Monday, June 5th 2023

AMD Confirms Zen 5 will Get Ryzen 8000 Series Branding, "Navi 3.5" Graphics in 2024

AMD in one of its Meet the Experts presentations to the retail channel vendors, confirmed that the next-generation "Zen 5" architecture will see its desktop part branded under the Ryzen 8000 series. The company has known to skip a thousand-number sequence each generation for its mainstream-desktop series, the way it skipped Ryzen 4000 series nomenclature between the "Zen 2" based Ryzen 3000 "Vermeer" and "Zen 3" based Ryzen 5000 Vermeer; and more recently, between "Vermeer" and the "Zen 4" based Ryzen 7000 "Raphael," which makes this an interesting development. AMD's next-generation mainstream-desktop processor is expected to be codenamed "Granite Ridge," it will feature up to 16 "Zen 5" CPU cores across up to two CCDs. The processor I/O (and its 6 nm cIOD) is expected to be largely carried over, except that it could be upgraded with support for higher DDR5 memory speeds.

Another major disclosure is the very first mention of "Navi 3.5" This implies an incremental to the "Navi 3.0" generation (Radeon RX 7000 series, RDNA3 graphics architecture), which could even be a series-wide die-shrink to a new foundry node such as TSMC 4 nm, or even 3 nm; which scoops up headroom to dial up clock speeds. AMD probably finds its current GPU product stack in a bit of a mess. While the "Navi 31" is able to compete with NVIDIA's high-end SKUs such as the RTX 4080, and the the company expected to release slightly faster RX 7950 series to have a shot at the RTX 4090; the company's performance-segment, and mid-range GPUs may have wildly missed their performance targets to prove competitive against NVIDIA's AD104-based RTX 4070 series, and AD106-based RTX 4060 series; with its recently announced RX 7600 being based on older 6 nm foundry tech, and performing a segment lower than the RTX 4060 Ti.
Source: harukaze5719 (Twitter)
Add your own comment

67 Comments on AMD Confirms Zen 5 will Get Ryzen 8000 Series Branding, "Navi 3.5" Graphics in 2024

#26
AusWolf
AnotherReaderThe comments were about the desktop SKUs. Those haven't followed the abominable mobile naming scheme so far.
This. AMD desktop and mobile are like two separate companies when it comes to naming these days. I think it's stupid and misleading.
Posted on Reply
#27
DemonicRyzen666
TheinsanegamerNAMD doesnt know what it's targeting, given its own 6600xt undermines the 7600 at every turn. The 4060ti was a wet fart that showed how gimped nvidia's GPUs are, and the 7600 was an embarrassment that really showed off how little rDNA3 (or its compiler) brings to the table.
The lower RTX cards are in the same boat without the new software of D.L.S.S 3 F.G.
Posted on Reply
#28
mukumi
Am I missing it or there is no talk about compatibility of current b650 and x670 chipset with those ryzen 8000? Or is it obvious that it will work?
Posted on Reply
#29
Chrispy_
AusWolfThis. AMD desktop and mobile are like two separate companies when it comes to naming these days. I think it's stupid and misleading.
Definitely stupid and misleading.
AnotherReaderThe comments were about the desktop SKUs. Those haven't followed the abominable mobile naming scheme so far.
The line between desktop and mobile is very very blurry:
  • You have 3000/4000/5000-series APUs which are mobile chips with an IGP shoved into an AM4 package.
  • You have monolithic mobile parts like the Ryzen 3 4100, Ryzen 5 4500, Ryzen 5 5500 hiding in among the chiplet-based true AM4 parts.
  • You have the MCP desktop parts skipping 4000-series and 6000-series to adhere to the mobile naming convention, despite the desktop parts not following the mobile naming convention. Why?!
Posted on Reply
#31
Space Lynx
Astronaut
NordicAMD PLEASE! 7970 or bust!!!
we have come full circle from the early days of 1440p gaming being possible. I still remember now flashing my 7950 to a 7970 to play on my imported south korean 1440p monitor, lol

this may be my stop, next year. 8800x3d + 7970 xtx navi 3.5 or w.e it gets called.

