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

[Chrispy_]

Oh great, so AMD has completely thrown out the naming scheme it introduced for Mobile chips just 6 months ago:

They likely won't make any attempt at logic for desktop parts, even though we have the same mix of Zen2 and Zen3 APUs and CPUs (without graphics across the 5000-series, the 6000-series is AWOL and I wouldn't be surprised to see them intentionally confuse the 7000-series desktop lineup with Zen3+ APUs in the near future....

 

[AnotherReader]

Oh great, so AMD has completely thrown out the naming scheme it introduced for Mobile chips just 6 months ago:

The comments were about the desktop SKUs. Those haven't followed the abominable mobile naming scheme so far.

 

[AusWolf]

The 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.

 

[DemonicRyzen666]

AMD 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.

 

[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?

 

[Chrispy_]

This. 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.

The 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?!

 

[Tech Ninja]

7900xtx competes with 3080 not 4080

 

[Space Lynx]

AMD 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.

 

[Minus Infinity]

Given 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

 

[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

 

[N3M3515]

AMD 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...

The 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.

 

[eidairaman1]

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?

DDR5

 

[AusWolf]

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

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.

 

[AlwaysHope]

Oh goody, more new toys to look forward too next year.

 

[TumbleGeorge]

iGPU only. Next year for dGPU rDNA4.

Oh goody, more new toys to look forward too next year.

 

[AlwaysHope]

iGPU only. Next year for dGPU rDNA4.

I'm concerned with 8000 series SKUs

 

[Vayra86]

AMD 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.

7900xtx competes with 3080 not 4080

Reading comprehension is clearly not your strong suit. Even the 7900XT is above the 3080 In RT.

 

[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.

 

[AusWolf]

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.

Mixing VCache chiplets with regular ones doesn't work so well, as the 7800X3D proves against the 7900 and 7950X3D.

 

[Dimitriman]

Mixing 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.

 

[AusWolf]

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.

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).

 

[Dimitriman]

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).

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.

 

[AusWolf]

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.

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.

 

[Tek-Check]

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.

Navi 3.5 is mentioned in the context of AM5 so might be iGPUs only, also could be just Display / Media engine update.

Yes 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.

AMD 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.

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.

• 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.

7900xtx competes with 3080 not 4080

What kind of nonsense is this dude? Read proper reviews.

AMD Radeon RX 7900 XTX Review - Disrupting the GeForce RTX 4080

Navi 31 is here! The new $999 Radeon RX 7900 XTX in this review is AMD's new flagship card based on the wonderful chiplet technology that made the Ryzen Effect possible. In our testing we can confirm that the new RX 7900 XTX is indeed faster than the GeForce RTX 4080, but only with RT disabled.

www.techpowerup.com

I'm concerned with 8000 series SKUs

Why?

 

[Squared]

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.

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.