Talking 12nm and Zen+

One of the highlights of the Ryzen 2000-series launch is that these processors use GlobalFoundries’ 12LP manufacturing process, compared to the 14LPP process used for the first generation of Ryzen processors. Both AMD and GlobalFoundries have discussed the differences in the processes, however it is worth understanding that each company has different goals: AMD only needs to promote what helps its products, whereas GlobalFoundries is a semiconductor foundry with many clients and might promote ideal-scenario numbers. Earlier this year we were invited to GlobalFoundries Fab 8 in upstate New York to visit the clean room, and had a chance to interview Dr. Gary Patton, the CTO.

The Future of Silicon: An Exclusive Interview with Dr. Gary Patton, CTO of GlobalFoundries

In that interview, several interesting items came to light. First, that the CTO doesn’t necessarily have to care much about what certain processes are called: their customers know the performance of a given process regardless of the advertised ‘nm’ number based on the development tools given to them. Second, that 12LP is a series of minor tweaks to 14LPP, relating to performance bumps and improvements that come from a partial optical shrink and a slight change in manufacturing rules in the middle-line and back-end of the manufacturing process. In the past this might not have been so news worthy, however GF’s customers want to take advantage of the improved process.

Overall, GlobalFoundries has stated that its 12LP process offers a 10% performance improvement and a 15% circuit density improvement over 14LPP.

This has been interpreted in many ways, such as an extra 10% frequency at the same power, or lower power for the same frequency, and an opportunity to build smaller chips.

As part of today’s launch, AMD has clarified what the move to 12LP has meant for the Ryzen 2000-series:

  1. Top Clock Speeds lifted by ~250 MHz (~6%)
  2. All-core overclocks around 4.2 GHz
  3. ~50 mV core voltage reduction

AMD goes on to explain that at the same frequency, its new Ryzen 2000-series processors draw around 11% less power than the Ryzen 1000-series. The claims also state that this translates to +16% performance at the same power. These claims are a little muddled, as AMD has other new technologies in the 2000-series which will affect performance as well.

One interesting element is that although GF claims that there is a 15% density improvement, AMD is stating that these processors have the same die size and transistor count as the previous generation. Ultimately this seems in opposition to common sense – surely AMD would want to use smaller dies to get more chips per wafer?

Ultimately, the new processors are almost carbon copies of the old ones, both in terms of design and microarchitecture. AMD is calling the design of the cores as ‘Zen+’ to differentiate them to the previous generation ‘Zen’ design, and it mostly comes down to how the microarchitecture features are laid out on the silicon. When discussing with AMD, the best way to explain it is that some of the design of the key features has not moved – they just take up less area, leaving more dark silicon between other features.

Here is a very crude representation of features attached to a data path. On the left is the 14LPP design, and each of the six features has a specific size and connects to the bus. Between each of the features is the dark silicon – unused silicon that is either seen as useless, or can be used as a thermal buffer between high-energy parts. On the right is the representation of the 12LP design – each of the features have been reduced in size, putting more dark silicon between themselves (the white boxes show the original size of the feature). In this context, the number of transistors is the same, and the die size is the same. But if anything in the design was thermally limited by the close proximity of two features, there is now more distance between them such that they should interfere with each other less.

For reference, AMD lists the die-size of these new parts as 213mm2, containing 4.8 billion transistors, identical to the first generation silicon design. AMD confirmed that they are using 9T transistor libraries, also the same as the previous generation, although GlobalFoundries offers a 7.5T design as well.

So is Zen+ a New Microarchitecture, or Process Node Change?

