Scientific and Synthetic Benchmarks

2D to 3D Rendering Agisoft PhotoScan v1.0: 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

Console Emulation Dolphin Benchmark: link

At the start of 2014 I was emailed with a link to a new emulation benchmark based on the Dolphin Emulator. The issue with emulators tends to be two-fold: game licensing and raw CPU power required for the emulation. As a result, 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; meaning that anything above this is faster than an actual Wii for processing Wii code, albeit emulated.

Dolphin Benchmark

Point Calculations – 3D Movement Algorithm Test: link

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

Encryption TrueCrypt v0.7.1a: link

TrueCrypt is an off the shelf open source encryption tool for files and folders. For our test we run the benchmark mode using a 1GB buffer and take the mean result from AES encryption.

TrueCrypt 7.1a AES

Synthetic – 7-Zip 9.2: link

As an open source compression tool, 7-Zip is a popular tool for making sets of files easier to handle and transfer. The software offers up its own benchmark, to which we report the result.

7-Zip MIPS

Real World CPU Benchmarks F1 2013, Bioshock Infinite, Tomb Raider
Comments Locked

44 Comments

View All Comments

  • fteoath64 - Friday, March 21, 2014 - link

    AMD/ATI needs to be very aggressive in lowering the power demands of their gpu. What NV has done in Maxwell should tell them a very important thing. Lowering the power demands means, one can cram more cores into the die, hence it will boost performance. There is so much one can cram into a specific node-technology but the power demands meaning heat dissipation is going to be a real issue that is hard to solve.
    With the latest R9 series running at such high heat and high power demands, it is going to impossible to cram even half that performance into an APU without resorting to water cooling so the challenge is huge for AMD to tackle. I hope they can make headway into power optimization so that we can get more serious APU chips with powerful gpus for once and help move the industry along.
  • Ammohunt - Thursday, March 20, 2014 - link

    cpu performance is one thing getting a stable glitch free windows system has always been the true challenge. I had never seen a Win7 BSOD until i ran an FX-6100 AMD Build which i promptly replaced with an intel rig. As a server it runs linux like a champ though.
  • Demiurge - Friday, March 21, 2014 - link

    I have multiple laptops, all Intel based, at work that BSOD Win7. It isn't the CPU, it's the drivers. I know because mine doesn't crash anymore after updating the drivers. I'm pretty sure it isn't the CPU that was the weak point of failure in most problems because the CPU is one of the few things that gets tested and validated the most. Not saying it can't happen, but it is far more likely you or the device manufacturers screwed up. Trust me, I own a Creative X-Fi =)... sometimes I don't get sound on reboot. I know the hardware's good there too.
  • MrBungle123 - Friday, March 21, 2014 - link

    I've noticed instability with AMD rigs before and discovered that the issue was that the stock voltage was too low. AMD is always trying to compete from a process node behind so I think they drive the Vcore as low as possible to try and bring down their TDP numbers and as a consequence bring the CPUs to the edge of instability.
  • 0ldman79 - Saturday, March 29, 2014 - link

    Odd.

    I've found that most of my AMD chips can work fine with a little less voltage at stock speeds.

    Of course they don't stay that way, the tech in me overclocks them and gets Cool'n'Quiet working so they idle nice and cool then ramp up when needed.
  • Demiurge - Friday, March 21, 2014 - link

    Not sure why...I see something a little different...

    Tomb Raider is probably very heavily AMD CPU (just assuming relative to the other benchmark performance) optimized because the $200 APU + GTX 770 is actually outperforming (ever so slightly) the $1000 and $320 I7... In the F1 game the exact opposite is happening ~84fps vs ~129fps... from what I see in the other games, it looks like about a -15% typical difference toward the APU just by looking at a high level. That's not bad considering the price/performance ratio.

    The numbers (to me) aren't important as a CPU comparison for the vague remarks I made about suspected optimization, but it does matter if you are comparing the game performance in order to make a decision about which CPU to buy if I play a particular set of games.
  • PUGSRULE! - Monday, August 10, 2015 - link

    As of today 8-10-15 an Intel i7-4960X costs $1,100 versus an AMD A10-7850k that goes for $130. If you have an unlimited budget, yeah go for the Intel. But dollarwise, you cannot do better with the AMD. It's like comparing a Hennessey Venom GT to a Mustang.
  • TETRONG - Wednesday, March 19, 2014 - link

    Hmm, I agree. It's confusing why they keep reviewing and devoting so much time to something that hasn't been viable for a long time. Anyone can compare performance/price and conclude that there is no good AMD buy relative to Intels Core/Xeon lineup. It doesn't sound so bad until you factor in electricity which completely negates anything AMD might otherwise have going for them. Whatever you would save with the cheaper chip would get eaten up by the utilities -
    No thanks
  • tech6 - Wednesday, March 19, 2014 - link

    I think they can be viable at a certain price point. Offering "good enough" performance for office and non-3D gaming computers is AMDs strength and that is where OEMs should be aiming also. Making a $100+ "Extreme" AMD board makes no performance sense at all.
  • bobbozzo - Wednesday, March 19, 2014 - link

    A mini-ITX Kaveri is attractive for HTPC builds, thanks to the excellent integrated graphics.

Log in

Don't have an account? Sign up now