We have officially met the data of the star GPU of this new generation NVIDIA RTX 40 Series, the AD102 on which the most powerful is based NVIDIA RTX 4090. But we also saw how the 16 and 12 GB NVIDIA RTX 4080 they would have a different GPU, the AD103 and AD104 respectively of which we had not known more details. Ryan Smith from Anandtech has left us this information on his Twitter account where we see that the smallest model, the AD104, is even superior to the top of the range of the previous generation GA102.
The AD103, in its complete configuration, has 45.9 billion transistorscount with one total of 10,204 CUDA cores and 80 SMs. Its L2 cache is 64 MB and the chip size is 378.6mmtwo. This AD103 is used by the 16 GB NVIDIA RTX 4080 limiting CUDA cores to 9,728.
The smallest of those presented, the AD104have higher number of transistors than the GA102, 35.8 billion in AD104 compared to 28.3 billion in GA102. All this in half the surface, the AD104 measures 294.5mmtwo vs. 628mmtwo of the GA102. Additionally, this AD104 features 7,680 CUDA cores and 60 SMs along with 48 MB of L2 cache. This shows us that the NVIDIA RTX 4080 12GB uses the full configuration of this AD104.
End of Article. Tell us something in the Comments!
Juan Antonio Soto
I am a Computer Engineer and my specialty is automation and robotics. My passion for hardware began at the age of 14 when I gutted my first computer: a 386 DX 40 with 4MB of RAM and a 210MB hard drive. I continue to give free rein to my passion in the technical articles that I write in Geeknetic. I spend most of my free time playing video games, contemporary and retro, on the more than 20 consoles I have, in addition to the PC.
Add Comment