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.

x264 Benchmark

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 LIVA X is better than the LIVA, but loses out to the quad-core solution in the ZBOX CI320 nano.

Video Encoding - x264 5.0 - Pass 1

Video Encoding - x264 5.0 - Pass 2

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 MIPS ratings when utilizing all the available threads.

7-Zip LZMA Compression Benchmark

7-Zip LZMA Decompression Benchmark

TrueCrypt

As businesses (and even home consumers) become more security conscious, the importance of encryption can't be overstated. CPUs supporting the AES-NI instruction for accelerating the encryption and decryption processes have, till now, been the higher end SKUs. However, with Avoton and Rangeley, even the lowly Atom series has gained support for AES-NI. Unfortunately, the Celeron N2808 doesn't support AES-NI. TrueCrypt, a popular open-source disk encryption program can take advantage of the AES-NI capabilities. Its 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 ECS LIVA X and how it would compare with other select PCs. This is a purely CPU feature / clock speed based test.

TrueCrypt 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). 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.

Agisoft PhotoScan Benchmark - Stage 1

Agisoft PhotoScan Benchmark - Stage 2

Agisoft PhotoScan Benchmark - Stage 3

Agisoft PhotoScan Benchmark - Stage 4

Dolphin Emulator

Wrapping up our application benchmark numbers is the Dolphin Emulator benchmark mode results. This is again a test of the CPU capabilities, and the LIVA X is better than the LIVA as expected. Surprisingly, the performance of the ZBOX CI320 nano took a hit in this benchmark, and the LIVA X surprisingly pulled ahead.

Dolphin Emulator Benchmark

Performance Metrics - I Networking and Storage Performance
Comments Locked

35 Comments

View All Comments

  • ozzuneoj86 - Saturday, January 17, 2015 - link

    Seems a bit expensive for its capabilities. A 1.58Ghz Bay Trail is pretty slow for a non-mobile device.
  • ganeshts - Saturday, January 17, 2015 - link

    They run the CPU at 2.25 GHz (max. turbo speed) throughout the time the CPU is loaded. At this point of time, CPUs with such clocks are more than enough for thin-clients and basic browsing / word-processing [ well, that is what the market reception to the original ECS LIVA signified to ECS :) ]

    In the end, it is all a matter of 'horses for courses' - what fits the requirements of one person might be an overkill for someone else (isn't that why tablet PC sales have caused a decline in shipment of low-end notebooks / PCs?)
  • ozzuneoj86 - Saturday, January 17, 2015 - link

    I see, I missed that about it running at its max turbo since it isn't limited thermally.

    I guess I just have trouble picturing the target market being anyone who actually knows what they are getting vs. what they need. Most of the places that I've seen thin clients used could easily just use a small ITX-sized desktop PC that is significantly faster, and (as is the case with this LIVA X) you generally pay a price premium for a thin client sized system. When you factor in the OS price, it seems unlikely that cost has anything to do with the purchase of a system like this, so that leaves size as the only real reason to get one.

    My workplace replaced several Core 2 based itx-sized HP desktops a few years ago with these awful little WYSE thin clients. Everything takes longer, runs slower and now there is a tiny bit more desktop space for people to clutter paperwork that shoudn't be left out in the first place. I'm sure there will be some power savings, but it can't be much in relation to the cost of installing a bunch of new equipment, and they are already at their limit as far as capabilities. I give it another year before we have some new application that is too much for them to handle.

    Obviously this LIVA system is faster, but it just doesn't seem like that many places are so constrained for space that PCs of this size are actually necessary, and for those that are, there are cheaper and faster alternatives, even at this price point (mostly due to the OS not being included).
  • kgh00007 - Saturday, January 17, 2015 - link

    They need to sell a Windows 8.1 with Bing edition of these, the windows Licence increases the cost of the device by 1.5 times!!

    That's the biggest barrier to these cheaper mini PC's for me and for recommending them to anyone like family members!
  • Teknobug - Saturday, January 17, 2015 - link

    hmm only dual core? I've been liking those Bay Trail Z37**'s.
  • powerarmour - Saturday, January 17, 2015 - link

    If a 59'C case temp isn't hot to touch, you probably need to visit the doctor!, 100'C core temps are ridiculous also, terrible design.
  • ganeshts - Saturday, January 17, 2015 - link

    The Zotac C-series with the Core i5-Y CPUs had chassis temperatures of the order of 75C. This is definitely much better.

    As for the 96 C core temp prior to throttling, there was a thermal pad placement issue in the media review samples. Seeing how this is similar to LIVA in terms of CPU performance and the fact that the material used for thermal protection is far superior, I have no doubt the units reaching the end user will have much lower core temperatures under *power virus* loads.
  • kmmatney - Sunday, January 18, 2015 - link

    The temp is running furmark and Prime95 at the same time, which is a way higher load than normal. I've had computers that would crash while running that test, but were otherwise rock stable no matter what else I did.
  • Oxford Guy - Monday, January 19, 2015 - link

    Exactly. Who is ever going to use one of these for anything like that sort of load. It's bogus.
  • BrokenCrayons - Tuesday, January 20, 2015 - link

    I think the point of including an unrealistic scenario like furmark + prime95 is to stress the system in a way that induces a worst possible case situation. While most end users won't ever have that sort of thermal load on their hardware, doing this kind of testing in a review exposes potential flaws that wouldn't otherwise be discovered. I'd much rather someone does that kinda thing for me and uncovers a problem than having to figure it out for myself after I've made a purchase and have put it to use.

Log in

Don't have an account? Sign up now