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 in our system reviews. 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.

3D Rendering - CINEBENCH R15 - Single Thread

3D Rendering - CINEBENCH R15 - Multiple Threads

3D Rendering - CINEBENCH R15 - OpenGL

The Core i7-8550U's 4C/8T configuration helps the CI660 nano to perform better than even the Skull Canyon NUC in the multi-threaded workload. The single-threaded performance of the configuration is very similar to that of the actively-cooled Kaby Lake NUC (Baby Canyon). That said, the Coffee Lake NUC (Bean Canyon) with its 28W TDP processor easily comes out on top. In the OpenGL case, the systems with Iris Plus Graphics perform better than the CI660 nano. The key takeaway here is that the CI660 nano can easily compete with other actively cooled PCs in terms of performance.

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

The performance in both tests depends on a combination of factors - the processor TDP, as well as the number of available threads. When this combination is taken into account, the 15W TDP Core i7-8550U loses out to almost all other tested combinations - the Skull Canyon NUC has a 45W TDP 4C/8T processor, the Bean Canyon has a 28W TDP 4C/8T processor, the DeskMini 310 has a 65W TDP 4C/4T processor, and the ZBOX MI553 has a 45W 4C/4T processor. The CI660 nano almost matches the performance of the ZBOX MI553 in these workloads.

7-Zip

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

The performance in these workloads tracks what we observed in the SYSmark 2018 and PCMark 10 benchmarks.

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 numbers are closely stacked, with the CI660 nano surpassed only by the Bean Canyon NUC.

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

In this workload, the CI660 nano is in the middle of the pack, but the numbers are very close to each other for the systems with similar number of cores / threads.

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

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 Agisoft numbers are impressive, considering that the CI660 nano is passively cooled.

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

Only the Bean Canyon NUC performs significantly better than the CI660 nano.

Storage Performance

On the storage side, one option would be repetition of our strenuous SSD review tests on the drive(s) in the PC. Fortunately, to avoid that overkill, PCMark 8 has a storage bench where certain common workloads such as loading games and document processing are replayed on the target drive. Results are presented in two forms, one being a benchmark number and the other, a bandwidth figure. We ran the PCMark 8 storage bench on selected PCs and the results are presented below.

Futuremark PCMark 8 Storage Bench - Score

Futuremark PCMark 8 Storage Bench - Bandwidth

One of the drawbacks (if users might want to call it that) of the CI660 nano's platform is the absence of a NVMe SSD slot. Only a single SATA drive is supported, and this reults in an entry in the lower half of the graph for the CI660 nano and its Crucial BX300 SATA SSD. Make no mistake - the BX300 has very good performance for a SATA SSD with its MLC NAND, but, it does come up short against the NVMe SSDs installed in most of the other systems.

UL Benchmarks - PCMark and 3DMark HTPC Credentials - Display Outputs Capabilities
POST A COMMENT

23 Comments

View All Comments

  • jgraham11 - Tuesday, April 16, 2019 - link

    BAPCo's SYSmark 2018 is an application-based benchmark that has been developed by Intel engineers for Intel CPUs and does not truly reflect performance of any real world application by any other chip vendor. The fact that every other chip maker have all abandoned Bapco's boards tell you something. This is a known conflict of interest that degrades Anandtech's credibility by highlighting it. At least in the past the articles, these conflicts were pointed out regarding Bapco's shaky past. Reply
  • Daeros - Tuesday, April 16, 2019 - link

    Anandtech's quality has been on a continuous downward slide, including increasing Intel/Nvidia bias, ever since Anand left. The site looks and sounds like it's written by children now - especially including comments the editorial staff post in comments sections and on twitter. Reply
  • Eris_Floralia - Tuesday, April 16, 2019 - link

    Hey what about my Andrei Reply
  • DigitalFreak - Tuesday, April 16, 2019 - link

    While I would agree that the quality is not near as good as it was when Anand was around, I don't see any bias. Reply
  • PeachNCream - Thursday, April 18, 2019 - link

    Read literally anything written about a Killer NIC. Reply
  • rrinker - Tuesday, April 16, 2019 - link

    Seems like this article only compares Intel systems to other Intel systems - so what's the problem? Other than, of course, this article does not agree with some personal bias of yours, therefore all of Anandtech is now not credible, etc. A little extreme reaction don't you think? But such is the way witht he extremism in EVERYTHING these days. Social media has destroyed any chance for critical thinking. Anandtech does an article that's positive towards Intel, OMG BIASED, They hate AMD. They write a different article that's positive towards an AMD product - OMG BIASED! Why the hate on Intel? Reply
  • Irata - Tuesday, April 16, 2019 - link

    Yup, using a benchmark by Bapco in which no chip company besides Intel seems to have confidence does leave a rather bad taste.
    nVidia, AMD and VIA all left the consortium back in 2011 and prior to that Bapco was found to have modified their benchmarks in a way that favored Intel CPU
    Reply
  • Ryan Smith - Wednesday, April 17, 2019 - link

    SYSmark 2018 is one of several tools we use in this article. It is certainly not the only tool we use, and it's not a tool we use in all situations (e.g. architecture deep dives). Meanwhile for SFF PCs in particular, its power measurement capabilities are pretty handy to have. Plus the only other systems we're comparing it to are all Intel-based anyhow. Reply
  • MDD1963 - Thursday, April 18, 2019 - link

    If BAPCO SYSMark was developed by Intel engineers, this would seem more an issue if/when comparing Intel systems to AMD, and not really an issue when comparing all Intel systems... Reply
  • mammothboy - Tuesday, April 16, 2019 - link

    The Realtec NICs may be a blessing for use with Windows Server (Intel has a nasty habit of not providing drivers for many of their NICs). Having two will let you set up a team there (perhaps to use as a AD/DNS server) or use as a firewall/router (not that I'd use Windows Server for either).

    I've generally had good luck with Realtec with Windows Server and PFSense.
    Reply

Log in

Don't have an account? Sign up now