i also may say fk it and go with 14th/15th gen intel and high end nvidia refresh late next year. we will see. for now im happy just chilling with my steam deck and gtx 1070 desktop.
Posted on Reply
#32
Minus Infinity
AnotherReaderGiven the purported specifications of the 7800 XT and the performance of the 7600 compared to the 6650 XT, I expect The 7800 XT to be about 5-10% faster than the 6800 XT. That explains why they haven't released it yet. They have to wait for the 6800 and the 6900 to go out of stock before they can sell something that has essentially the same performance for most games.
Keep your expectations low. The 7800XT is what we should expect of a 7700XT and is only targetting 4070, that's how disappointing this will be. It will be cheaper than 4070 but expensive for is what really a 7700XT. The 7700XT would only be targetting 4060 Ti which in itself is really a 4050 Ti.

AMD has fcuked up with the naming like Nvidia to hoodwink buyers and justify stupid prices;

The line up as it is and what it should be called:

7900XTX -> 7900XT. $899
7900XT -> 7800XT. $699
7800XT -> 7700XT. $549
7700XT -> 7600XT $399
7600 -> 7500XT. $229
Posted on Reply
#33
wheresmycar
TPU made no mention of AMD suggesting ~2026 AM5 support for Desktop processors. This is what i'm seeing everywhere else - correct?

"AMD in one of its Meet the Experts presentations to the retail channel vendors...." - sounds like a fancy tea party where some AMD officials/staff got drunk and probably said a little too much with a touch of optimism at play.

A more official statement would have been nice: SUE: "Hi, we're going to carry you all the way to 10800X3D by 2026 because you we love you. Now give us DA MANAYYYYYY!!"

Or, will it be a disappointment with 2026 triggered APUs/refreshes/poopiedoopies
Posted on Reply
#34
N3M3515
TheinsanegamerNAMD doesnt know what it's targeting, given its own 6600xt undermines the 7600 at every turn.
I used to think like that almost a decade ago.
Why didn't amd priced the 7600 at $200, that's the price of the 6600!

Every cycle that moment repeats, when the older gen is so fuckin' discounted that the new gen can't quite compete.
Yet the true comparison is what was the msrp of the 6600, $330, now the 7600 debuts at $60 less and brings +25% performance. I'm not saying they have a winner there, not even close. But that moment always repeats.
Before anyone comments about the 7600 being a 6600 xt replacement, i won't delve in to that, i'm guiding by name, and expecting a 7600 xt.

Like always, the 7600 in a few months will be 230 and by the time the 8600 comes it will be at $200. Then everyone will be losing their mind because the 8600 msrp will be $300 and only be 30%-40% faster than the 7600.

It is what it is...
Minus InfinityThe 7800XT is what we should expect of a 7700XT and is only targetting 4070
That would be a new level of stupid, if the 7800XT is not at least 15% faster than the 6800XT. The 7600 is 25% faster than the 6600.
Posted on Reply
#35
eidairaman1
The Exiled Airman
mukumiAm I missing it or there is no talk about compatibility of current b650 and x670 chipset with those ryzen 8000? Or is it obvious that it will work?
DDR5
Posted on Reply
#36
AusWolf
Minus InfinityKeep your expectations low. The 7800XT is what we should expect of a 7700XT and is only targetting 4070, that's how disappointing this will be. It will be cheaper than 4070 but expensive for is what really a 7700XT. The 7700XT would only be targetting 4060 Ti which in itself is really a 4050 Ti.

AMD has fcuked up with the naming like Nvidia to hoodwink buyers and justify stupid prices;

The line up as it is and what it should be called:

7900XTX -> 7900XT. $899
7900XT -> 7800XT. $699
7800XT -> 7700XT. $549
7700XT -> 7600XT $399
7600 -> 7500XT. $229
AMD doesn't compete because they can't. Nvidia doesn't compete because they can't be bothered. The result is lacklustre products from both, combined with unreasonably high prices from Nvidia.
Posted on Reply
#37
AlwaysHope
Oh goody, more new toys to look forward too next year. :laugh:
Posted on Reply
#38
TumbleGeorge
iGPU only. Next year for dGPU rDNA4.
AlwaysHopeOh goody, more new toys to look forward too next year. :laugh:
Posted on Reply
#39
AlwaysHope
TumbleGeorgeiGPU only. Next year for dGPU rDNA4.
I'm concerned with 8000 series SKUs
Posted on Reply
#40
Vayra86
NordicAMD PLEASE! 7970 or bust!!!
To be fair... they should do this naming wise. They could easily make it a repeat of Kepler refresh battlefields, which was a pretty good time for GCN.

