Leaks Suggest AMD AM5 Future Support for Ryzen 9000G "Gorgon Point" & EPYC 4005 "Grado" CPUs

[T0@st]

PC hardware watchers continue to pore over official AMD repositories and adjacent databases, in the hopes of finding unannounced next-gen technologies. Olrak29 and InstLatX64 have presented their latest Team Red-related findings; apparently reaching across futuristic desktop, mobile, and workstation product families. As outlined and interpreted by VideoCardz, several of these next-gen branches are already somewhat "known" properties—namely AMD's allegedly Zen 5-based Ryzen Threadripper "Shimada Peak" 9000WX (workstation) processor series. Following almost two years of leaks, an official introduction is expected to happen during Computex 2025. The Ryzen 9000G "Gorgon Point" desktop (Zen 5 + RDNA 3.5) APU series has turned up again; now "fully" linked to the AM5 socket platform (not a big surprise). The two leakers have also uncovered another rumored AM5-bound product lineup—"Grado" chips could be based on existing "Granite Ridge" foundations, but elevated to commercial/enterprise levels. These speculated basic/entry-level "EPYC 4005" processors are floated as natural successors to currently available 4004 forebears (related to Ryzen 7000 "Raphael" architecture).

Olrak29 and InstLatX64 have also found multiple mysterious FP8 socket-related Ryzen AI Mobile SoCs. "Krackan2" could be a cheaper refresh of current "Krackan Point" APUs—Tom's Hardware proposes smaller designs that sport fewer cores, and not configured with NPUs. Kepler_L2 has weighed in on the matter of three listed "Gorgon Point" IPs—he reckons that the third variant ("Gorgon Point3") will be a spin-off (aka refresh) of a "Krackan2" design. As suggested by insider knowledge, Team Red's convoluted scheme points to "Gorgon Point" being the sequel to "Strix Point." An FF5-based "Soundwave" processor design has appeared alongside the aforementioned futuristic Ryzen AI Mobile chipsets—industry whispers propose that AMD will be leveraging Arm architecture within a lower product tier. InstLatX64 pulled additional compelling information from AMD's Technical Information Portal—providing further insight into Ryzen AI "Medusa Point" APUs (Zen 6 + RDNA 3.5) being dreamt up, with a matching "larger footprint" FP10 platform.



View at TechPowerUp Main Site | Source

 

[Mrgravia]

9000G is very high on my watch list, as it's pretty on target for a small APU build for younger folks or family who don't game much.

Only question is about supported ram speeds, which will determine if I try for an asrock X600 build or make it with an B850 itx board.

 

[Nhonho]

How I wish Nvidia would enter the home APU market with high-performance iGPUs. I think only these high-performance APUs from Nvidia would force AMD to stop selling APUs with old/outdated iGPUs.

 

[ymdhis]

How I wish Nvidia would enter the home APU market with high-performance iGPUs. I think only these high-performance APUs from Nvidia would force AMD to stop selling APUs with old/outdated iGPUs.

RDNA 3.5 isn't exactly outdated, especially since RDNA4 was just 3 with more raytracing units and better clocks, and there are rumors of RDNA being completely axed in favor of a new universal compute+game arch.

 

[TheinsanegamerN]

RDNA 3.5 isn't exactly outdated, especially since RDNA4 was just 3 with more raytracing units and better clocks, and there are rumors of RDNA being completely axed in favor of a new universal compute+game arch.

Well based on the 9070/xt, those "3 more" RT units would be doing a much better job. rDA is at the end of its life and uDNA is coming next.

 

[Cheeseball]

RDNA 3.5 isn't exactly outdated, especially since RDNA4 was just 3 with more raytracing units and better clocks, and there are rumors of RDNA being completely axed in favor of a new universal compute+game arch.

While it does look like it, there are probably more significant changes under the hood. Remember the RX 9070 XT only has 128 ROPs on 64 CUs while the RDNA3 RX 7900 XTX had 192 ROPs on 96 CUs yet it punches hard above its weight that it can challenge it sometimes with only a 256-bit memory bus. RDNA4 is not just better RT cores and clocks.

 

[Launcestonian]

Very happy with my 8600G build, be nice to see if the FCLK on 9000G series can go higher than 2400 when on auto in bios like my 8600G can. The FLCK speed is paramount to current Zen architectures for memory performance.

 

[Nhonho]

AMD needs to stop selling us APUs with old, outdated integrated iGPUs. We've had to put up with archaic VEGA iGPUs for years on previous AMD APUs.
AMD has to realize that, if it sells low-performance iGPUs or iGPUs with outdated or removed features (without hardware video encode, for example), people will buy cheap video cards from Nvidia (like RTX 4060), which doesn't remove features from its cheaper video cards like AMD does.

 

[blinnbanir]

Very happy with my 8600G build, be nice to see if the FCLK on 9000G series can go higher than 2400 when on auto in bios like my 8600G can. The FLCK speed is paramount to current Zen architectures for memory performance.

I was shocked how fast the 8600G is in all things. A great job done by AMD.

AMD needs to stop selling us APUs with old, outdated integrated iGPUs. We've had to put up with archaic VEGA iGPUs for years on previous AMD APUs.
AMD has to realize that, if it sells low-performance iGPUs or iGPUs with outdated or removed features (without hardware video encode, for example), people will buy cheap video cards from Nvidia (like RTX 4060), which doesn't remove features from its cheaper video cards like AMD does.

Most new AMD APUs are RDNA. The 5600G was AM4. As far as features go what exactly do you mean? You have full access to AMD software and it's features using AMD software.