GIGABYTE GB-BKi7HA-7500 Kaby Lake BRIX Reviewby Ganesh T S on March 16, 2017 8:00 AM EST
Performance Metrics - II
In this section, we mainly look at benchmark modes in programs used on a day-to-day basis, i.e, application performance and not synthetic workloads.
First off, we have some video encoding benchmarks courtesy of x264 HD Benchmark v5.0. This is simply a test of CPU performance. As expected, the Core i7-7500U helps the BRIX come out on top in both passes.
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 MIPS ratings when utilizing all the available threads.
As businesses (and even home consumers) become more security conscious, the importance of encryption can't be overstated. CPUs supporting the AES-NI instruction can accelerate the encryption and decryption processes. The Core i7-7500U has AES-NI support. TrueCrypt, a popular open-source disk encryption program can take advantage of this. The TrueCrypt internal benchmark provides some interesting cryptography-related numbers to ponder. In the graph below, we can get an idea of how fast a TrueCrypt volume would behave in the GIGABYTE GB-BKi7HA-7500 and how it would compare with other select PCs. This is a purely CPU feature / clock speed based test. Note that the BRIX can operate at a higher power level for a longer duration compared to other Kaby Lake UCFF PCs. That explains why the Cubi2-005B comes behind the GB-BKi7HA-7500 in this test despite sporting the same processor.
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). The benchmark takes around 50 photographs and does four stages of computation:
- Stage 1: Align Photographs
- 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, others multithreaded, and some use GPUs, it is interesting to record the effects of CPU generations, speeds, number of cores, DRAM parameters and the GPU using this software.
Workloads that stress the CPU for long durations like Photoscan lower the effectiveness of the BRIX configuration. While the initial higher power budget helps the BRIX come out on top in the first three stages, we find that the MSI Cubi2-005B catches up in Stage 4 and starts delivering similar performance.
Wrapping up our application benchmark numbers is the Dolphin Emulator benchmark mode results. This is again a test of the CPU capabilities, and the BRIX easily comes out on top amongst the considered PCs.
Post Your CommentPlease log in or sign up to comment.
View All Comments
HomeworldFound - Friday, March 17, 2017 - linkI wish 3D were better, I was one of those people that couldn't see the effect. The moment I looked at a 3D screen my eyes would hurt and my brain just felt like I'd been hit in the face.
mooninite - Thursday, March 16, 2017 - linkIntel is so cheap in that they don't want to pay for the HDMI 2 license... What will it take for them to bite the bullet and do it? Even AMD's APUs support HDMI 2... SAD!
faiakes - Thursday, March 16, 2017 - linkThe HTPC playback tables are somewhat misleading.
Surely the MPC-HC results are with MadVR enhancements enabled, while the Kodi one is simple playback.
You're giving the impression that MPC-HC is less capable of upscaling than Kodi is.
BrokenCrayons - Thursday, March 16, 2017 - linkI really like the idea of the NUC form factor. For non-gaming or very casual gaming, they're really a nice form factor. Low power consumption is always a bonus and, specifically the BRIX, passing AT's pretty demanding thermal testing is good too. I just wish they were a little less expensive. The same dollars can purchase a pretty powerful desktop in a MicroATX case that really isn't _that_ much bigger.
Stochastic - Thursday, March 16, 2017 - linkYeah, high price is the Achilles' heel that would keep me from buying one.
Also, for my purposes I find Chromecast/Chromecast TV to be sufficient for my TV watching needs, so I couldn't justify purchasing an HTPC.
TheinsanegamerN - Monday, March 20, 2017 - linkYou can easily fit 10+ NUCs into a single MicroATX case. Calling it "not that much bigger" is like saying a semi truck is only a bit bigger then a ford fiesta.
BrokenCrayons - Monday, March 20, 2017 - linkYou're right, of course. I was viewing it relative to a desk and the typical number of cubic feet/meters in an office or a bedroom. On those scales, the difference is minimal, but if you just compare them to one another without factoring in the size of a human or the interior rooms a human occupies, it does seem a lot bigger. Though maybe adding the external power supply into consideration to be completely fair (mATX PSUs are internal after all) would reduce the NUC to mATX number to ~5-6.
Shadowmaster625 - Thursday, March 16, 2017 - linkWhy is the Cubi2 so much more efficient?
MrSpadge - Thursday, March 16, 2017 - link"Netflix streaming evaluation was done using the Windows 10 Netflix app. Manual stream selection is available (Ctrl-Alt-Shift-S) and debug information / statistics can also be viewed (Ctrl-Alt-Shift-D)"
... when "Ctrl+S" just doesn't cut it! Remindes me of emacs and its weird many-key shortcuts.
bryanb - Thursday, March 16, 2017 - linkTwo things I wished these NUC-form-factor devices would fix:
1) Integrate the power brick. Just look at the picture of this box next to its power adapter - you always end up with a tangle of cords and small boxes that take *more* room than an equivalent integrated device. Apple was able to do this on their Mac mini, so I know it is possible.
2) Ditch these loud blower fans that exhaust out a tiny hole in the side and just put a nice big 80mm-120mm fan on the top. Heck, the entire top surface can be a perforated. Plus, the large fan will likely be much slower moving and quieter.