Time Spy Extreme: How Does Hardware Stand Up To The New 4K DX12 Tests?

Oct 4, 2017

Futuremark has taken note of the recent GPU and CPU launches and responded with finally bringing their updated Time Spy Extreme 4k DX12 test to the public on October 11 this year so you can pound your hardware as well.  We’ve got an early look at the new update to the test and wanted to share the updated features.  We will also be looking at early performance on today’s drivers.  Just in case anyone is curious, this will be a FREE update for existing Advanced and Professional license.   But only if purchased after July 14, 2016 otherwise it can be added with the Time Spy Upgrade.

What’s Updated

The Graphics portion of the test is a more stressful version of the Time Spy benchmark by cranking the resolution up from 1440p to 4K.  The CPU portion has seen the biggest overhaul and is completely different to take advantage of newer multi-core CPUs from Intel and AMD.

Related Futuremark’s 3DMark Portal Royal, The First Official Ray Tracing Benchmark Now Available

In 2017, both AMD and Intel introduced new processors with more cores than
had ever been seen in a consumer-level CPU before.
The Time Spy CPU test does not scale well on processors with 10 or more
threads. It simply doesn’t have enough workload for the large-scale
parallelization that high-end CPUs provide. A new test is needed.
Enhanced test design
The Time Spy Extreme CPU test also features a combination of physics
computations and custom simulations, but it is three times more demanding
than the Time Spy CPU test.
Adding more simulation requires more visualization, however, which can make
rendering the bottleneck in some cases. This issue was solved by changing the
metric for the test.
Instead of calculating the time taken to execute an entire frame, in the
Extreme CPU test we only measure the time taken to complete the simulation
work. The rendering work in each frame is done before the simulation and
doesn’t affect the score.
The test metric is average simulation time per frame reported in milliseconds.
Unlike frame rate, with this metric a lower number means better performance.

-3DMark Technical Guide


Test System and Results

The bulk of the GPU testing was done on our X370 Test Bench, we found no more than 1% variance between the Graphics Scores or the CPU Score regardless of CPU and GPU configuration. We have included the specifications of the X99 Test Bench as well since it was used to pull a CPU comparison. In addition to just the scores we also included charts showing the frames per second for each of the two runs.

X370 Test Bench

CPU Ryzen 7 1700 3.9GHz
Memory 16GB G.Skill Flare X DDR4 3200
Motherboard MSI X370 XPower Gaming Titanium
Storage Adata SU800 128GB
2TB Seagate SSHD
PSU Cooler Master V1200 Platinum

X99 Test System

CPU Intel Core i7 6800k (4.1GHz)
Memory 32GB CORSAIR Vengeance LPX DDR4 2666MHz
Motherboard ASUS X99A-II
Storage Crucial MX100 512GB SSD
Seagate 2TB SSHD
PSU Corsair AX860i

Graphics Cards Tested

GPU Architecture Core Count
Clock Speed Memory Capacity
Memory Speed
NVIDIA GTX 1080 FE Pascal
2560 1607/1733 8GB GDDR5X 10Gbps
NVIDIA GTX 1060 FE 6GB Pascal
1506/1708 6GB GDDR5 8Gbps
RX Vega 64 Liquid Cooled Vega 10 4096 1406/1677 8GB HBM2 945Mbps
XFX RX 480 8GB Polaris 10 2304 1266 8GB GDDR5 8Gbps

Drivers Used

Radeon Settings 17.10.1
GeForce 387.92


Time Spy Extreme Overall and Graphics Score
Time Spy Extreme Average FPS Per Test
Time Spy Extreme CPU Only Score


While we would have liked to deliver more results with even more CPU cores, these are the most we have on hand at the time.  Interesting to see say the least.  The liquid cooled variant of the Radeon RX Vega 64 sure put out a bit more impressive numbers than anticipated.  It’ll be interesting to see if any new drivers come along before the public release that may change the balance now.  We hope to bring more coverage and a full lineup of results from the RX 460 to the GTX 1080ti when the public release hits on October 11.