Section by Andrei Frumusanu

The New Zen 3 Core: High-Level

As we dive into the Zen3 microarchitecture, AMD made a note of their journey of the last couple of years, a success-story that’s been started off in 2017 with the revolutionary Zen architecture that helped bring AMD back to the competitive landscape after several sombre years of ailing products.

The original Zen architecture brought a massive 52% IPC uplift thanks to a new clean-sheet microarchitecture which brought at lot of new features to the table for AMD, introducing features such as a µOP cache and SMT for the first time into the company’s designs, as well as introducing the notion of CPU core-complexes with large (8MB at the time) L3 caches. Features on a 14nm FinFET process node, it was the culmination and the start-off point of a new roadmap of microarchitectures which leads into today’s Zen3 design.

Following a minor refresh in the form of Zen+, last year’s 2019 Zen2 microarchitecture was deployed into the Ryzen 3000 products, which furthered AMD’s success in the competitive landscape. Zen2 was what AMD calls a derivative of the original Zen designs, however it contained historically more changes than what you’d expect from such a design, bringing more IPC increases than what you’d typically see. AMD saw Zen2 as a follow-up to what they had learned with the original Zen microarchitecture, fixing and rolling out design goal changes that they had initially intended for the first design, but weren’t able to deploy in time for the planned product launch window. AMD also stated that it enabled an opportunity to bring some of the future Zen3 specific changes were moved forward into the Zen2 design.

This was also the point at which AMD moved to the new chiplet design, leveraging the transition to TSMC’s new 7nm process node to increase the transistor budget for things like doubling the L3 cache size, increasing clock speeds, and vastly reducing the power consumption of the product to enable aggressive ramp in total core counts both in the consumer space (16-core Ryzen 9 3950X), as well as in the enterprise space (64-core EPYC2 Rome).

Tying a cutting-edge high-performance 7nm core-complex-die (CCD) with a lower cost 12/14nm I/O die (IOD) in such a heterogenous package allowed AMD to maximise the advantages and minimise the disadvantages of both respective technologies – all whilst AMD’s main competitor, Intel, was, and still is, struggling to bring out 10nm products to the market. It was a technological gamble that AMD many times has said was made years in advance, and has since paid off plenty.

Zen 3 At A Glance

This brings us to today’s Zen3 microarchitecture and the new Ryzen 5000 series. As noted earlier, Mark Papermaster had mentioned that if you were to actually look at the new design from a 100,000-foot level, you’d notice that it does look extremely similar to previous generation Zen microarchitectures. In truth, while Zen3 does share similarities to its predecessors, AMD’s architects started off with a clean-sheet design, or as they call it – “a ground-up redesign”. This is actually quite a large claim as this is a quite enormous endeavour to venture in for any company. Arm’s Cortex-A76 is the most recent other industry design that is said to have been designed from scratch, leveraging years of learning of the different design teams and solving inherent issues that require more invasive and large changes to the design.

Because the new Zen3 core still exhibits quite a few defining characteristics of the previous generation designs, I think that AMD’s take on a “complete redesign” is more akin to a deconstruction and reconstruction of the core’s building blocks, much like you’d dismantle a LEGO set and rebuild it anew. In this case, Zen3 seems to be a set-piece both with new building blocks, but also leveraging set pieces and RTL that they’ve used before in Zen2.

Whatever the interpretation of a “clean-sheet” or “complete redesign” might be, the important take is that Zen3 is a major overhaul in terms of its complete microarchitecture, with AMD paying attention to every piece of the puzzle and trying to bring balance to the whole resulting end-design, which comes in contrast to a more traditional “derivative design” which might only touch and see changes in a couple of the microarchitecture’s building blocks.

AMD’s main design goals for Zen3 hovered around three main points:

- Delivering another significant generational single-threaded performance increase. AMD did not want to be relegated to top performance only in scenarios where workloads would be spread across all the cores. The company wanted to catch up and be an undisputed leader in this area to be able to claim an uncontested position in the market.

- Latency improvements, both in terms of memory latency, achieved through a reduction in effective memory latency through more cache-hits thanks to the doubled 32MB L3 that an individual core can take advantage of, as well as core-to-core latency which again thanks to the consolidated single L3 cache on the die is able to reduce long travel times across the dies.

- Continuing a power efficiency leadership: Although the new Zen3 cores still use the same base N7 process node from TSMC (although with incremental design improvements), AMD had a constraint of not increasing power consumption for the platform. This means that any new performance increases would have to come through simultaneous power efficiency improvements of the microarchitecture.

The culmination of all the design changes AMD has made with the Zen3 micro-architecture results in what the company claims as a 19% average performance uplift over a variety of workloads. We’ll be breaking down this number further into the review, but internal figures show we are matching the 19% average uplift across all SPEC workloads, with a median figure of 21%. That is indeed a tremendous achievement, considering the fact that the new Ryzen 5000 chips clock slightly higher than their predecessors, further amplifying the total performance increase of the new design.