They even have the VRAM advantage just the same as they did back then lol, and it'll be a history repeats affair entirely.
Tech Ninja7900xtx competes with 3080 not 4080
Reading comprehension is clearly not your strong suit. Even the 7900XT is above the 3080 ;) In RT.
Posted on Reply
#41
Dimitriman
I wonder why AMD doesn't make the CPU as 8 Zen5 VCache cores + 16 Zen5c/4c cores.

Why not compete with Intel that way? They can still offer 16 full zen5 core CPUs and it would greatly differentiate the VCache variants from the regular.
Posted on Reply
#42
AusWolf
DimitrimanI wonder why AMD doesn't make the CPU as 8 Zen5 VCache cores + 16 Zen5c/4c cores.

Why not compete with Intel that way? They can still offer 16 full zen5 core CPUs and it would greatly differentiate the VCache variants from the regular.
Mixing VCache chiplets with regular ones doesn't work so well, as the 7800X3D proves against the 7900 and 7950X3D.
Posted on Reply
#43
Dimitriman
AusWolfMixing VCache chiplets with regular ones doesn't work so well, as the 7800X3D proves against the 7900 and 7950X3D.
But that is also my point though, instead they should mix big zen vcache cores with little C cores so that the windows scheduler can more easily separate them just like they already do with Intel.
Posted on Reply
#44
AusWolf
DimitrimanBut that is also my point though, instead they should mix big zen vcache cores with little C cores so that the windows scheduler can more easily separate them just like they already do with Intel.
AFAIK, the scheduler already separates them with the proper driver installed, but the 7800 runs miles around its bigger siblings anyway (in games, that is).
Posted on Reply
#45
Dimitriman
AusWolfAFAIK, the scheduler already separates them with the proper driver installed, but the 7800 runs miles around its bigger siblings anyway (in games, that is).
Sure but AMD is sitting on this "c" type core technology since 2 gens now and is not doing anything on the client segment with it. Intel is about to bring 8+32 cores to the market and AMD will remain with just 16 big cores which won't win either the single or the multi threaded benches. It will just be more energy efficient. I would like to see a 8 + 16 from AMD at some point.
Posted on Reply
#46
AusWolf
DimitrimanSure but AMD is sitting on this "c" type core technology since 2 gens now and is not doing anything on the client segment with it.
Maybe it's not good enough for public release, or there's some complications. Personally, I'm not a fan of heterogenous designs and relying on the scheduler to decide what's what, so I'm OK with what we have, especially if it's as good in gaming as VCache technology is.
Posted on Reply
#47
Tek-Check
john_RX 6950 XT 5120 cores, RX 7900 XT 5376 cores, little performance improvement.
6900XT vanilla model is compared to 7900XTX vanilla model. The same price, but RDNA3 card is 50% faster in 4K. It's quite a decent uplift.
If they ever release 7950XTX, that would the a card to compare with 6950XT, as refresh cards have beefed up specs and performance.

We know that 7900XTX can reach 3GHz in non-gaming workloads, such as Blender. If AMD pursued a new stepping of Navi 31 die (they must be testing it in labs by now), we could see interesting results on refresh cards. It remains to be seen whether they succeed in this task.
Snoop05Navi 3.5 is mentioned in the context of AM5 so might be iGPUs only, also could be just Display / Media engine update.
TumbleGeorgeYes Ryzen 8000 series was mentioned with rDNA3.5 for iGPU.
Both mobile Strix Point and desktop Granite Ridge will have enhanced RDNA3 graphics. It could be called RDNA3.5 for desktop or 'RDNA3+' for mobility, or one name for all SKUs. AMD is flirting with '0.5' and '+' labels. It does not really matter. Strix will be introduced at CES 2024 and will feature (refined?) AIE, which does take a sizebale space on a die. Desktop Zen5 is unlikely to get AIE until I/O die receives a major upgrade.

