The Ryzen Die

Throughout the time leading up to the launch of Ryzen, AMD reaffirmed its commitment to at least +40% IPC improvement over Excavator. This was specifically listed as a goal relating to performance, at an equivalent energy per cycle, resulting in a 40% increase in efficiency. At the Tech Day, AMD listed an overall 2.7x (or 270%) performance per watt improvement, split into the following:

Obviously a number of benefits come from moving the 28nm TSMC process to GloFo’s 14nm FinFET process which is used via a Samsung license. Both the smaller node and FinFET improvements have been well documented so we won’t go over them here, but AMD is stating that Zen is much more than this as a direct improvement to immediate performance, not just efficiency. While Zen is initially a high-performance x86 core at heart, it is designed to scale all the way from notebooks to supercomputers, or from where the Cat cores (such as Jaguar and Puma) were all the way up to the old Opterons and beyond, all with at least +40% IPC.

The first immediate image out of the presentation is the CPU Complex (a CCX), which shows the Zen core design as a four-CPU cluster with caches. This shows the L2/L3 cache breakdown, and also confirms 2MB of L3 per core with 8 MB of L3 per CCX. It also states that the L3 is mostly inclusive of the L2 cache, which stems from the L3 cache as a victim cache for L2 data. AMD is stating that the protocols involved in the L3 cache design allow each core to access the L3 of each other core with an average (but range) of latencies.

Over the next few pages, we’ll go through the slides. They detail more information about the application of Simultaneous Multithreading (SMT), New Instructions, the size of various queues and buffers, the back-end of the design, the front-end of the design, fetch, decode, execute, load/store and retire segments.

Zen: New Core Features The High Level Zen Overview
Comments Locked

574 Comments

View All Comments

  • theuglyman0war - Saturday, March 4, 2017 - link

    I'd like to see a lot more older i7 extreme editions covered all the way to westmere so I can sell clients on new builds with such a comparison.
  • mapesdhs - Sunday, March 5, 2017 - link

    Which older i7s interest you specifically?
  • theuglyman0war - Saturday, March 4, 2017 - link

    Checking what I paid last month for i7-7700k at Microcenter...
    Although I did get the motherboard combo price sale they "usually" offer...
    The supposed $60 off for $319 is the cheapest price I found with a quick survey of new egg, amazon etc... And only $20 less then what I paid! Hardly A slashed priced answer shot across the bow by Intel! Not by a long shot!
    I thought I was going to recommend the new cheap price to all my customer's new builds but I am pushing RYZEN and AM4 for a real combined price that makes a difference. ( the cheap price for enthusiast Am4 is enticing but the loss of PCI lanes is of concern for extreme cpu comparison anyway. Not so much compared to i7-7700k though which brings the comparison back to 16 lane parity! )
  • theuglyman0war - Saturday, March 4, 2017 - link

    Could anyone actually point me to the amazing slashed deals that "BEAT" what I couldn't get last month by a long shot?

    ( which was $349 BEFORE rebate. In other words it's not like there were not sales last month as well. And I see nothing now that really amounts to AMAZING compared to last month? )

    Pretty dam insulting from somewhere in the pipe? Not sure if it's Intel. Or it's resellers clinging on to greedy margins not reflecting the savings to save their own ass's and bottom line due to stock considerations? Which iz no excuse considering the writing was on the wall. Someone needs to do a lot better. A heck of a lot better. Particularly considering I was thinking I could jes laff off AMD with an Intel savings and now have egg on my face! :)
  • rpns - Saturday, March 4, 2017 - link

    The 'Test Bed Setup' section could do with some more details. E.g. what BIOS version? Windows 10 build version? Any notable driver versions?

    These details aren't useful just now, but also when looking back at the review a few months down the line.
  • jorkevyn - Saturday, March 4, 2017 - link

    why they don't get 4 channel for DDR4 memory? I think, if you get that you will may be the real I7 6950K Killer
  • sedra - Saturday, March 4, 2017 - link

    have a look at this:
    "Many software programmers consider Intel's compiler the best optimizing compiler on the market, and it is often the preferred compiler for the most critical applications. Likewise, Intel is supplying a lot of highly optimized function libraries for many different technical and scientific applications. In many cases, there are no good alternatives to Intel's function libraries.

    Unfortunately, software compiled with the Intel compiler or the Intel function libraries has inferior performance on AMD and VIA processors. The reason is that the compiler or library can make multiple versions of a piece of code, each optimized for a certain processor and instruction set, for example SSE2, SSE3, etc. The system includes a function that detects which type of CPU it is running on and chooses the optimal code path for that CPU. This is called a CPU dispatcher. However, the Intel CPU dispatcher does not only check which instruction set is supported by the CPU, it also checks the vendor ID string. If the vendor string says "GenuineIntel" then it uses the optimal code path. If the CPU is not from Intel then, in most cases, it will run the slowest possible version of the code, even if the CPU is fully compatible with a better version."

    http://www.agner.org/optimize/blog/read.php?i=49&a...
  • HomeworldFound - Saturday, March 4, 2017 - link

    Everyone here already knew that ten years ago.
  • Notmyusualid - Sunday, March 5, 2017 - link

    Indeed it was.
  • sedra - Sunday, March 5, 2017 - link

    it is worth to bring it up now.

Log in

Don't have an account? Sign up now