AMD Zen 2 Microarchitecture Analysis: Ryzen 3000 and EPYC Rome
by Dr. Ian Cutress on June 10, 2019 7:22 PM EST- Posted in
- CPUs
- AMD
- Ryzen
- EPYC
- Infinity Fabric
- PCIe 4.0
- Zen 2
- Rome
- Ryzen 3000
- Ryzen 3rd Gen
AMD Zen 2 Microarchitecture Overview
The Quick Analysis
At AMD’s Tech Day, on hand was Fellow and Chief Architect Mike Clark to go through the changes. Mike is a great engineer to talk to, although what always amuses me (for any company, not just AMD) is that engineers that talk about the latest products coming to market are already working one, two, or three generations ahead at the company. Mike remarked that it took him a while to think back to the specific Zen+ to Zen 2 changes, while his mind internally is already several generations down the line.
An interesting element to Zen 2 is around the intention. Initially Zen 2 was merely going to be a die shrink of Zen+, going from 12nm down to 7nm, similar to what we used to see with Intel in its tick-tock model for the initial part of the century. However, based on internal analysis and the time frame for 7nm, it was decided that Zen 2 would be used as a platform for better performance, taking advantage of 7nm in multiple ways rather than just redesigning the same layout on a new process node. As a result of the adjustments, AMD is promoting a +15% IPC improvement for Zen 2 over Zen+.
When it comes down to the exact changes in the microarchitecture, what we’re fundamentally looking at is still a similar floorplan to what Zen looks like. Zen 2 is a family member of the Zen family, and not a complete redesign or different paradigm on how to process x86 – as will other architectures that have familial updates, Zen 2 affords a more efficient core and a wider core, allowing better instruction throughput.
At a high level, the core looks very much the same. Highlights of the Zen 2 design include a different L2 branch predictor known as a TAGE predictor, a doubling of the micro-op cache, a doubling of the L3 cache, an increase in integer resources, an increase in load/store resources, and support for single-operation AVX-256 (or AVX2). AMD has stated that there is no frequency penalty for AVX2, based on its energy aware frequency platform.
AMD has also made adjustments to the cache system, the most notable being for the L1 instruction cache, which has been halved to 32 kB, but associativity has doubled. This change was made for important reasons, which we’ll go into over the next pages. The L1 data cache and L2 caches are unchanged, however the translation lookaside buffers (TLBs) have increased support. AMD also states that it has added deeper virtualization support with respect to security, helping enable features further down the pipeline. As mentioned previously in this article, there are also security hardening updates.
For the quick analysis, it’s easy to tell that doubling the micro-op cache is going to offer a significant improvement to IPC in a number of scenarios, and combine that with an increase in load/store resources is going to help more instructions get pushed through. The double L3 cache is going to help in specific workloads, as would the AVX2 single-op support, but the improved branch predictor is also going to showcase raw performance uplift. All-in-all, for an on-paper analysis, AMD’s +15% IPC improvement seems like a very reasonable number to promote.
Over the next few pages, we’ll go deeper into how the microarchitecture has changed.
Facebook
Twitter
RSS
216 Comments
View All Comments
Gastec - Wednesday, June 19, 2019 - link
I'm 95% convinced that your micro-stuttering is caused by the GPU/drivers. Disable SLI or Crossfire if that's what you have (you never said what video card you use). And please stop trolling.wurizen - Thursday, June 20, 2019 - link
Really? After all that I said about this... you think that you're 95% sure it's caused by GPU drivers and you want me to disable SLI or Crossfire? Really?Qasar - Thursday, June 20, 2019 - link
have you even mentioned which vid card you are using, or what version the drivers are, or if they are up to date ??Gastec - Wednesday, June 19, 2019 - link
It could also be related to G-sync/FreeSync and your monitor. When debugging the best way is to reduce everything to a minimum.wurizen - Thursday, June 20, 2019 - link
Really, dude? You think it's related to Gsyng and Freesync?Qasar - Thursday, June 20, 2019 - link
it very well could be.. a little while ago.. there was a whole issue with micro stuttering and the fix.. was in new drivers after a certain revision...wurizen - Thursday, June 20, 2019 - link
This is gonna be my last comment regarding my comment about Infinity Fabric High memory latency issue... an objective response would be "It could;" or, "it's quit possible;" or, "110 nanoseconds latency via cross-ccx-memory-performance is nothing to sneeze at or disregard or a non-issue;"instead, i get the replies above; which doesn't need to be repeated since one can just read them. but, just in case, the replies basically say I am trolling such as the most recent from user Gastec; and someone prior I jumped to my conclusion of pointing my scrawny little finger at Infinity Fabric high memory latency; someone plain said I didn't know what I was talking about; etc!
So, I just wanna say that as my one last piece. It's odd no one has aired to the caution of objectivity and just plain responded with "It's possible..."
Instead, we get the usual techligious/fanboyish responses.
Qasar - Thursday, June 20, 2019 - link
it doesnt help, you also havent cited any links or other proof of this other then your own posts... and i quote " And, there are people having head-scratching issues similar to me with Ryzen CPU. " oh.. and where are these other people ?? where are the links and URLs that show this ??? lastly.. IF you have a spare hdd ( ssd or mechanical ) that isnt in use that you could install windows on to, so you wont have to touch the current one you are using, try installing windows on to that, update windows as much as you can via windows update, update all drivers, and do the same things you are doing to get this issue.. and see if you still get it.. if you do.. then it isnt your current install of windows, and it is something else.Carmen00 - Friday, June 21, 2019 - link
Qasar, Gastec et al, I appreciate that you're trying to educate wurizen but when you get responses like "bruh!" and "Really?", I think it's time to call it quits. Like HStewart, feeding wurizen will just encourage him and that makes it difficult to go through the comments and see the important ones. Trust that the majority of Anandtech's readership is indeed savvy enough to know pseudo-technical BS when we encounter it!Qasar - Friday, June 21, 2019 - link
well.. the fact that he didnt cite any one else with this problem, or links to forums/web pages.. kind of showed he was just trolling.. but i figured... was worth a shot to give him some sort of help....