Office Performance: Extreme Editions

The dynamics of CPU Turbo modes, both Intel and AMD, can cause concern during environments with a variable threaded workload. There is also an added issue of the motherboard remaining consistent, depending on how the motherboard manufacturer wants to add in their own boosting technologies over the ones that Intel would prefer they used. In order to remain consistent, we implement an OS-level unique high-performance mode on all the CPUs we test which should override any motherboard manufacturer performance mode.

All of our benchmark results can also be found in our benchmark engine, Bench.

Dolphin Benchmark: link

Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that raytraces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU. Results are given in minutes, where the Wii itself scores 17.53 minutes.

Dolphin Emulation Benchmark

WinRAR 5.0.1: link

Our WinRAR test from 2013 is updated to the latest version of WinRAR at the start of 2014. We compress a set of 2867 files across 320 folders totaling 1.52 GB in size – 95% of these files are small typical website files, and the rest (90% of the size) are small 30 second 720p videos.

WinRAR 5.01, 2867 files, 1.52 GB

3D Particle Movement

3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins in the single thread version, whereas the multithread version has to handle the threads and loves more cores.

3D Particle Movement: Single Threaded

3D Particle Movement: MultiThreaded

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

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

The Market, X99 Refresh and our Test Setup Office and Web Performance
Comments Locked

205 Comments

View All Comments

  • redfirebird15 - Tuesday, May 31, 2016 - link

    There is data in the bench for 1070 and 1080 founders editions. The 1070 is on par with the 980ti, and the 1080 beats it in all categories. Review complete.
  • HOOfan 1 - Tuesday, May 31, 2016 - link

    I imagine they are getting more clicks without it being posted, than they would with it being posted.

    Once it is posted, people will read it and move on. Now people have to stop by every day to ask "are they finally done yet?"
  • Impulses - Tuesday, May 31, 2016 - link

    I get the impatience, even tho there's plenty of other places with decent reviews, but the aggressive and entitled attitude is a little bizarre. You can't every buy the cards right now, and you'd be silly to overpay for a Founder's already, so why are you stressing so much and spamming every other article about it?
  • SkiBum1207 - Tuesday, May 31, 2016 - link

    Good quality reporting and reviewing takes a TON of time. Doing benches aren't as simple as firing up a few runs of 3DMark and calling it a day. Then on top of that, there's the analysis, conversations with the manufacturer to clear up any issues, and writing it in clear and concise prose.

    That's not easy to do. You can get raw benchmarks anywhere online, but getting actual deep analysis by people who actually understand their respective fields? That is hard to find.

    Anandtech has always had a hallmark of taking their time, doing their research, and not shoving out hacked together reviews/articles. If anything, they have gotten better over time, rather than "used to be better".

    @HOOfan1, that's literally the opposite of how journalism online works. The quantity of people who rapid-refresh a page for a single article is a vast minority in comparison to once an article is published. That's one of the reasons why publish-fast, fact check later publishing has become more prevalent.

    @Ryan - I know things have gotten "noisier" the past 5 or so years on the internet and in the comments, but there are still some absolutely loyal readers which absolutely appreciate the work and detail you put into each article. Thank you, and keep up the amazing work.
  • Eden-K121D - Wednesday, June 1, 2016 - link

    You want a deep dive into pascal read this https://images.nvidia.com/content/pdf/tesla/whitep...
  • HOOfan 1 - Wednesday, June 1, 2016 - link

    Plenty of other sites have given a lot more than benchmarks. Maybe not as much as a typical anandtech article, but certainly much more than just "raw benchmarks".

    Is George RR Martin writing graphics card reviews on the side?

    Anandtech doesn't owe us anything, but I would say the fact that people are frustrated that there is no full review yet shows they are loyal readers. If they weren't loyal readers, they just wouldn't care.
  • HollyDOL - Tuesday, May 31, 2016 - link

    Ouch, this definitely puts high perf line both out of my reach and interest.
  • jabber - Tuesday, May 31, 2016 - link

    Glad I didn't bother waiting when I bought the 5820k last month.
  • getho - Tuesday, May 31, 2016 - link

    Bonkers. I was holding out for this, but was forced to replace my 1366 system this year (and went with 5820). THere is no way i would've contemplated dropping $1700 on a CPU. If it was twice as fast, maybe. Even at $999 i think i'd look at dual xeons - and probably second hand at that.
  • adamod - Wednesday, June 1, 2016 - link

    ive got an hp z600 with dual x5660's that consistently run at 3.1ghz al cores at 100 percent load...i love it....cheap r9 280x in there and a pair of ssds and its prety damn quick.....graphic card is older and kinda sucks but it DOES play crysis at 1080P which is, well just ok.....point is i plan to get a 1070 for it and i dont expect i will need to upgrade for another 5 years for gaming and CAD work that i do

Log in

Don't have an account? Sign up now