AMD Phoenix AM5 APUs to Get Ryzen 8000 Series Branding, Company Readies 5000GT Series for AM4

[btarunr]

AMD is giving final touches to its first APUs for the Socket AM5 desktop platform. A report by Sakhtafzar Magazine suggests that the company could give processor models in the series Ryzen 8000G numbering, instead of the previously thought 7000G series. The company is preparing as many as 14 processor models spanning the 4 nm "Phoenix" and "Phoenix 2" monolithic dies. Both chips combine "Zen 4" CPU cores with an iGPU based on the RDNA 3 graphics architecture. While the current Ryzen 7000 series "Raphael" desktop processors feature integrated graphics, AMD doesn't consider them APUs, as their iGPU are just about enough for non-gaming desktop use cases. APUs are designed for entry-level gaming.

The "Phoenix" silicon has up to 8 "Zen 4" CPU cores, and an iGPU with up to 12 RDNA3 compute units. This chip is powering the Ryzen 5 8600G, Ryzen 7 8700G, their PRO variants, and their respective "GE" (energy efficient) sub-variants. The "Phoenix 2" silicon barely qualifies as an APU, as its iGPU only has 4 RDNA3 compute units (compared to the 2 RDNA2 CUs on the "Raphael" iGPU. It also has a maximum CPU core count of 6, from which two are "Zen 4" cores that can sustain higher boost frequency bins, and four are "Zen 4c" cores which run at lower clock speeds (albeit with an identical IPC and ISA). AMD is using "Phoenix 2" on the desktop platform to carve out several sub-$150 class processor models across the Ryzen 5 and Ryzen 3 brands; a package with a monolithic "Phoenix 2" die probably has a lower bill of materials (BOM) than a "Raphael" multi-chip module.



The source also claims to have gaming performance comparisons of the Ryzen 8000G "Phoenix" desktop APU's iGPU, compared to the Ryzen 7 5700G "Cezanne" Socket AM4 desktop APU, where it posts performance gains between 40% to 200% higher. This is because "Cezanne" packs a much older iGPU based on the Vega graphics architecture, while "Phoenix" uses the 3 generations ahead RDNA3.

Sticking with the AM4 platform, and AMD is planning to release several new processor models for the older platform, including the Ryzen 7 5700X3D and 5500X3D that feature the 3D Vertical Cache technology that benefits gaming performance; and a handful new APUs, namely the 5700GT and 5600GT. At this point, it's not known what the "T" brand extension signifies in AMD nomenclature. Intel uses "T" to denote energy-efficient SKUs, but AMD uses "E" for that job.

AMD is expected to announce the new Socket AM5 and AM4 processors on January 31, the article says.

View at TechPowerUp Main Site | Source

 

[kapone32]

Maybe I should get a decent B650 while they are on sale. I expect them to announce new MBs for this lineup as well. Probably in the B650 range but even A620 boards will become a lot more popular if AMD actually does what is reported. As the driver on AMD is unified these APUs should age quite well indeed.

 

[Shou Miko]

I hope to see real fps numbers when the cpu's get reviewed because if they only "shine" in 1080p it will be a couple of generations before hopefully they can do 1440p with the same settings.

 

[wNotyarD]

Would the GT-suffix be APU's with 3D V-Cache, but without making them GX3D which would be quite the mouthful?

 

[Denver]

Would the GT-suffix be APU's with 3D V-Cache, but without making them GX3D which would be quite the mouthful?

I think they will just push the iGPU to the limit and sell it as a new product.

 

[TheinsanegamerN]

I think they will just push the iGPU to the limit and sell it as a new product.

Just a mild OC at most. Everything else they've done has been rewarmed leftovers.

 

[kapone32]

I hope to see real fps numbers when the cpu's get reviewed because if they only "shine" in 1080p it will be a couple of generations before hopefully they can do 1440p with the same settings.

1440P in all scenarios will still be a pipe dream. These are aimed directly at users who want to get handheld performance without the entry cost of getting a handheld and new users looking to get in on the hobby.

 

[Kyan]

So it's the end of my 8800X3D dream ?

 

[kapone32]

So it's the end of my 8800X3D dream ?

Nope that will probably come in the late spring or early summer with B750 boards.

 

[Kyan]

Nope that will probably come in the late spring or early summer with B750 boards.

You think that they will release The 8000G before the "classic" 8000 ?

 

[kapone32]

You think that they will release The 8000G before the "classic" 8000 ?

That has been the practice before.

 

[bug]

I will be blunt: AMD's naming scheme sucks.
I just had to buy a laptop and I discarded AMD simply because no website will let you search for 7x40. There aren't too many SKUs to choose from anyway, lumping them all together may help AMD sell to the non-informed customers, but will do little else. Wth is wrong with using one prefix for one architecture?

 

[DeathtoGnomes]

I will be blunt: AMD's naming scheme sucks.
I just had to buy a laptop and I discarded AMD simply because no website will let you search for 7x40. There aren't too many SKUs to choose from anyway, lumping them all together may help AMD sell to the non-informed customers, but will do little else. Wth is wrong with using one prefix for one architecture?

That would be smart and easy, not something AMD is known for when it comes to naming.

 

[mtosev]

I'm quite surprised that amd still supports and is releasing new CPUs for the AM4 platform.

 

[the54thvoid]

I will be blunt: AMD's naming scheme sucks.
I just had to buy a laptop and I discarded AMD simply because no website will let you search for 7x40. There aren't too many SKUs to choose from anyway, lumping them all together may help AMD sell to the non-informed customers, but will do little else. Wth is wrong with using one prefix for one architecture?

