After Nvidia has once again refreshed its current generation (“Ada Lovelace”) with the Geforce RTX 4080 Super, Geforce RTX 4070 Ti Super and Geforce RTX 4070 Super and made it interesting for gamers with a slightly better price-performance ratio and AMD in particular with its comparatively cheap Radeon RX 7900 XT, the successor plan has already been made and has long been on everyone’s lips.
Rumors about Radeon RX 8000 and Geforce RTX 5000
The usually well-informed rumor mill once again has the latest rumors about the next-gen graphics cards in the AMD Radeon RX 8000 (“RNDA 4”) series with Navi 4x and Nvidia Geforce RX 5000 (“Blackwell”) with GB20x series, as now Once again the YouTube channel Moore’s Law Is Dead can report.
Radeon RX 8000 with Navi 4x based on RDNA 4
As PCGH had already reported in November 2023, the Radeon RX 8000 will be based on the two graphics processors Navi 48 and Navi 44, which, unsurprisingly, use the upcoming graphics architecture RDNA 4.
Radeon RX 8000: First facts about RDNA 4 and many rumors about Navi 44 and Navi 48
For the first time, information about RDNA 4 can be considered facts, but in addition to solid information, there are also many wild rumors about Navi 44 and Navi 48.
After the first preliminary information was shared by RedGamingTech, it has now been largely confirmed by Moore’s Law Is Dead and supplemented with further details. Accordingly, the two graphics processors should have the following technical specifications at launch.
Navi 48*
MonolithicUp to 350 mm Die-SizeUp to 4,096 Shader Units (“ALUs”)Up to 32 Workgroup Processors (“WGPs”)Up to 64 Compute Units (“CUs”)Up to 48 MiByte Infinity CacheUp to 20 GiByte MemoryUp to 3, 3GHzTSMC N4P
*) not confirmed.
The full expansion of Navi 48 with 4,096 shader units is said to have a grid performance roughly between the AMD Radeon RX 7900 XT and the Radeon RX 7900 XTX, while the ray tracing performance should be significantly higher. In the new portfolio, Navi 48 will be used on the Radeon RX 8800 series.
Navi 44*
MonolithicUp to 210 mm Die-SizeUp to 2,560 Shader Units (“ALUs”)Up to 20 Workgroup Processors (“WGPs”)Up to 40 Compute Units (“CUs”)Up to 24 MiByte Infinity CacheUp to 16 GiByte MemoryTSMC N4P
*) not confirmed.
The full expansion of Navi 44 with 2,560 shader units is said to have a grid performance roughly between the AMD Radeon RX 7600 XT and the Radeon RX 7800 XT, while the ray tracing performance should be significantly higher. In the new portfolio, Navi 44 will be used on the Radeon RX 8700 series.
Source: Moore’s Law Is Dead Whether AMD decides to attack the high-end segment again and unpacks Navi 41 with GDDR7 has still not been decided according to Moore’s Law is Dead and RadGamingTech.
Rumors about RDNA 4: AMD is said to have canceled the Radeon RX 8900 and Radeon RX 8800, or maybe not?
In addition to Navi 41, AMD is said to have completely canceled Navi 42 and thus the potential “Radeon RX 8900” and “Radeon RX 8800”, according to the latest rumors.
As Twitter users @Kepler_L2, @All_The_Watts and @uzzi38, who are known for such information, have more or less indicated, the Radeon RX 8000 based on the upcoming RDNA 4 architecture will only rely on smaller graphics chips, while the Navi 41 and Navi 42 will were deleted.
Source: Videocardz With regard to the rumors, it is repeatedly stated that this decision would be related to AMD’s greater focus on AI accelerators. AMD CEO Dr. Lisa Su has already confirmed this several times, but the consumer hardware segment has never been discussed in this context.
Still to be enjoyed with extreme caution
All of this information should currently be viewed with the greatest caution, as the sources involved have been wrong and wrong in the past. In addition, AMD has not said a word about the possible deletion of its high-end class (“Ultra-Enthusiast Class”) and upper class (“Enthusiast Class”). All information can therefore clearly be classified as rumors.
Geforce RTX 5000 is also simmering in the rumor mill
Rumors about Nvidia’s next-gen graphics cards from the Geforce RTX 5000 series (“Blackwell”) have been in the headlines for months. PCGH also tries to classify these seriously based on the current facts.
Nvidia should also rely on chiplets
As can be seen from the rumor mill around @kopite7kimi and other leakers, Nvidia is also said to be switching to a multi-chiplet module (“MCM”) and specifically the graphics units of the upcoming Geforce RTX 5000 (“Blackwell”), also known as “Ada Lovelace Next”, fundamentally remodel accordingly. This concept is known to already be in use with AMD’s Navi 31 and Navi 32 GPUs.
Furthermore, the number of Graphics Processing Clusters (“GPCs”) and Texture Processing Clusters (“TPCs”) will not change much, but their internal structure will be fundamentally revised. This process could also be observed during AMD’s generation change from RDNA 2 to RDNA 3.
However, the rumor mill considers it rather unlikely that Nvidia will switch from TSMC back to Samsung Foundry and its 3 nm node (“3GAA”), which is targeted for 2025, for the production of its graphics processors.
