The Mac Pro Review (Late 2013)
by Anand Lal Shimpi on December 31, 2013 3:18 PM ESTCPU Choices
Had I gotten around to publishing my rMBP review prior to this one you would’ve seen my praise Apple’s CPU selection abilities as of late. Outfitting all 15-inch rMBPs with Crystalwell was a very wise move on Apple’s part. With the Mac Pro the CPU selection is good, but the decision of what to buy is far more complex than in any other product line.
The Mac Pro not only serves as Apple’s ultra high end Mac, but it’s the only option if your needs exceed that of an iMac or 15-inch MacBook Pro. Literally anyone who needs more performance than Apple offers in an all-in-one or a notebook inevitably is pushed to consider the Mac Pro. With a relatively broad professional audience in mind, Apple offers more CPU options for the Mac Pro than on any other shipping Mac:
| Mac Pro (Late 2013) CPU Options | ||||||
| Intel CPU | Xeon E5-1620 v2 | Xeon E5-1650 v2 | Xeon E5-1680 v2 | Xeon E5-2697 v2 | ||
| Cores / Threads | 4 / 8 | 6 / 12 | 8 / 16 | 12 / 24 | ||
| CPU Base Clock | 3.7GHz | 3.5GHz | 3.0GHz | 2.7GHz | ||
| Max Turbo (1C) | 3.9GHz | 3.9GHz | 3.9GHz | 3.5GHz | ||
| L3 Cache | 10MB | 12MB | 25MB | 30MB | ||
| TDP | 130W | 130W | 130W | 130W | ||
| Intel SRP | $294 | $583 | ? | $2614 | ||
| Apple Upgrade Cost (Base Config) | - | +$500 | +$2000 | +3500 | ||
| Apple Upgrade Cost (High End Config) | - | - | +$1500 | +3000 | ||
There are four CPU options, each with varying core counts. The more cores you get, the lower your base CPU frequency is. In the old days, that would be the end of the discussion - you either choose more cores or more frequency, a tradeoff that is ultimately determined by your workload. Starting with its Nehalem architecture back in 2008, Intel introduced two key technologies that changed the face of multicore on the desktop: power gating and turbo boost. The former is a technology that can almost entirely remove power to a core (both active and leakage) when idle, while the second takes advantage of that freed up thermal budget to drive any active core(s) at higher frequencies. Subsequent implementations of Intel’s Turbo Boost technology have scaled the aggressiveness of this opportunistic frequency scaling, but the basic principle remains the same.
Apple advertises core count and base frequency for all of the Mac Pro CPU options, but to really understand what you’re getting yourself into you need to look at each CPU’s max turbo states vs. number of active cores. Neither Apple nor Intel do a great job of publicly exposing this information, Apple avoids doing so in order to keep things clean/simple, and Intel avoids doing so because perhaps it’s fun? Either way I’ve compiled the data on the four CPU options into the charts below.
I've left base clocks out of the graphs although you can see them noted in the legend at the bottom of each chart.
This first chart has the y-axis starting at 0MHz, but the next one is the more interesting as it starts at 2.7GHz and better illustrates/exaggerates the sort of frequency tradeoff you can expect vs. core count:
The 4, 6 and 8 core CPU options all offer the same peak single core frequency (3.9GHz). This is very important as single threaded performance remains the gate for system responsiveness outside of thread heavy applications. The 12-core CPU sacrifices around 10% of this peak single core performance.
Early on the 8-core CPU holds the advantage over the rest, being able to hit a higher 2-core max turbo. The octa-core’s crossover point happens at 3 active cores, beyond this point the quad and six core CPUs maintain a slight max turbo advantage.
The key takeaway here is that more cores isn’t necessarily better. You need to weigh the needs of your applications against the number of cores in your system. There is no one-size-fits-all answer here. For kicks I looked at the CPU load for a handful of my benchmarks:
Application version seems to have a huge impact on threading. Running our Photoshop benchmark on CS5 vs. CS6 is the difference between loading 2 - 8 cores vs. 3 - 10. The same is true if I compare Final Cut Pro 10.0 vs. 10.1; the latest version from Apple (optimized for the new Mac Pro), makes great use of all 12 cores/24 threads. Workload also has an impact. I took our old Final Cut Pro 10.0 benchmark (1080p) and ran it on 10.1, saw a maximum of 1217% CPU usage. I ran our new 4K benchmark on 10.1 and saw nearly full virtual core utilization (2114% CPU usage).
Final Cut Pro 10.0 - 1080p Benchmark
Final Cut Pro 10.1 - 1080p Benchmark
Final Cut Pro 10.1 - 4K Benchmark
Offline 3D rendering applications typically have the easiest time of chewing up tons of cores, while many others are likely better suited by having fewer cores running at a higher frequency. There's also a serious multitasking benefit if you're the type of person that runs multiple thread heavy workloads in parallel. It's pretty nice having a fairly responsive system while rendering a beefy 4K project in Final Cut Pro. The responsiveness comes courtesy of having a ton of cores in addition to extremely fast IO. That PCIe SSD definitely comes in handy.
