a big win for the 16-core Core i9 is in denial.

POV Ray Performance

The Persistence of Vision Raytracer is an app that literally goes back to the days of the Commodore Amiga. Obviously converted to run on modern hardware, the free ray tracer loves CPU cores and threads. As we saw with Cinebench, the Core i9 has a slight edge in performance.

POV-Ray also supports running in single-threaded mode. As with Cinebench, we see a very clear advantage go to the Core i9, mostly due to the clock speed advantage the Intel chip holds. (We'll get into just how much of a clock speed advantage that is later on.) There's no denying that on lightly threaded loads, Core i9 has the advantage.

Blender Performance

Blender is an open-source 3D modeler that sees a lot of use by independent movie makers for effects sequences. Even NASA uses Blender these days to produce 3D models.

Blender was also the benchmark of choice AMD used when it first unveiled its Zen CPU last year. So who leads the way here? In the chart below (showing Blender using the BMW benchmark), lower scores are better in rendering, and the Core i9 has a double-digit lead over the Threadripper part. Ouch.

Corona Renderer 1.3 Performance

Corona Renderer was first introduced with AMD's Threadripper, and it was used to soundly trounce Intel's 10-core Core i9-7900X chip because 16 > 10. When it's 16-on-16, though, things go a little sideways. Where Cinebench and POV-Ray put the two CPUs fairly close, Corona Renderer 1.3 puts the Threadripper about 19 percent slower than the Core i9. Ouch again.

Benchmarks can be easily become political footballs, with one side's fans claiming a test is cooked to favor the other. Let's remind everyone that it was AMD who recommended the Corona Renderer test.

Handbrake Performance

For encoding, we ran our standard test, which tasks the free Handbrake encoder with converting a 30GB 1080p MKV file using the Android Tablet preset. Like most encoders, Handbrake favors having more cores, and we see the two chips in the same neighborhood at least. The Core i9 still comes out ahead by 8 percent, but at least it isn't the blowout we saw in Corona or Blender.

Power consumption

We usually shy away from power consumption comparisons because they can be blown out of proportion. In a desktop PC with multiple drives and a graphics card, the CPU isn't the power hog, it's the graphic card. The second reason is the difficulty measuring power consumption between different systems. But hey, here we are with nearly duplicate systems, so we plugged the Northwest Talon PCs into Watts Up Pro meters and measured the total power consumption under different CPU-only loads.

Using Cinebench R15 to push the systems from 1 thread to 32 threads, it was clear which CPU was the winner. What's also interesting is to see how Threadripper's power consumption levels off once it hits about a 16-thread load. Core i9 just continues to ramp up power consumption as you increase the load. And mind you—this is stock clocked. Vendors have told us they've seen Core i9 consume more than 500 watts under heavy overclocking.

The bang for buck stops here

One last thing to consider is that the price of just the CPU isn't everything. When it's watered down by the total cost of the system, it may indeed be worth it for some. For example, the Falcon Northwest Talon systems that we used were both dream configurations with $2,400 in GPUs, maybe $1,800 in RAM and $1,200 in SSDs. That doesn't count the motherboard, hard drive, cooling, case, power supply or custom hand-paint jobs. When you're building a box in this range, the price difference in the CPU isn't that much. Of course, not everyone buys loaded machines like the Falcons. If your machine budget is closer to $3,500, then the $700 you save on a Threadripper represents a much larger part of the budget.

Conclusion

Looked at in a core-vs.-core battle without considering price, Intel's Core i9-7960X leads the way. It gives you great performance at light-duty applications and generally can't be touched by the Threadripper 1950X in heavy-duty applications, either. In a lot of the tests we ran, we were actually surprised Core i9 ran away from Threadripper so easily.

That said, it's pretty hard to ignore price when you're spending your own money on a build. Our opinion hasn't changed for Threadripper: It is absolutely the best you can get for the price, a spectacular deal. But price aside, in a 16-vs.-16 battle, Core i9 is the winner.

Comments

roadkill612 said: This is the correct answer. Zen is disproportionately gimped by the lesser ram clock in the comparison, as stated.TR is comfortable with ~3000 ram clock even if its not stock, so that would have been better, but its a crap review anyway. Best ignored.It would be far wiser to focus on utilising the 100x faster storage speed improvements on offer in relativelyy recent times fom the latest nvme ssds in raid, than on piddling increments in cpu speeds.The best performance you can buy is inevitably whats for sale next year, and the more you spend now, the longer you must defer availing yourself of future improvements.This especially relevant here, as AMD mobos tend to be supported for years, and simple future drop in cpu upgrades are a very real option.

scienceomatica said: False, the important difference can be noticed only with specific tests, and with a large difference in the operating frequency of RAM, here is a small difference to make it noticeable.

scienceomatica said: Something else I wanted to say, you misunderstood, I said that tests that were multithread challenging, the difference was even greater in favor of Intel.

scienceomatica said: This is something else. Anyway, what is a purpose to have ultra-fast data storage, unless you have an interface that will be able to operate these data at the same time and at the another data at a higher speed.

scienceomatica said: I agree with you, but you do not have to buy a laptop, it's much more interesting to build a good gaming system based on the Ryzen platform, although here I support a certain superiority of Intel.