GB202, GB203, GB205, GB206 and GB207 for Blackwell
In the meantime, the user “Panzerlied” from the Chiphell forum, which is known for such information, has also confirmed that he has information about the graphics processors GB202, GB203, GB205, GB206 and GB207 for the upcoming graphics cards in the Geforce RTX 5000 series (“Blackwell “), which is currently listed as “Ada Lovelace Next” on an Nvidia roadmap. Nvidia itself has not yet commented on this.
Those: Nvidia
Geforce RTX 5090 and 5080 are probably the start
The graphics processors AD102, AD103, AD104, AD106 and AD107 (“Ada Lovelace”) will most likely be followed by the new GPUs GB202 and GB203 (“David Blackwell”). Numerous further expansion stages with an even higher identifier are also expected here, which are planned for the Geforce RTX 5070 (Ti) and the smaller model series. Nvidia should stay true to its formula.
GDDR7 with 36 GiBit/s and PCIe 5.0 x16 are considered set
In addition to a connection via PCIe 5.0 x16, the new GDDR7 graphics memory will be used at least for the Geforce RTX 5090 and Geforce RTX 5080. This should achieve up to 36 gigabits per second and rely on three-stage pulse amplitude modulation (“PAM-3”) for signal transmission. It can be assumed that energy efficiency will be improved by around 25 percent in this sub-area. GDDR6X, on the other hand, already uses PAM-4.
Source: Panzerlied via Chiphell The number sequence “23567” stands for GB202, GB203, GB205, GB206 and GB207 The effective memory bandwidth would also benefit significantly from the fast GDDR7 memory with up to 36 GiBit/s:
128-Bit @ 36 Gbps: 576 GiByte/s192-Bit @ 36 Gbps: 846 GiByte/s256-Bit @ 36 Gbps: 1.152 GiByte/s320-Bit @ 36 Gbps: 1.440 GiByte/s384-Bit @ 36 Gbps: 1.728 GiByte/s512-Bit @ 36 Gbps: 2.304 GiByte/s
As can be seen from several entries in the Chiphell forum, Nvidia could also take a two-pronged approach:
GB202: GDDR6X (“PAM-4”) mit 512-BitGB203: GDDR6X (“PAM-4”) mit 384-BitGB205: GDDR7 (“PAM-3”) mit 256-BitGB206: GDDR7 (“PAM-3”) mit 192-BitGB207: GDDR7 (“PAM-3”) mit 128-Bit
But even this is usually just speculation, which is based on information that has been leaked so far, but cannot yet be viewed as binding. Nvidia itself has not yet said a word about the next generation of its Geforce graphics cards.
Performance predictions are almost impossible
The rumor mill predicts that the upcoming top model, the Geforce RTX 5090, will have up to 2.5 times the performance of an already very fast Geforce RTX 4090. However, great caution is advised here for the time being, because it is currently completely unclear whether DLSS 2 or even DLSS 3 with frame generation will be included in the equation. Performance predictions are currently almost impossible.
Geforce RTX 5090 with up to 18,432 CUDA cores
The specifications assigned to the Geforce RTX 5090 are also currently purely speculative. Accordingly, in the future it will go from 128 streaming multiprocessors and 16,384 shader units to 144 streaming multiprocessors and 18,432 CUDA cores. In addition, the L2 cache will be increased from 72 MiByte to 96 MiByte and the GPU clock speed will increase to more than 3 GHz. Videocardz has already compared the graphics processors of the three generations.
Source: Videocardz Great caution is still required with regard to the rumors about the Geforce RTX 5000 (“Blackwell”); the information is still highly speculative and varies greatly from source to source.
When will Radeon RX 8000 and Geforce RTX 5000 be released?
As Moore’s Law Is Dead would like to have learned, the Radeon RX 8000 series graphics cards based on the RDNA 4 architecture are scheduled to appear between the third and fourth quarters of 2024 and are expected to appear at Computex 2024, which will take place from June 4th to 7th, 2024 in Taipei is taking place. The Geforce RTX 5000, on the other hand, should follow at the end of the year and, due to Nvidia’s currently enormous performance lead, will not be launched on the market until the beginning of 2025.
Source: Moore’s Law Is Dead Further exciting rumors can be found in the 25-minute YouTube video from Moore’s Law Is Dead, which, in addition to the Radeon RX 8000 and Geforce RTX 5000, also takes a closer look at the possible technical specifications of the potential Playstation 5 Pro. But this information is definitely not watertight.
Recommended editorial contentHere you will find external content from [PLATTFORM]. To protect your personal data, external integrations will only be displayed if you confirm this by clicking on “Load all external content”:Load all external contentI agree to external content being displayed to me. This means that personal data is transmitted to third-party platforms. Read more about our privacy policy.
Your opinion is asked!
What is your opinion on this topic? The PCGH editorial team would be pleased to hear your well-founded opinion in the comments to this report. To comment, you must be logged in to PCGH.de or the Extreme forum. If you don’t have an account yet, you can register here without obligation. Please note the applicable forum rules when commenting.
Those: Moore’s Law Is Dead, RedGamingTech, All_The_Watts, Kepler_L2