Yeah, totally agree. The ordinary consumer will surely think an 8xxx is better than a 7xxx? It's just smoke and mirrors.

 

[btarunr]

Would the GT-suffix be APU's with 3D V-Cache, but without making them GX3D which would be quite the mouthful?

I don't think the CZN die has TSV sites for stacked cache.

 

[R0H1T]

Wth is wrong with using one prefix for one architecture?

Well they use the third digit for that, don't they? Also not defending AMD here but using one numbering convention(10th gen Intel?) for different uarch isn't something new ~ happened with AMD in the past as well as Intel.

Part of it is to keep the OEM's happy but more importantly the majority of plebs do infer bigger==better

 

[kapone32]

I'm quite surprised that amd still supports and is releasing new CPUs for the AM4 platform.

That is exactly what Lisa Su said.

 

[Count von Schwalbe]

I hope to see real fps numbers when the cpu's get reviewed because if they only "shine" in 1080p it will be a couple of generations before hopefully they can do 1440p with the same settings.

2x 64bit DDR5 channels is not enough for anything over 1080p. Even with DDR4-8000 it has less memory bandwidth than a 4060; adding CUs won't help at higher resolutions - just faster at lower resolutions.

Would the GT-suffix be APU's with 3D V-Cache, but without making them GX3D which would be quite the mouthful?

I doubt it - the CCD based CPUs have the TSVs for the extra cache chiplet on top, and AFAIK the monolithic ones do not. I also doubt there would be the physical room without overlapping the cores, as the cache is considerably smaller.

 

[Squared]

Yeah, totally agree. The ordinary consumer will surely think an 8xxx is better than a 7xxx? It's just smoke and mirrors.

Intel and AMD have for years released a new mobile "generation" every year (like 7xxx -> 8xxx) even when there wasn't anything new, and in 10th gen Intel provided Sunny Cove and gen11 graphics for the U series when everything else was some Skylake derivative. But what AMD is doing now is worse, selling Zen 4 and RDNA3, Zen 3+ and RDNA2, Zen 3 and Vega, and Zen 2 and Vega all under the 7xxx umbrella. They did provide enthusiasts a way to know the CPU microarchitecture with the 7x4x naming scheme, but as someone mentioned the stores didn't offer a filter for this. Moreover if a user settles for 7x3x, it could be Zen 3+ and RDNA2, or Zen3 and Vega.

I feel like AMD is using this naming scheme in part to pretend to be ahead of Intel by more than they really are. Many enthusiasts point out that AMD is using TSMC N5 and N4 while Intel is still stuck with Intel 7. But a lot of AMD's latest 7xxx chips are not 7x4x, so a lot of what AMD is still making is N6 and N7. So if Intel actually ships Meteor Lake on Intel 4 next month for U-series laptops, Intel may actually be pretty close behind AMD at least in the overall laptop market.

 

[Random_User]

Nothing certain being said about the AM4 APUs. But this nonetheless is the great thing. Might actually be the great answer, or even replacement for a EOL-ing Vega archhitecture. Maybe this is another sign of it is about to go away soon.

But what does this mean. Is it proof, that AM4 can actually run Ze4? Or this is uncertainty in AM5, and its motherboard mayhem?

My guess the NPU is nothing else, but defective MI300.

I will be blunt: AMD's naming scheme sucks.
I just had to buy a laptop and I discarded AMD simply because no website will let you search for 7x40. There aren't too many SKUs to choose from anyway, lumping them all together may help AMD sell to the non-informed customers, but will do little else. Wth is wrong with using one prefix for one architecture?

Exactly. It would be somewhat undestandable, if the CPU was Ze4+, or iGPU was RDNA3.5/4/ But it's exacly the same old chip, that mobile has for a year already. Not only that it's very late to the party. But also their greedy marketing makes AMD huge disservice. They have great product, but they twist and mess its naming to the point, that many would stop bother altogether and will simply avoid.

I wonder if the salespeople can get clue themselves what generation they sell without use of that decoder wheel. Surely it's somewhat better than intel's naming without one. But this is yet a wrong achievement in wrong comptetition. This is silly, that people need a decoder for naming scheme, in order to know if that is not "sh*t in bag", they are buying.

Intel and AMD have for years released a new mobile "generation" every year (like 7xxx -> 8xxx) even when there wasn't anything new

But the thing is, they went even with Zen 3 (5xxx) Ryzen series, for both desktop and mobile. So they can, if they want.

Yeah, totally agree. The ordinary consumer will surely think an 8xxx is better than a 7xxx? It's just smoke and mirrors.

Indeed. The first number should be the µacrhitecture generation, as it more or less was aligned for previous six gens of Ryzen.

 

[Dr_b_]

will compute performance of the 8 core APU parts be similar to the 7000X series?

 

[evernessince]

I will be blunt: AMD's naming scheme sucks.
I just had to buy a laptop and I discarded AMD simply because no website will let you search for 7x40. There aren't too many SKUs to choose from anyway, lumping them all together may help AMD sell to the non-informed customers, but will do little else. Wth is wrong with using one prefix for one architecture?

All the mobile naming schemes from AMD, Intel, and Nvidia are god awful and misleading. It doesn't really matter which brand you buy, they all perpetuate it.

 

[Denver]

will compute performance of the 8 core APU parts be similar to the 7000X series?

Probably not, APUs have less cache and the low end (Phoenix 2) APUs have Zen4C cores whose maximum clock appears to be 3.5Ghz.

 

[TechLurker]

Here's hoping that an AM4 5900X3D and 5950X3D are announced too. Just let AM4 go out with an encore performance.