Elcideous said: LOL

Falcuk said: Oh dear :( lazy journalism and clearly someone who doesn't know how to build an AMD rig correctly.2400mhz ram on the Threadripper while Intel gets 3000mhz? Oh dear, deliberately handycapping or just ignorance?A quick glance around the internet shows you AMD chips scale off Ram speed, re do those tests with 3000mhz Ram, and Raid on the AMD rig and then we can talk.Until then you have zero credibility and are just another Intel shill hidden by your end disclaimer of "oh but we still recommend AMD"Proper lolworthy at best

David Thiel said: It's been over 2 weeks since AMD has had RAID available on Threadripper (with no dongle or additional cost) and how about 60 vs 44 PCIe lanes advantage... In time I expect 3200 MT/s (it's not mhz) and faster memory to be available... So stay tuned

Paul17041993 said: false, the CPU will always be bound to how fast data can be copied to and from the RAM, even when it comes to ultra-light loops as the OS needs to schedule thousands of other threads to run as well.

scienceomatica said: The operational frequency of the RAM memory can not make any special difference here in this type of test. This is about essential differences in processor performance. The difference would be even greater if a number of tests were used that were able to use all processor cores.

EveryoneHasAnOpinion said: Yes, it can, and it does. Not sure what leads you to believe otherwise scienceomatica . http://www.guru3d.com/artic... Guru3D did some testing a while back, and I've seen these results replicated elsewhere. Some differences are more dramatic than others, but almost every benchmark reflects some kind of difference.

Sawyer Bass said: It quite literally seems like the only reason thus guy is comparing two systems is because the $700 difference between the CPUs looks medium and not outright insane like it would if not factored into a build that costs more than any normal person would pay. Everything besides the CPUs are just one huge red herring. There's no non CPU benchmarks, so none of it really matters.To sum it up: The article points out that people paying out of their ass for the unnecessary 5% way off the value chart will like the I9, just like they'd like to pay $2400 for two titan pascals, which in a professional compute side could be matched by $1200 via two Vega 64s.How is this news?

gimpeverydayvidia said: I wish to know how many watts difference between the two chips. Maybe 100w when loaded.

Paul17041993 said: pretty sure the intel system uses a _lot_ more due to the high clocks it runs at, that and intel chips tend to surpass their TPD at stock on a regular basis...

Fleetwood said: Ehhh, flawed tests. Until you make actual apples to apples comparison, this is invalid results.

meh... said: That's a terrible comparison. Please adjust the test systems appropriately, and then we'll talk.

shakum said: AMD wins. With the price difference you can add a whole extra GPU or 100GE interfaces, where the Intel would be bottlenecked at 40 PCIe lanes. Also the Asus BIOS had an incorrect default setting that sets all Intel's cores at the turbo frequency. Not sure if that's a factor here but overall a pretty lousy review.

Mercurious1 said: You are missing the point. Even if RAM is kept at the same speed the impact concern is not on the RAM transfer rate it is on the affect this has on the Threadripper's Infinity Fabric. The RAM speed sets the Infinity Fabric speed which sets the transfer rate between CPU cores as well as the RAM. So faster RAM will make the Intel system faster but will vastly speed up the entire Threadripper CPU.

scienceomatica said: Exactly as I wanted to say at the beginning, If you notice the difference in some tests, there is not even a difference of 1.1 ghz RAM. The biggest difference is when the processor is overclocked or in the case of specific games that realize the improvement of the high frequency of the RAM memory. After all, even in cases where there is a difference, it does not exceed 8-9%.

Paul17041993 said: nope, because regardless of the amount of actual data that has to be copied over time, a fixed buffer is copied over with a fixed latency. The higher the clocks the lower the latency until you reach the peak of diminishing return (physical copper resonant limit on the PCB, resulting in large timing increases over clock).The physical buffer limit per dimm is 64bit, so for these processors the total width is 256bit, as such single load and store operations between 1 to 32 bytes in size will perform the same, but if you were to do 32 single byte load's it should scale to 32 provided you haven't hit the CPU core ALU and memory controller limits.Now, adding to that as well, the AMD processor differs in that it has a multi-layer memory fabric that runs at a multiple of the RAM clock, thus the RAM clock will have an even more profound effect on cache synchronisation performance between cores, clusters, dies and the RAM itself, the higher the clocks the higher the potential IPC to the CPU base clock.

satish chilakamarri said: sir...i want to buy new system for the purpose of 3D animation and vfx composing purpose...could you pls suggest me the good configuration better equal or better than i7 8th generation 8700k wih supporting mother board and better graphic card...as i am going buy it with bank loan below 200,000 rupees in indian currency value

John Aldridge said: Get a Ryzen based system, such as an overclocked Ryzen 7 1700, with fast RAM such as Ballistix Sport LT 2666 (which overclocks to around 3000 - 3200 Mhz). If you can wait a couple of months, new Ryzen CPU's are coming out that will offer better performance for about the same price.

John Aldridge said: What an embarrassing article. Does the author even understand why RAM speed is important on Ryzen systems, or was the system just deliberately gimped?

Elsewhere on IDG sites

Read Next...