Ultimately, nothing about most of the Zen+ physical design layout is new. Aside from the manufacturing process node change and likely minor adjustments, the rest of the adjustments are in firmware and support:

  • Cache latency adjustments leading to +3% IPC
  • Increased DRAM Frequency Support to DDR4-2933
  • Better voltage/frequency curves, leading to +10% performance overall
  • Better Boost Performance with Precision Boost 2
  • Better Thermal Response with XFR2
New CPUs, New Process, New Competition Improvements to the Cache Hierarchy: Lower Latency = Higher IPC
Comments Locked


View All Comments

  • spdragoo - Thursday, April 19, 2018 - link

    Per Tom's Hardware (

    "Our test rigs now include Meltdown And Spectre Variant 1 mitigations. Spectre Variant 2 requires both motherboard firmware/microcode and operating system patches. We have installed the operating system patches for Variant 2.

    Today's performance measurements do not include Intel's motherboard firmware mitigations for Spectre Variant 2 though, as we've been waiting for AMD patches to level the playing field. Last week, AMD announced that it’s making the mitigations available to motherboard vendors and OEMs, which the company says should take time to appear in the wild. We checked MSI's website for firmware updates applicable to our X370 platforms when AMD made its announcement, but no new BIOSes were available (and still aren't).

    Unfortunately, we were only made aware that Variant 2 mitigations are present in our X470 board's firmware just before launch, precluding us from re-testing the Intel platforms with patches applied. We're working on this now, and plan to post updated results in future reviews.

    The lack of Spectre Variant 2 patches in our Intel results likely give the Core CPUs a slight advantage over AMD's patched platforms. But the performance difference should be minimal with modern processors."

    For those that are TL:DR in their viewpoint: unlike Anandtech, TH did NOT include all of the Spectre/Meltdown patches, & even said that there might be differences in their test results.
  • Chris113q - Thursday, April 19, 2018 - link

    Other reviewers also had their setups meltdown/spectre patched and it's been already confirmed that these patches don't greatly impact gaming performance at all.
    It's clear that Anandtech's results are wrong here. I have read 12 other reviews and most of their results differ from the ones you got. You'd have to be delusional to take just 1 review as the absolute truth.
  • Ninjawithagun - Thursday, April 19, 2018 - link

    Incorrect. Those reviews were conducted back in January 2018 (look at the review dates). Microsoft issued new patches for Meltdown and Spectre earier this month (April 2018). I could find no other performance review showing performance gain/loss for Intel CPUs based upon the new patches other than the one posted now by AnandTech.
  • Ninjawithagun - Thursday, April 19, 2018 - link

    The only way to know for sure is for each hardware reviewer to provide the exact version of Windows 10 they used for testing. This will prove whether or not they ran benchmarks with the most current Windows updates/patches.
  • Intel999 - Thursday, April 19, 2018 - link

    It is plausible that many reviewers were lazy and carried over data from earlier reviews on Intel and 1000 series Ryzen CPUs.

    Thank you Anandtech for doing aa genuinely unbiased review that required a great deal of extra work compared to others.
  • 5080 - Thursday, April 19, 2018 - link

    And don't forget BIOS patches as well. If you have a fully patched system the impact is even bigger than just updating with the Windows KB patches.
  • sor - Thursday, April 19, 2018 - link

    Looking at Tom’s results, they have OC intels in first place. Other than that it’s damn close. Is there a chance you’re just browsing graphs to see who is in the top spot and not really comprehending the results?

    Aside from that, the test setups and even benchmarks used are different. You owe Ian an apology for not realizing you’re comparing OC results to his.
  • Silma - Thursday, April 19, 2018 - link

    Yes. Ian is a top reviewer. At worst he made a mistake in this evaluations. It happens to the best of us.
    However, I have an issue with non OC test. It seems to me people will purchase overclockable processors and graphic cards to overclock them. At least game results should probably be based on OC benchmarks.
  • pogostick - Thursday, April 19, 2018 - link

    @Silma No, it makes more sense to do it this way. Everyone who buys these processors are guaranteed to have a part that will run the manufacturer spec. OC is a random lottery.
  • ACE76 - Thursday, April 19, 2018 - link

    Wrong... majority of even gamers DON'T overclock...that us relagated to a niche market of enthusiasts.

Log in

Don't have an account? Sign up now