TheinsanegamerNAMD doesnt know what it's targeting, given its own 6600xt undermines the 7600 at every turn. The 4060ti was a wet fart that showed how gimped nvidia's GPUs are, and the 7600 was an embarrassment that really showed off how little rDNA3 (or its compiler) brings to the table.
It's just not well-priced at the moment. It will be a good card below $250.
It's like TV models gen-to-gen. You get a few new perks, a bit more brightness, one or two new codecs, 2-3W more on speakers.
Not a revolution, just a bit of evolution.
Chrispy_The line between desktop and mobile is very very blurry:
  • You have 3000/4000/5000-series APUs which are mobile chips with an IGP shoved into an AM4 package.
  • You have monolithic mobile parts like the Ryzen 3 4100, Ryzen 5 4500, Ryzen 5 5500 hiding in among the chiplet-based true AM4 parts.
That's ok. Nothing wrong with it, as soon as it falls into correct class and performance tier. There should always be flexibility with using some dies that had been overmanufactured or not capable of higher tier performance as originally intended. The same happens in many other industries...

If a shape, size or taste of fresh tomato does not fall into intended retail class, it's packaged into different class, cut into salad, dried or crushed for sauces. Better use than throw away as waste. The same applies to silicon. If only 4 cores work on 8 core chiplet, it should never be thrown away, but used in lower power devices such as NAS, mini-PC, entry notebook/desktop, etc.
Chrispy_
  • You have the MCP desktop parts skipping 4000-series and 6000-series to adhere to the mobile naming convention, despite the desktop parts not following the mobile naming convention. Why?!
It's becoming more complex. Several MCP desktop parts became mobile CPUs Dragon Range. Should they name Dragon Range SKUs 7000 and then Phoenix 8000? Hell, no. That would be even more confusing. 7000-series are 2022/2023 products on several architectures for many segments.

Series are usually based on time cycles or calendar year, as variety of products are released. Architecture still plays a role as diversity of products and the number of staggered release cycles increase. It's not easy with naming scheme if product/family/architecture cadence does not fall neatly into 12 or 24 month cycles. Intel also released Alder Lake-N series in 2023, in the middle of Raptor Lake generation. This happens.

I actually quite like new naming scheme for 7000, 7020, 7030, 7035, 7035G, 7040, 7040G and 7045 SKUs, as this includes specific architectures to highest possible extent. There will always be one or two odd SKUs that do not fit neatly, but that's fine. The world is not an ideal place.

In 2024, there will be the same situation: 8000 for desktop, 8035 for Rembrandt successor, 8040 for Hawk Point, etc. In January 2025, Hawk Point successor will be called 9040, Strix Sarlak 9050, Fire Range 9055, etc.
Tech Ninja7900xtx competes with 3080 not 4080
What kind of nonsense is this dude? Read proper reviews.
www.techpowerup.com/review/amd-radeon-rx-7900-xtx/32.html
AlwaysHopeI'm concerned with 8000 series SKUs
Why?
Posted on Reply
#48
Squared
AusWolfMaybe it's not good enough for public release, or there's some complications. Personally, I'm not a fan of heterogenous designs and relying on the scheduler to decide what's what, so I'm OK with what we have, especially if it's as good in gaming as VCache technology is.
I've heard that Zen4c is pretty much Zen4 with less cache. I've always pictured that it's Zen4 but with the layout more computer-generated, so it's more area-efficient but can't clock as high. With these differences, I think a Zen4c core would perform very similar to a Zen4 core that's been clocked down because many cores are loaded and they can't all boost. So in an AMD CPU with a Zen4 chiplet and a Zen4c chiplet, if all cores are loaded, scheduling a new independent thread on a Zen4c core probably wouldn't result in much less performance than a Zen4 core. So as long as the scheduler prioritizes the Zen4 cores until most of them are busy, I imagine there won't be any situations that see a significant loss in performance.
Posted on Reply
#49
Tek-Check
DimitrimanI wonder why AMD doesn't make the CPU as 8 Zen5 VCache cores + 16 Zen5c/4c cores.

