'

AMD hints at Zen 3's performance gains - Claims its an "entirely new architecture"

AMD is 'confident [in] being able to drive significant IPC gains each generation.'

AMD hints at Zen 3's performance gains - Claims its an

AMD hints at Zen 3's performance gains - Claims its an "entirely new architecture"

Zen 2 has been a gamechanger for AMD, enabling the company to make gains in every market segment where the architecture is available. Simply put, Zen 2 architectural changes and cutting-edge manufacturing have allowed AMD to be more competitive than they have been at any time in the past decade. 

While Zen 2 offered a tremendous leap for AMD's CPU performance, AMD doesn't expect things to slow down with Zen 3. In an interview with The Street, AMD's Forrest Norrod said that Zen 3 would be an "entirely new architecture", and that Zen 3 would be "right in line with what you would expect from an entirely new architecture." This sets some high expectations for Zen 3. 

In the same interview, AMD's Forrest Norrod stated that AMD was "confident [in] being able to drive significant IPC gains each generation," and that AMD's future server CPU launches would rely on a "tick-tock" cadence, which is something that Intel has failed to do for several years. 

We know that Zen 3 will a more mature version of the same 7nm manufacturing techniques that today's Zen 2 processors are based on, making most of Zen 3's performance gains due to architectural changes. 

Zen 3's architectural changes

At the HPC AI Advisory Council's 2019 UK Conference, AMD's Martin Hilgeman confirmed that Zen 3 would move away from Zen/Zen 2's split cache design, which split the L3 cache on AMD's CPU dies between two quad-core CCXs. This suggests that AMD is making some major changes to its Zen core architecture with Zen 3, and lowering the barriers between the multi-CCX designs of today's Zen processors. 

Instead of offering two L3 caches that are 16MB in size (as seen in AMD's current Zen 2 design), AMD's Zen 3 core design will offer a combined "32+MB" of L3 cache between all eight CPU cores. This will lower (or eliminate) potential inter-CCX latencies between the CPU cores in a single die and grant CPU cores better access to each chip's onboard L3 cache memory. 

The slide below also suggests that Zen 3's L3 cache will be bigger than what was seen in Zen 2. This means that Zen 3 could offer a larger, combine L3 cache, granting all CPU cores better cache access while also providing the potential for more cache capacity. This could lower some internal CPU latencies, and allow Zen 3 processors to cache more data on-die. These changes could be beneficial for Zen 3's gaming performance, given AMD's existing marketing for "GameCache", and its benefits for Zen 2. 

Combine these cache changes with alterations to AMD's Zen 3 compute units, and it is easy to believe that AMD will deliver a notable boost to Zen's IPC with their Zen 3 processor designs. Today's rumours place Zen 3's IPC gains at 8-10%

  AMD reveals early Zen 3/Milan architecture details and Zen 4/Genoa plans


An 8-10% IPC gain with Zen 3 and a few 100 MHz in clock speed would make Zen 3 a decent upgrade over Zen 2, especially if Intel cannot adequately react to AMD's HEDT and server-grade offerings. 

AMD's Zen 3 architecture is due to release in 2020 for both the desktop and server markets. 

You can join the discussion on AMD's Zen 3 processors on the OC3D Forums

«Prev 1 Next»

Most Recent Comments

19-11-2019, 12:25:27

NeverBackDown
AMD will be moving from TSMCs 7nm to TSMCs 7nm+ which itself will give a decent performance improvement. A few percentage better but most of the improvements will be directly from architecture. I'm excited for the combined cache. Might just be what it needs to close the gap in Single threaded performance. Also curious to see if this helps cut down memory latency as well since it will have one central location. Would be interesting if a reviewer could do that if possible.

My only concern is AMD has released Zen twice so far and each time it has required extensive changes to how OS's handle them. By doing this yet again it's just causing more frustration from OS makers and surely HPC groups having to constantly reoptimize for Zen.

AMD is probably leaving performance on the table by doing this. They should be working extremely hard making sure all the changes to each new architecture launch has the best performance possible. Make it easier for everyone and gain the benefitsQuote

19-11-2019, 14:40:38

WYP
Quote:
Originally Posted by NeverBackDown View Post
AMD will be moving from TSMCs 7nm to TSMCs 7nm+ which itself will give a decent performance improvement. A few percentage better but most of the improvements will be directly from architecture. I'm excited for the combined cache. Might just be what it needs to close the gap in Single threaded performance. Also curious to see if this helps cut down memory latency as well since it will have one central location. Would be interesting if a reviewer could do that if possible.

My only concern is AMD has released Zen twice so far and each time it has required extensive changes to how OS's handle them. By doing this yet again it's just causing more frustration from OS makers and surely HPC groups having to constantly reoptimize for Zen.

AMD is probably leaving performance on the table by doing this. They should be working extremely hard making sure all the changes to each new architecture launch has the best performance possible. Make it easier for everyone and gain the benefits
The radical changes are what's making things work better through, especially with Threadripper. Zen 2 Threadripper and EPYC now look like a single CPU to windows, removing the NUMA issues. Now Threadripper is just a bigger Ryzen, rather than a strange multi-CPU system on a single socket. If anything, the new threadrippers are simpler than the old ones, at least as far as Windows is concerned.

AMD needs to address the downsides of their Zen architecture and that requires some big changes. We haven't had major changes in the CPU market for a long time, so new OS updates to reflect new architectures are just something that we will need to deal with. Look at Intel and Tremont, having a big-little approach to x86. That will need big OS changes too to use correctly. It's just the way things are these days.Quote

19-11-2019, 15:16:50

NeverBackDown
My point is by constantly making it so developers have to constantly reoptimize for the changes just leaves performance on the table as less time is spent getting the most out of it. Just getting it to work is all they have time for.Quote

19-11-2019, 15:25:45

Daiyus
Quote:
Originally Posted by NeverBackDown View Post
My point is by constantly making it so developers have to constantly reoptimize for the changes just leaves performance on the table as less time is spent getting the most out of it. Just getting it to work is all they have time for.
It's a bit of a chicken/egg situation though. We have to dramatically change how we approach CPU's now that we're approaching the limit of silicon. Sure, that can make it more difficult for OS's, but at least it's pushing towards higher performance in the market overall.Quote

19-11-2019, 16:19:54

WYP
Quote:
Originally Posted by NeverBackDown View Post
My point is by constantly making it so developers have to constantly reoptimize for the changes just leaves performance on the table as less time is spent getting the most out of it. Just getting it to work is all they have time for.
All of the changes so far have been for the better, software that's optimised for Zen 1 will work great on Zen 2. They are based on the same core architecture. It's just the Zen 2 has fewer weaknesses and new strengths. A lot of the same rules will still apply.

What you're saying only would become a problem if an iteration of Zen was worse than its predecessors in some way. I don't see AMD regressing like that with Zen 3.

By "entirely new architecture", I'm sure AMD's talking about this in an RDNA way. RDNA is still just modified GCN, but it makes big enough changed in enough places to be something that's considered different/new. Software that runs on GCN doesn't run badly on RDNA.Quote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.