The Mac Pro Review (Late 2013)
by Anand Lal Shimpi on December 31, 2013 3:18 PM ESTCPU Performance
I like to have large historical databases of performance so I can put new products in perspective. The Mac Pro and its funny lineage make this a little difficult. For starters, I simply haven't reviewed all of the Mac Pro CPU combinations that have existed over the years. Then there's also the fact that not all of my Mac suite applies well to a 12-core/24-thread Mac Pro. I'm going to try my best to put the new Mac Pro's performance in perspective, but it's going to require a couple of subsections.
Let's first start with a look at the historical performance of the Mac Pro. I really have to thank @elfurberino and @tapbot_paul for lending their time (and their Mac Pros) to help flesh out this comparison. With their help I managed to put together performance data for almost every single generation of Mac Pro.
We'll start with Cinebench R10's single threaded test. Unfortunately the benchmark crashes on Macs with 16+ threads so single threaded performance is all we'll be able to look at:
That's right, I still have my old PowerMac G5 Dual 2.5GHz (upgrade from my original 2.0 model). It's interesting to note that single threaded performance has only improved by 2.8x over that 2.5GHz dual G5 machine from around a decade ago. If we were able to also look at multithreaded performance we'd see a much larger gap. The dual G5's multithreaded performance is actually lower than the single threaded performance of the new Mac Pro's IVB-EP (3346 vs 5187). And the new Mac Pro has 12 of those cores.
Here you can see a very healthy increase in single threaded performance over the 2010/2012 12-core system. The 34% increase in performance is because the Mac Pro never got the Sandy Bridge bump. All previous Mac Pros topped out at Nehalem/Westmere. Couple all of the Sandy Bridge improvements with the much higher peak clock speeds (3.5GHz vs. 3.0GHz) and the performance gains make sense.
The 8C system from early 2009 gives us an example of how it's very possible to have a newer Mac Pro actually perform worse than its predecessor. Apple has done a relatively good job this round of keeping the core count/frequency tradeoffs sensible, but you still have to align your silicon choices to your workload.
Moving on to Cinebench 11.5, we lose the PowerMac G5 comparison but we gain a more modern benchmark. Once again we'll start with the single threaded numbers:
There's that healthy single threaded performance bump again. It is pretty incredible to me just how far we've come in single threaded performance since the mid-2000s. What's even crazier is that 2.0GHz Mac Pro from 2006 is only about 40% faster than a Bay Trail tablet with an Atom Z3770.
The multithreaded story is more evolutionary for sure, especially compared to the previous generation 12-core model. Here we're showing a 20% gain over the previous 12-core design. If you're migrating from a machine with fewer cores you can expect a corresponding increase in multithreaded performance. What is most surprising here is that a 2.3GHz 15-inch MacBook Pro with Retina Display (Late 2013) actually offers better multithreaded performance than the 8-core 2.66GHz Mac Pro from early 2008 in the chart above. The new 15-inch rMBP scores a 6.62 here compared to the 6.58 of that old Mac Pro.
I also shared my Firefox build test with Adam and Paul, who helped me fill out the chart below:
There isn't much of an advantage to having 12 cores here, but the new Mac Pro does deliver an amazingly quick build time compared to anything else. The new Mac Pro is good for around a 24% improvement in build performance compared to the outgoing 12-core model.
Facebook
Twitter
RSS
267 Comments
View All Comments
JlHADJOE - Wednesday, January 1, 2014 - link
AFAIK the D700 is also a FirePro, and also has ECC on its VRAM.tipoo - Wednesday, January 1, 2014 - link
Wrong, it has no ECC. On OSX Apple writes much of the graphics driver anyways, so they can get away with calling Radeons FirePros as ECC isn't a necessity to call them that.Kevin G - Wednesday, January 1, 2014 - link
ECC on the FirePro's doesn't actually add additional RAM like it does on traditional server DIMM's. Instead as RAID5 like parity is performed on GPU memory channels to be able to be able to detect a memory error. Thus the 6 GB card will only have 5.25 GB available to use with ECC enabled. Since all the memory channel have to be used for a memory access, performance in some workloads takes a significant hit. I believe by default ECC is disabled for performance and memory capacity reasons.There is also one other difference between the D700 and the W9000: clock speeds and voltages. The D700 runs are a lower clock speed by default and presumably lower voltage to cut power consumption.
DaveGirard - Wednesday, January 1, 2014 - link
the D700 is clocked lower than the W9000. It's at 850MHz instead of 950.lilo777 - Wednesday, January 1, 2014 - link
Except it does not have ECC memory or the Pro drivers which are the only things that differentiate Pro from consumer grade cards. As such they are consumers grade cards (and the two year old generation) which cost around $700 at most not the $3500 pro cards.japtor - Wednesday, January 1, 2014 - link
There's never been a pro driver distinction in OS X, Radeons are validated for pro apps in OS X like FirePros in Windows. Granted there hasn't been the pro branding until now, but Apple does the drivers iirc so I don't see them bothering with splitting the driver base like AMD does.melgross - Wednesday, January 1, 2014 - link
You know nothing about Apple's drivers. I would bet that at the very least, they are based on the pro driver configurations, as apple has little interest in gaming, and a lot of interest in pro users. If you look at the performance of this in a pro app you can see that performance is pretty good. Mac Pro's are used in NASA, drug company research labs, CAD shops, video, photography labs and studios and publishing. Game drivers are of no interest to them.solipsism - Tuesday, December 31, 2013 - link
Note that he speculates that the CPU would be soldered (something no Mac Pro has ever had) and the thermal cap removed (something I believe Apple had only done once).Also note he doesn't have any more PCIe available for the SSD so he ends up going with the much slower SATA version but to make up some of the speed he gets 2x512GB in a RAID 0 configuration.
I like the case they used and I'm expect to see *more* of these smaller cases hit the market for DIYer and from OEMs now that Apple has stepped in.
Lonyo - Wednesday, January 1, 2014 - link
There are lots of small cases on the market and there have been for a while now... sure there could be more, but they are already widely available with a hell of a lot of variety of designs... not sure exactly how you think Apple will have any real impact on this market.If anything is going to have an impact it would be Steam boxes because OEMs might start pulling their fingers out and designing more gaming oriented small boxes, although they also are already rather common, but not always available for end users, such as the Alienware system which has a horizontal GPU mount with a riser.
solipsism - Wednesday, January 1, 2014 - link
Where are all these OEM PCs with very small cases but high performance like the new Mac Pro?