Why not compete with Intel that way? They can still offer 16 full zen5 core CPUs and it would greatly differentiate the VCache variants from the regular.
The number of cores matters less. Addressable threads matter more in many workloads. 16C/32T 7950X is as good in MT workloads as 24C/32T 13900K is, and Ryzen uses less power in those workloads.

7700X is 8C/16T. It competes against 13600K with 14C/20T. It has 6 cores less, but it is only 5% slower in MT workloads. 6 cores less for 5% less! Do you get the vibe?
DimitrimanBut that is also my point though, instead they should mix big zen vcache cores with little C cores so that the windows scheduler can more easily separate them just like they already do with Intel.
Big cores+c cores+V cache is more complex combination that they are testing in labs. You will need to be patient for that.
Once AMD first releases vanilla big cores+c cores, Windows scheduler will not have any problems, as c cores have the same instructions and HT, just less L1/L2/L3 memory. Those are simply smaller cores, but different than Intel's little cores. AMD's big and c cores both support HT and AVX512. So, 8+8 SKU will have 32 threads, unlike Intel's 24 threads on 8+8 cores. AMD did not want to go Intel's way with c cores and make them single-threaded because this creates more problems with execution of instructions. That's why Intel cancelled AVX512 on consumer big-little CPUs. AMD's version of efficient c-cores will be far more capable in MT workloads than little cores
DimitrimanSure but AMD is sitting on this "c" type core technology since 2 gens now and is not doing anything on the client segment with it. Intel is about to bring 8+32 cores to the market and AMD will remain with just 16 big cores which won't win either the single or the multi threaded benches. It will just be more energy efficient. I would like to see a 8 + 16 from AMD at some point.
Which two generations? Nonsense. The first SKU with c-cores will be Bergamo with 128 c cores, to be released this summer. The CPU is already in test systems of hyperscalers. It's the first ever product with 16-core chiplets, each with 8 core CCX.

Most advanced and complex technologies usually come to server space that needs it, and later trickle down consumer segment.
Posted on Reply
#50
wheresmycar
Tek-CheckThe number of cores matters less. Addressable threads matter more in many workloads. 16C/32T 7950X is as good in MT workloads as 24C/32T 13900K is, and Ryzen uses less power in those workloads.

7700X is 8C/16T. It competes against 13600K with 14C/20T. It has 6 cores less, but it is only 5% slower in MT workloads. 6 cores less for 5% less! Do you get the vibe?


Big cores+c cores+V cache is more complex combination that they are testing in labs. You will need to be patient for that.
Once AMD first releases vanilla big cores+c cores, Windows scheduler will not have any problems, as c cores have the same instructions and HT, just less L1/L2/L3 memory. Those are simply smaller cores, but different than Intel's little cores. AMD's big and c cores both support HT and AVX512. So, 8+8 SKU will have 32 threads, unlike Intel's 24 threads on 8+8 cores. AMD did not want to go Intel's way with c cores and make them single-threaded because this creates more problems with execution of instructions. That's why Intel cancelled AVX512 on consumer big-little CPUs. AMD's version of efficient c-cores will be far more capable in MT workloads than little cores

Which two generations? Nonsense. The first SKU with c-cores will be Bergamo with 128 c cores, to be released this summer. The CPU is already in test systems of hyperscalers. It's the first ever product with 16-core chiplets, each with 8 core CCX.

Most advanced and complex technologies usually come to server space that needs it, and later trickle down consumer segment.
Hi Tek-Check, tech-checking time!



Without context or just briefly observing the above, the less informed notion being 600-series "consumer level" boards will now be officially supported until 2026, beyond the initial 2025 plan. The immediate thrill being maybe another 2 Generations support beyond 8000. Digging deeper, its a page pulled from a server deployment plan of action and to make matters worse the road-mapped parts displayed from 2022-2024 are APUs (assuming the "+" signifies "integrated" only)

So what on earth are we looking at here? I've lost my marbles with this sort of mind-trucking disorientation and hope someone can shed some light and help me find them (the marbles that is)
Posted on Reply
Add your own comment
Nov 12th, 2024 06:22 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts