The Mac Pro Review (Late 2013)
by Anand Lal Shimpi on December 31, 2013 3:18 PM ESTGaming 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 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 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.
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.
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.
267 Comments
View All Comments
Ryan Smith - Tuesday, December 31, 2013 - link
Yes. 1 and 3 are on the same TB controller.JlHADJOE - Tuesday, December 31, 2013 - link
You, sir, are a very hardworking man.Thanks very much for the review, and a happy new year to you.
scribblemonger - Tuesday, December 31, 2013 - link
"The part I haven’t quite figured out yet is how Apple handles DisplayPort functionality. All six Thunderbolt 2 ports are capable of outputting to a display, which means that there’s either a path from the FirePro to each Thunderbolt 2 controller or the PEX 8723 switch also handles DisplayPort switching. It doesn’t really matter from an end user perspective as you can plug a monitor into any port and have it work, it’s more of me wanting to know how it all works."The former is correct.
funwithstuff - Tuesday, December 31, 2013 - link
Could you please share more details of your FCP X benchmarks? I'd like to analyse where the pain points are in for different Macs.funwithstuff - Tuesday, December 31, 2013 - link
And also, a quick typo fix. In the article you say you're testing the iMac 2013 i5-3.4GHz, but the charts all say i7-3.4GHz.macgeeky - Tuesday, June 3, 2014 - link
Anand, which is it: are you testing the iMac Late 2013 i5 or i7?Thanks!
AnTech - Tuesday, December 31, 2013 - link
Apple should bring these to match the Mac Pro:- Thunderbolt 2 matte display (24-inch) 4K and 3D with USB 3 and SD card reader.
- Wired extended keyboard with USB 3 hub built-in.
miahshodan - Tuesday, December 31, 2013 - link
Doesn't having external storage kind of negate the entire clean and small design? I would rather have a larger case with my extra drives in it and no messy cables all over my desk.Gigaplex - Wednesday, January 1, 2014 - link
Yes. Yes it does.nedjinski - Tuesday, December 31, 2013 - link
I guess you're using FCP as the reference for benchmarks because it is mac exclusive. Since most really serious video editor pros have migrated to Premiere it would be interesting to see if the numbers were different or better using that as your reference.