Miscellaneous Performance Metrics

This section looks at some of the other commonly used benchmarks representative of the performance of specific real-world applications.

3D Rendering - CINEBENCH R15

We use CINEBENCH R15 for 3D rendering evaluation. The program provides three benchmark modes - OpenGL, single threaded and multi-threaded. Evaluation of different PC configurations in all three modes provided us the following results. It must be noted that R15 is good enough for the current crop of SFF PCs. Once we start getting 16 cores or more, the shift to more modern versions of CINEBENCH will be made.

3D Rendering - CINEBENCH R15 - Single Thread

3D Rendering - CINEBENCH R15 - Multiple Threads

3D Rendering - CINEBENCH R15 - OpenGL

Except for the OpenGL case, both the single (ST) and multi-threaded (MT) versions bring out Frost Canyon on top. As expected, there is negligible difference in the ST performance of the Bean Canyon and Frost Canyon NUCs, as the CPUs are both based on the same Skylake microarchitecture, with the optimizations allowing for higher clocks getting compensated by the increased core count in the processor.

x265 Benchmark

Next up, we have some video encoding benchmarks using x265 v2.8. The appropriate encoder executable is chosen based on the supported CPU features. In the first case, we encode 600 1080p YUV 4:2:0 frames into a 1080p30 HEVC Main-profile compatible video stream at 1 Mbps and record the average number of frames encoded per second.

Video Encoding - x265 - 1080p

Our second test case is 1200 4K YUV 4:2:0 frames getting encoded into a 4Kp60 HEVC Main10-profile video stream at 35 Mbps. The encoding FPS is recorded.

Video Encoding - x265 - 4K 10-bit

In both cases, the hexa-core nature of Frost Canyon stands in good stead, even enabling it to get a sizable lead over competing systems sporting processors with higher TDPs.


7-Zip is a very effective and efficient compression program, often beating out OpenCL accelerated commercial programs in benchmarks even while using just the CPU power. 7-Zip has a benchmarking program that provides tons of details regarding the underlying CPU's efficiency. In this subsection, we are interested in the compression and decompression rates when utilizing all the available threads for the LZMA algorithm.

7-Zip LZMA Compression Benchmark

7-Zip LZMA Decompression Benchmark

Here, we again see the hexa-core feature enabling Frost Canyon to surpass the performance of systems sporting processors with higher TDPs.

Cryptography Benchmarks

Cryptography has become an indispensable part of our interaction with computing systems. Almost all modern systems have some sort of hardware-acceleration for making cryptographic operations faster and more power efficient. In this sub-section, we look at two different real-world applications that may make use of this acceleration.

BitLocker is a Windows features that encrypts entire disk volumes. While drives that offer encryption capabilities are dealt with using that feature, most legacy systems and external drives have to use the host system implementation. Windows has no direct benchmark for BitLocker. However, we cooked up a BitLocker operation sequence to determine the adeptness of the system at handling BitLocker operations. We start off with a 2.5GB RAM drive in which a 2GB VHD (virtual hard disk) is created. This VHD is then mounted, and BitLocker is enabled on the volume. Once the BitLocker encryption process gets done, BitLocker is disabled. This triggers a decryption process. The times taken to complete the encryption and decryption are recorded. This process is repeated 25 times, and the average of the last 20 iterations is graphed below.

BitLocker Encryption Benchmark

BitLocker Decryption Benchmark

The availability of 6 cores to issue AES-NI operations on enables BitLocker to perform better on the Frost Canyon compared to Bean Canyon, despite the Bean Canyon configuration sporting a much higher performing memory sub-system with a DDR4-3000 SODIMM kit at a lower latency.

Creation of secure archives is best done through the use of AES-256 as the encryption method while password protecting ZIP files. We re-use the benchmark mode of 7-Zip to determine the AES256-CBC encryption and decryption rates using pure software as well as AES-NI. Note that the 7-Zip benchmark uses a 48KB buffer for this purpose.

7-Zip AES256-CBC Encryption Benchmark

7-Zip AES256-CBC Decryption Benchmark

The observations we made for the BitLocker workload work for 7-Zip too. The Ryzen 5 2400G, for some reason, seems to offer much faster / optimized hardware acceleration for certain cryptographic operations, enabling it to be neck-and-neck with the Frost Canyon for AES256-CBC decryption in the above case. Obviously, the TDP difference (65W vs 25W) needs to be taken into account, though it is likely that the Frost Canyon NUC was at turbo-speeds in PL2 for at least the first few iterations of the benchmark.

Yet another cryptography application is secure network communication. OpenSSL can take advantage of the acceleration provided by the host system to make operations faster. It also has a benchmark mode that can use varying buffer sizes. We recorded the processing rate for a 8KB buffer using the hardware-accelerated AES256-CBC-HAC-SHA1 feature.