AMD Zen 3 Ryzen Deep Dive Review Zen 3: Front-End Updates & Execution Unit Redesigns
POST A COMMENT

342 Comments

View All Comments

  • jakky567 - Tuesday, November 24, 2020 - link

    Total system, I think the 5950x should be more popular. That being said, the 5900x is still great. Reply
  • mdriftmeyer - Monday, November 9, 2020 - link

    I spend $100 or more per week on extra necessities from Costco. Your price hike concerns are laughable. Reply
  • bananaforscale - Monday, November 9, 2020 - link

    5900X has good binning and the cheapest price per core. For productivity 3900X has *nothing* on 5900X for the 10% price difference and 5950X is disproportionately more expensive. Zen and Zen+ are not an option if you want high IPC, 3300X basically doesn't exist... I'll give you that 3600 makes more sense to most people than 5600X, it's not that much faster. Reply
  • Kangal - Wednesday, November 11, 2020 - link

    "Price per Core".... yeah, that's a pointless metric.
    What you need to focus on is "Price per Performance", and this should be divided into two segments: Gaming Performance, Productivity Performance. You shouldn't be running productivity tools whilst gaming for plenty of reasons (game crashes, tool errors, attention span, etc etc). The best use case for a "mixed/hybrid" would be Twitch Gaming, that's still a niche case.... but that's where the 5800X and 5900X makes sense.

    Now, I don't know what productivity programs you would use, nor would I know which games you would play, or if you plan on becoming a twitcher. So for your personal needs, you would have to figure that out yourself. Things like memory configurations and storage can have big impacts on productivity. Whereas for Gaming the biggest factor is which GPU you use.

    What I'm grasping at is the differences should/will decrease for most real-world scenarios, as there is something known as GPU scaling and being limited or having bottlenecks. For instance, RTX 2070-Super owners would target 1440p, and not 1080p. Or RTX 3090 owners would target 4K, and not for 1440p. And GTX 1650 owners would target 1080p, they wouldn't strive for 4K or 1440p.

    For instance, if you combine a 5600X with a Ultra-1440p-card, and compare the performance to a 3600X, the differences will diminish significantly. And at Ultra/4K both would be entirely GPU limited, so no difference. So if you compare a 5800X to a 3900X, the 3900X would come cheaper/same price but offer notably better productivity performance. And when it comes to gaming they would be equal/very similar when you're (most likely) GPU limited. That scenario applies to most consumers. However, there are outliers or niche people, who want to use a RTX 3090 to run CS GO at 1080p-Low Settings so they can get the maximum frames possible. This article alludes to what I have mentioned. But for more details, I would recommend people watch HardwareUnboxed video from YouTube, and see Steve's tests and hear his conclusions.

    Whereas here is my recommendation for the smart buyer, do not buy the 5600X or 5800X or 5900X. Wait a couple months and buy then. For Pure Gaming, get the r5-5600 which should have similar gaming performance but come in at around USD $220. For Productivity, get the r7-5700 which should have similar performance to the 5800X but come in at around USD $360. For the absolute best performance, buy the r9-5950x now don't wait. And what about Twitch Streamers? Well, if you're serious then build one Gaming PC, and a second Streaming PC, as this would allow your game to run fast, and your stream to flow fluidly.... IF YOU HAVE A GOOD INTERNET CONNECTION (Latency, Upload, Download).
    Reply
  • lwatcdr - Monday, November 9, 2020 - link

    "You can get the 3700 for much cheaper than the 5800X. Or for the same price you can get the 3900X instead."
    And if you want both gaming and productivity? They get the 5800X or 5900X. So AMD has something for every segment which is great.
    Reply
  • TheinsanegamerN - Thursday, November 12, 2020 - link

    The 5900x is margin of error from the 5950x in games, still shows a small uptick in gaming compared to 5800/5600x, offers far better performance then 5600/5800x in productivity tasks, and is noticeably cheaper then the 5950x.

    How on earth is that a non buy?

    The rest may be better value for money, but by that metric a $2 pentium D 945 is still far better value for money depending on the task. The 5000 series consistently outperforms the 3000 series, offring 20% better performance for 10% better cash.
    Reply
  • Kishoreshack - Saturday, November 14, 2020 - link

    AMD has the best products to offer
    Soo you expect them to sell it at a cheaper rate than intel ?
    Reply
  • Threska - Monday, November 16, 2020 - link

    AMD has a good product RANGE, which means something for everyone AND all monies go to AMD regardless of consumer choice. Reply
  • Ninjawithagun - Friday, November 20, 2020 - link

    The price hike is mainly to cover ongoing R&D for the next-gen Ryzen Zen 4 CPUs due out in 2022. The race between Intel and AMD must go on! Reply
  • jakky567 - Monday, November 23, 2020 - link

    I disagree about the 5900x being a no buy.

    I feel like it goes 5950x for absolute performance. 5900x for high tier performance on a budget. And then the 3000 series for people on a budget, except the 3950x.

    The 5900x has all the l3 cache.
    Reply

Log in

Don't have an account? Sign up now