CPU 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.

Plotting the Mac Pro’s GPU Performance Over Time CPU Performance - Five Generations of Mac Pros Compared
Comments Locked

267 Comments

View All Comments

  • tipoo - Thursday, January 2, 2014 - link

    But can you use them as Firepros when dual booting Windows?
  • hoboville - Thursday, January 2, 2014 - link

    Nvidia GPUs run those applications faster, the Mac Pro GPUs, while having more RAM, are underclocked to meet temps because of the small form factor. If you don't need ECC, and aren't using more than 3 GB of RAM, build a PC with R9 280Xs. If you want a serious workstation, buy Nvidia.
  • HydraMac - Tuesday, December 31, 2013 - link

    @Ananad - Hey interesting results with that power virus and throttling but what would happen doing the same thing to the older more conventional MP running 2xGPU cards as well? I'd be curious how the old school machine handled the same type of thrashing. It would give a frame of reference as opposed to the results being shown in a vacuum i.e. unified core vs. conventional machine cooling.
  • justizin - Tuesday, December 31, 2013 - link

    "All of that being said, I don’t expect there to be a lot of cross shopping between DIY builders and those looking for a Mac Pro."

    Actually, everyone I've ever known who worked at Apple was a hackintosh enthusiast and had a home-build machine faster than a Mac Pro at a far lower price. I assume since Apple has curtailed its' employee discounts in recent years, this trend will only continue to grow.
  • Kevin G - Wednesday, January 1, 2014 - link

    For consumer systems, yes.

    For professional level systems, there indeed will be little overlap. The professional level DIY market is quiet small as it is preferred that companies order from an OEM like Dell or HP to get a centralized warranty, support and service. There is a price premium there from the OEM's but they do tend to follow through on their support contracts. This saves time instead of having to go through multiple vendors for support and RMA's equipment. The prices of professional level equipment on the PC side (Xeons, ECC memory, and graphics) don't offer the same mass market price benefits as consumer parts.
  • darkcrayon - Wednesday, January 1, 2014 - link

    Exactly. If the DIY market were so large for Pro systems, there's no way HP or Lenovo could justify having them in their product line- and a DIY Windows machine doesn't even need a hacked OS.
  • newrigel - Wednesday, March 1, 2017 - link

    You're full of BS man... They are hassle to maintain and if you want to get work done that's the wrong machine to have.... buy cheap and be cheap because that's what you are... ghetto productions!!!!
  • wkw - Tuesday, December 31, 2013 - link

    10 USB 2 ports on the Lenovo. Sweeeeeeet
  • newrigel - Wednesday, March 1, 2017 - link

    Ever heard of a USB hub?????
  • El Aura - Tuesday, December 31, 2013 - link

    Is the preferred order of TB port usage really 1, 2, 5 and not 1, 3, 5?

Log in

Don't have an account? Sign up now