Office Performance

The dynamics of CPU Turbo modes, both Intel and AMD, can add a wrinkle to testing in 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-threaded 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

Crystal Well doesn’t help much in Dolphin, indicating it is more CPU frequency limited than DRAM/cache limited.

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

WinRAR is our typical benchmark to go to when testing whether DRAM is factor, and the improvements provided by the Crystal Well implementation trump any frequency deficit.

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

3DPM, like Dolphin, is concerned more with CPU frequency than DRAM accesses.

FastStone Image Viewer 4.9

FastStone is the program I use to perform quick or bulk actions on images, such as resizing, adjusting for color and cropping. In our test we take a series of 170 images in various sizes and formats and convert them all into 640x480 .gif files, maintaining the aspect ratio. FastStone does not use multithreading for this test, and results are given in seconds.

FastStone Image Viewer 4.9

Web Benchmarks

On the lower end processors, general usability is a big factor of experience, especially as we move into the HTML5 era of web browsing.  For our web benchmarks, we take four well known tests with Chrome 35 as a consistent browser.

Mozilla Kraken 1.1

Kraken 1.1

WebXPRT

WebXPRT

Google Octane v2

Google Octane v2

In the webtests, the Broadwell-DT CPUs didn’t necessarily take top spot but they are punching above their expected weight for their frequency.

Intel Broadwell Test Setup, Power Consumption Professional Performance: Windows
Comments Locked

196 Comments

View All Comments

  • Zingam - Wednesday, June 3, 2015 - link

    Well, nothing to see here! Move along, sir!

    Where is the Skylake?
  • ryrynz - Wednesday, June 3, 2015 - link

    Ian, what driver was used? Intel just released a new one with some significant performance improvements (15.36.21.4222) Retest?
  • Phartindust - Wednesday, June 3, 2015 - link

    Please fix the graphs for GRID Min frames, or did the A10-7700k really beat everything else by 10fps?
  • unityole - Thursday, June 4, 2015 - link

    "due to time constraint we will save overclocking for part 2" care to explain why both you and tomshardware don't do OC? i have a feeling intel not allowing reviewers to do OC at first for sample, until at least few weeks or even months later.

    can't blame you though, need to continuously get sample from intel.
  • unityole - Thursday, June 4, 2015 - link

    im extremely interested in OC, voltage used, power consumption and also performance is what we're after, before moving onto skylake.
  • Notmyusualid - Thursday, June 4, 2015 - link

    I'll second the request for identical-speed benchmarks too, thanks.
  • albert89 - Thursday, June 4, 2015 - link

    I've got to say I like what Intel has done to its iGPU side of the APU no matter how you read this review it actually doesn't look good for them. Overall Broadwell from these results seems to be between 1.5-3 times more expensive than AMD and if that doesn't both you, then its performance in the games above was between 1.6-6 points ahead while in one game beating AMD by 10 points (not good) while AMD beating Intel by 10 fps (nice). And don't forget we are comparing AMD (28nm) against Intel (14nm) which casts a not so flattering picture of Intel. And need I mention the latency gain over AMD, hardly to write home about by Intel. If your an all round user or a gamer the only thing you'll notice from Broadwell is the hole in your wallet.
  • unityole - Thursday, June 4, 2015 - link

    true that, most people here are for CPU performance though, doesn't hurt to have additional good IGPU in case of discrete dies on you, can still boot without dGPU and iGPU can still do things at 1080p.
  • NvidiaWins - Thursday, June 4, 2015 - link

    Literally no gain over Devils' Canyon.......
  • zodiacfml - Friday, June 5, 2015 - link

    Interesting. I could see a particular niche for this for users needing very good cpu performance and wants occasional gaming that is better than an entry level graphics card. Can't wait for overclocking results.

    I hope prices go down with Skylake's...

Log in

Don't have an account? Sign up now