Gaming Performance

As I mentioned earlier, under OS X games have to specifically be written to use both GPUs in the new Mac Pro. Under Windows however it's just a matter of enabling CrossFire X. I ran the new Mac Pro with dual FirePro D700s through a few of Ryan's 2014 GPU test suite games. The key comparison here is AMD's Radeon R9 280X CF. I've put all of the relevent information about the differences between the GPUs in the table below:

Mac Pro (Late 2013) GPU Comparison
  AMD Radeon R9 280X AMD FirePro D700
SPs 2048 2048
GPU Clock (base) 850MHz 650MHz
GPU Clock (boost) 1000MHz 850MHz
Single Precision GFLOPS 4096 GFLOPS 3481 GFLOPS
Texture Units 128 128
ROPs 32 32
Transistor Count 4.3 Billion 4.3 Billion
Memory Interface 384-bit GDDR5 384-bit GDDR5
Memory Datarate 6000MHz 5480MHz
Peak GPU Memory Bandwidth 288 GB/s 264 GB/s
GPU Memory 3GB 6GB

Depending on thermal conditions the 280X can be as little as 17% faster than the D700 or as much as 30% faster, assuming it's not memory bandwidth limited. In the case of a memory bandwidth limited scenario the gap can shrink to 9%.

All of the results below are using the latest Radeon WHQL drivers at the time of publication (13-12_win7_win8_64_dd_ccc_whql.exe) running 64-bit Windows 8.1. Keep in mind that the comparison cards are all run on our 2014 GPU testbed, which is a 6-core Ivy Bridge E (i7-4960X) running at 4.2GHz. In other words, the other cards will have a definite CPU performance advantage (20 - 30% depending on the number of active cores).

You'll notice that I didn't run anything at 4K for these tests. Remember CrossFire at 4K is still broken on everything but the latest GCN 1.1 hardware from AMD.

Battlefield 3 - 2560x1440 - Ultra Quality + 4x MSAA

Battlefield 3 starts out telling the story I expected to see. A pair of 280Xes ends up being 16% faster than the dual FirePro D700 setup in the Mac Pro. You really start to get an idea of where the Mac Pro's high-end GPU configuration really lands.

Bioshock Infinite - 2560x1440 - Ultra Quality + DDoF

Bioshock ends up at the extreme end of what we'd expect to see between the 280X and D700. I tossed in a score from Bioshock under OS X, which obviously doesn't have CF working and ends up at less than half of the performance of the D700. If you're going to do any heavy 3D gaming, you'll want to do it under Windows still.

Company of Heroes 2 - 2560x1440 - Maximum Quality + Med. AA

Not all games will scale well across multiple GPUs: Company of Heroes 2 is one of them. There's no performance uplift from having two 280Xes and thus the D700 performs like a slower single GPU R9 280X.

Company of Heroes 2 - Min. Frame Rate - 2560x1440 - Maximum Quality + Med. AA

Metro: Last Light - 2560x1440 - High Quality

Metro is the one outlier in our test suite. Although CrossFire is clearly working under Windows, under Metro the D700 behaves as if it wasn't. I'm not sure what's going on here, but this does serve as a reminder that relying on multi-GPU setups to increase performance does come with a handful of these weird cases - particularly if you're using non-standard GPU configurations.

GPU Choices 4K Support & The 4K Experience
POST A COMMENT

269 Comments

View All Comments

  • Ppietra - Friday, January 03, 2014 - link

    An object with black color only implies that it absorbs visible light. Thermal radiation is mostly infrared not visible light, so being black has no consequence since there is nothing emitting visible radiation internally. Externally the surface is very reflective so no problem there either - not that there would be one it wasn’t reflective Reply
  • cosmotic - Tuesday, December 31, 2013 - link

    It would be nice to see storage performance of the Mac Pro SSD against RAID on mechanical disks and SSD disks from a previous Mac Pro model. Reply
  • cosmotic - Tuesday, December 31, 2013 - link

    Including IOPS Reply
  • acrown - Tuesday, December 31, 2013 - link

    The early 2008 Mac Pro does not support hyperthreadimg as your charts indicate. Of course I could just be doing something wrong with mine... Reply
  • acrown - Tuesday, December 31, 2013 - link

    Stupid onscreen keyboard. I meant hyperthreading of course. Reply
  • Anand Lal Shimpi - Tuesday, December 31, 2013 - link

    Whoops, you're right! Fixed :) Reply
  • acrown - Tuesday, December 31, 2013 - link

    Great article by the way. I'm so on the fence about whether to get one to replace my current Mac Pro.

    The read is tempting me more and more though...
    Reply
  • ananduser - Tuesday, December 31, 2013 - link

    It's actually simple, it's the best OSX workstation for seemingly only Apple software that actually makes full use of the GPU setup.

    If your workflow revolves exclusively around FCX, it is the only workstation you'll need. If you're an average consumer wanting a powerful OSX machine you'd better get a consumer oriented imac.

    PS: No need for me to mention that if you'll need CUDA and Windows then it's a bad buy.
    Reply
  • akdj - Wednesday, January 01, 2014 - link

    I'd expect OpenCL to become more and more and MORE ubiquitous as time marches on and Moore's law in relation to CPU slows...and more computing can be taken care of via screaming fast GPUs. Again. Early adopters. But CUDA/Windows options are aplenty. Just more expensive and without twin GPUs. Without PCIe storage. And.....oh yeah, their Windows boxes. At least with the MP you can run Windows...and perhaps, as we saw Adobe so quickly do with HiDPI support post rMBP release (along with hundreds of other apps and software companies)---hopefully Windows 8.2/9.x realizes the more significant 'all around' gains utilizing OpenCL (nVidia too?) than the very, VERY select software titles that take advantage of CUDA....and when they do, it's primal in comparison to what OpenCL opens the doors for. Literally. Everything Reply
  • moppop - Wednesday, January 01, 2014 - link

    Considering CUDA is a GPGPU API there's no door that OpenCL opens that CUDA can't do...in fact, you could say that CUDA opens more doors on an Nvidia GPU. Nvidia also supports OpenCL since it was among the parties to help expand the api spec, but make no mistake, their flagship is CUDA.

    Aside from shunning Nvidia to market-segments whose software will be at least CUDA-accelerated (if there's GPU accelaration at all), my main beef with the Mac Pro, however, is that there are artificial limits placed by the design. Namely 1 CPU socket and only 4 DIMM slots.

    For VFX/3DCG pros, the reality is that GPU rendering simply isn't there yet. Your PRMan, Mental Ray, V-Ray (not real-time V-Ray), Arnold, and Mantra renderers are still very much in the CPU world. When professionals buy a machine they need it to work now, and not 5 years from now. While the Mac Pro certainly appeals to portions of the pro market-segment, it was a simply foolish reason to castrate the Mac Pro.
    Reply

Log in

Don't have an account? Sign up now