Professional Performance: Windows

Agisoft Photoscan – 2D to 3D Image Manipulation: link

Agisoft Photoscan creates 3D models from 2D images, a process which is very computationally expensive. The algorithm is split into four distinct phases, and different phases of the model reconstruction require either fast memory, fast IPC, more cores, or even OpenCL compute devices to hand. Agisoft supplied us with a special version of the software to script the process, where we take 50 images of a stately home and convert it into a medium quality model. This benchmark typically takes around 15-20 minutes on a high end PC on the CPU alone, with GPUs reducing the time.

Agisoft PhotoScan Benchmark - Total Time

The presence of Crystal Well had a small effect on Photoscan, occurring mostly in the second phase of the calculation which is the one that also has an option to enable the GPU, indicating that memory bandwidth is an potential limitation in that segment.

Cinebench R15

Cinebench is a benchmark based around Cinema 4D, and is fairly well known among enthusiasts for stressing the CPU for a provided workload. Results are given as a score, where higher is better.

Cinebench R15 - Single Threaded

Cinebench R15 - Multi-Threaded

Cinebench is a historically CPU-limited benchmark, and the results show this again here. The fact that the 3.6GHz Broadwell-based i5-5675C performs so closely to the 3.9GHz Haswell-based i5-4690 is a promising sign here, as it means that despite being a mere "tick" in Intel's development efforts, there are tangible IPC increases on the desktop from Broadwell.

HandBrake v0.9.9: link

For HandBrake, we take two videos (a 2h20 640x266 DVD rip and a 10min double UHD 3840x4320 animation short) and convert them to x264 format in an MP4 container.  Results are given in terms of the frames per second processed, and HandBrake uses as many threads as possible.

HandBrake v0.9.9 LQ Film

HandBrake v0.9.9 2x4K

While no obvious improvement was seen in the low quality conversion, the double UHD conversion put the i7 above what was otherwise expected.

Hybrid x265

Hybrid is a new benchmark, where we take a 4K 1500 frame video and convert it into an x265 format without audio. Results are given in frames per second.

Hybrid x265, 4K Video

Unlike the Handbrake H.264 tests, the Hybrid x265 tests show a clear uptick in performance on the Broadwell processors. It is not fast enough to catch the i7-4790K and its 4.4GHz turbo clockspeed, but we see the i5-5675C shoot well past the i5-4690 despite the clockspeed deficit. Whether this is due to Broadwell architecture enhancements, Crystal Well acting as an L4 cache, or a combination of the two is difficult to determine, but the end result is substantial.

Office and Web Performance Professional Performance: Linux
Comments Locked

196 Comments

View All Comments

  • MrSpadge - Tuesday, June 2, 2015 - link

    Simply use something representative of the current situation. Not old numbers which may be totally meaningless today. In Europe we have simple price comparison engines like geizhals.eu where it's really easy to find typical prices. Just exclude obvious outliers and cheap products not yet deliverable and voila, you've got the current street price.
  • nathanddrews - Tuesday, June 2, 2015 - link

    In Europe? You mean on the Internet? LOL

    There are tons of price comparison websites, but why should AT take the time and be responsible for tracking down pricing when we can all do that in our own areas or from our favorite retailers? They don't know where I like to shop or what currency I use, so it seems like a waste of their time. I'd much rather get quality performance analyses on a more regular basis than have them worry about updating price indexes. Who knows? Maybe their new parent company can do that for them off to the side or something?
  • MrSpadge - Wednesday, June 3, 2015 - link

    I never see people from the US referring to them. They seem to just use Newegg or Amazon. And getting prices for European shops won't do AT any good, as they're mainly writing for the US.

    And AT has to look up the launch prices of the hardware anyway when they write a review. How much more time would it take to instead look up the current price in a comparison engine? Again, I'm not talking about updating prices dynamically.

    I they're not doing this you always get comments like "who in their right mind would buy x? Vendor y must be totally stupid to keep offering this". Simply because the launch price is far higher than the current price.
  • Senpuu - Wednesday, June 3, 2015 - link

    Why should AT take the time, you asked? Well, why should they list a price at all then? Hell, why provide any information to the reader beyond specs and performance metrics? Why even talk about the market at all? There is obviously value to be had in doing so and it comes down to where you draw the line. Whereas you would rather they not 'waste their time', I would rather not waste mine by having to question whether a product is being valued near current market price or some esoteric launch price, and then being forced to google multiple things myself to get a feel for 'real world' prices. No, the price they come to will likely not tell me the exact total of the item in question at whatever preferred retailer a reader happens to use, but it will probably be within 5-10% of that value, which is highly useful for at-a-glance comparisons and understanding where something sits in a market segment.

    We're not talking about a large amount of effort here, but I'd rather AT do it than myself; it's less effort for them and it benefits a large portion of their readers. Simply provide a disclaimer about the methods used to gather the data as well as a liability warning, and everyone's happy.
  • Thud2 - Saturday, June 13, 2015 - link

    Very good point.
  • yannigr2 - Wednesday, June 3, 2015 - link

    There are official price cuts and so you have new OFFICIAL pricing that it is fair to put in the charts. If the launch price of 7850K was $500 and the last official price was $100, wouldn't be the above charts completely misleading? People do have a price/performance ratio in their minds when looking at these charts. In fact for 90% that's the biggest parameter when looking at those charts. And those charts LIE exactly there.
  • manifestation88method - Sunday, September 27, 2020 - link

    Nice post https://discoversoulpath.com/
  • yannigr2 - Wednesday, June 3, 2015 - link

    You can always take the last OFFICIAL price, but nevermind. It's AMD's pricing that it is wrong anyway. Who cares about poor poor AMD?
  • Gothmoth - Tuesday, June 2, 2015 - link

    intel is sitting on it´s laurels because there is no competition.
    AMD is no competition for poweruser.

    users want broadwell..mhm.. aha....

    i am the only one who wants intel to make a fast 6 (or better 8) core system without integrated graphics, that runs not to hot and does not cost a fortune?

    can´t we have such a CPU for 500-600 euro?

    ok then i stick to my OC ivy bridge for a few more years.. and you intel can complain about declining sales.
  • MrSpadge - Tuesday, June 2, 2015 - link

    That's exactly what i7-5820K is for. If it consumes too much power for your taste - well, that's simply the price you have to pay for more cores.

Log in

Don't have an account? Sign up now