OpenSSL Encryption Benchmark

OpenSSL Decryption Benchmark

Here, we see the Ryzen 5 2400G completely outperform the Frost Canyon NUC due to better optimization of the workload for the hardware acceleration capabilities offered by the Ryzen processor.

Agisoft Photoscan

Agisoft PhotoScan is a commercial program that converts 2D images into 3D point maps, meshes and textures. The program designers sent us a command line version in order to evaluate the efficiency of various systems that go under our review scanner. The command line version has two benchmark modes, one using the CPU and the other using both the CPU and GPU (via OpenCL). We present the results from our evaluation using the CPU mode only. The benchmark (v1.3) takes 84 photographs and does four stages of computation:

  • Stage 1: Align Photographs (capable of OpenCL acceleration)
  • Stage 2: Build Point Cloud (capable of OpenCL acceleration)
  • Stage 3: Build Mesh
  • Stage 4: Build Textures

We record the time taken for each stage. Since various elements of the software are single threaded, and others multithreaded, it is interesting to record the effects of CPU generations, speeds, number of cores, and DRAM parameters using this software.

Agisoft PhotoScan Benchmark - Stage 1

Agisoft PhotoScan Benchmark - Stage 2

Agisoft PhotoScan Benchmark - Stage 3

Agisoft PhotoScan Benchmark - Stage 4

The hexa-core nature makes the Frost Canyon NUC emerge as the best performer in the Agisoft Photoscan benchmark across all the SFF PCs considered in this review.

Dolphin Emulator

Wrapping up our application benchmark numbers is the new Dolphin Emulator (v5) benchmark mode results. This is again a test of the CPU capabilities.

Dolphin Emulator Benchmark

The benchmark is mostly bound by single-threaded performance, and we do not see much difference between the Bean Canyon and Frost Canyon NUCs in this workload.

UL Benchmarks: PCMark and 3DMark Networking and Storage Performance


View All Comments

  • TheinsanegamerN - Monday, March 2, 2020 - link

    Bleh UHD graphics. Terrible. The previous NUCs had Iris plus GPUs. AMD APU NUCs would dominate these things. Reply
  • drexnx - Monday, March 2, 2020 - link

    looks like the 2 year old 2400G already does, a 4800U would embarrass this Reply
  • timecop1818 - Monday, March 2, 2020 - link

    Yeh, if only AMD had stable/working graphics. Oh, wait... Reply
  • kaidenshi - Tuesday, March 3, 2020 - link

    If only you had something else to troll about. How about some citations to back up your claims? Going on a year with my 2400G APU based system with zero graphics issues and far outperforming any Intel iGPU. There's a reason Intel chose AMD graphics for its Hades Canyon NUC. Reply
  • MenhirMike - Wednesday, March 4, 2020 - link

    I think he might mean the (very real) issues that the RX 5x00 drivers have, like stuttering and random driver crashes. This has been much improved in later drivers, my 5700 XT is running perfectly fine now, but there were definitive issues. That said, those are Navi cards while integrated GPUs (which are applicable here) are using Vega. And initially, there was an issue with at least mobile APUs where AMD didn't offer their own drivers - I got a Ryzen 5 2500U laptop, and for the first year, I had to deal with way outdated drivers from Dell. But AMD finally came around and is now offering first-party drivers.

    So: There were definitive issues, there might still be issues, but it seems that all the big ones are resolved.
  • HStewart - Monday, March 2, 2020 - link

    You got to take in account of the market of this machine, most people do not need high end graphics for games and such. This is also likely use for engineering stuff where graphics is not actually used too much - like a monitor system, or back office systems for services and possibly reports. Reply
  • 29a - Monday, March 2, 2020 - link

    That's still no excuse for Intel's horrible iGPUs. Reply
  • Qasar - Monday, March 2, 2020 - link

    nope.. but hstewart, will keep making excuses for them. sorry hstewart, amds new apus would be for this market, and would probably out perform this by quite a bit. face it, your beloved intel, has lost this round. Reply
  • The_Assimilator - Monday, March 2, 2020 - link

    I strongly doubt that even AMD's latest APUs can idle with a 4K display at under 5W. That power-sipping performance is critical to the market segment these devices are aimed at. Reply
  • evernessince - Tuesday, March 3, 2020 - link

    Well yes if you are comparing desktop APUs vs the mobile chip in this system. If you compare apples to apples though, AMD certainly does have chips capable of idling that low even on the high end: https://www.notebookcheck.net/Lenovo-ThinkPad-T495...

    And that's with last generation Zen+, not Zen 2.

Log in

Don't have an account? Sign up now