If you want the best balance of heavily threaded performance without sacrificing performance in lighter workloads, the 8-core configuration seems to be the best bet. There are definitely bragging rights associated with the 12-core system, but unless you absolutely need a ton of cores you’re likely better suited by the 8-core configuration.
Facebook
Twitter
RSS
267 Comments
View All Comments
FunBunny2 - Tuesday, December 31, 2013 - link
Has everybody forgotten? This is just a Cube with one round corner. I suppose Tim will claim that's been patented too.newrigel - Wednesday, March 1, 2017 - link
Right.... with a unified core in it he he.... Mac's ruleY0ssar1an22 - Tuesday, December 31, 2013 - link
Off the Mac Pro topic but how come the 2013 13" rMBP scores significantly lower than the 2012 and various MBAs in the Cinebench 11.5? I'm personally interested as I have one on order :-) It scores better in later tests (so presumably not a typo?) Cinebench caught my eye as the first cross-benchmark in the review.Thanks for this review, and looking forward to the rMBPs in depth!
iwod - Tuesday, December 31, 2013 - link
1. What are the likely chances of a Mac that does Desktop Class Gfx card with 2 x8 PCI-E and uses Desktop Haswell instead. Unless i miss anything surely this is a simple change in production line.2. SSD speed is slow, for a Peak rate of 2GB/s, it seems Apple firmware or Samsung Controller not capable of feeling up the peak bandwidth? So which is likely the cause?
3. GFx ECC Ram. How much of a problem is it? For Professional market? And why Apple decide to ditch this since the price difference are minor for the price of Mac Pro.
dwade123 - Tuesday, December 31, 2013 - link
Who the **** put a trashcan here!?e375ued - Wednesday, January 1, 2014 - link
Is there some convenient reason Anand let the Mac Pro off easy by using Prime95 instead of Intel Burn Test or linpack?Ryan Smith - Wednesday, January 1, 2014 - link
It was my suggestion to try maxing out the Mac Pro, just to see if it would throttle (and if so, by how much). I picked Prime95 because it's good enough; not that there's anything wrong with IBT or Linpack, but all 3 of those are close enough that it shouldn't matter (and P95 is easy to use).jrs77 - Wednesday, January 1, 2014 - link
Good test that shows that the thermal core design works like a charm, even when applying very heavy and rather unrealistic loads to the system.Most people will run these new Mac Pros with only having a scene rendered or a video-filter applied etc and in this case the system is basically dead-silent and street-noise totally drowns the noise of the fan anyways.
Just a tad too expensive for me tho.
Kevin G - Wednesday, January 1, 2014 - link
The ‘mid range’ config is a far better value on the 2012 model since it is a 12 core model. The $200 savings can be put toward a better GPU.With regard to Cinebench, does it use AVX under OS X? I suspect that it does and that is where the majority of the single threaded CPU performance increase comes from. I strongly suspect that the single threaded performance advantage is far narrower in legacy code that doesn’t take advantage of AVX.
I’m glad the 2012 model was tested with a Radeon 7950. The ability to upgrade GPU’s matters and it’ll keep the 2012 model competitive for awhile. The system will support future video cards that come in from the PC side of things. With UEFI on video cards now, there is little difference between a Mac and PC version. For what it is worth, I have stuck an EVGA GTX 770 into a 2012 Mac Pro without issue and no modification on the video card or OS X drivers. It just works.
A bit of a random note is that the GPU connector used in the Mac Pro isn’t new to Apple: they used it for the G4 class daughter cards form 15 years back.
The PLX chip doesn’t have to do any port switching as a single GPU can drive up to 6 surfaces. That would imply the six DP signals from one GPU are routed in pairs to each of the Falcon Ridge controllers for encapsulation.
One shocking thing is that wall power draw exceeds that of the PSU’s DC rating. That is worrying as the system itself has only a 450W rated power supply. Due to the AC to DC conversion, there is an efficiency factor but the system has to be running close to its DC limit. Performing several file transfers over powered Thunderbolt devices could put the power draw beyond the rated DC limit. I wonder if Apple has implemented throttling based upon raw power consumption of the system as a whole in addition to temperature and power consumption of individual parts. Perhaps testing the system on a 240V AC circuit would alter things here as it is more efficient power delivery?
One aspect not accounted for is memory expansion. The 2009/2010/2012 Mac Pro’s will work with registered ECC memory which brings their maximum capacity up to 128 GB. Memory bandwidth too is superior in the dual socket 2010/2012 models: six channels of 1333 Mhz memory does have more bandwidth than four channels at 1866 Mhz. Going multi-socket does carry some overhead but still a bit of a disappointment that the theoretical number didn’t improve.
Bill Thompson - Wednesday, January 1, 2014 - link
My guess is the nVidia-based iMac is faster with After Effects and Premiere because of CUDA.Davinci Resolve has been updated for OpenCL, but I don't think Octane or Adobe apps have.
BTW, FCP X 10.1 displays multiple 4K streams in real time without rendering. It's a serious app.