NVIDIA GA103 graphics processor pictured, features 496 mm² die area

Published: Jan 27th 2022, 15:41 GMT   Comments

NVIDIA GeForce RTX 3080 Ti GA103 GPU has finally been pictured

After two days since the official launch of the RTX 3080 Ti Laptop GPU, we finally have the first photos thanks to Chinese YouTuber Geekerwan.

NVIDIA GA103 GPU, Source: Geekerwan

The history of GA103 GPU takes us back to May 2019. This is when Kopite7Kimi made the first comment on the supposed NVIDIA Ampere lineup. This new GPU was included in the list of the upcoming (at the time) GeForce RTX 30 series. However, it wasn’t until January 2022 for this information to be confirmed.

This week NVIDIA formally introduced its GeForce RTX 3080 Ti Laptop GPU featuring GA103S/GA103M GPU labeled as GN20-E8-A1 for this mobile graphics card. This is not the full implementation of the GA103 GPU though, as the rumored specs mentioned up to 7680 CUDA cores, whereas the mobile 3080 Ti comes with 7424 cores.

It should also be noted that the full GA103 GPU supposedly has ten 32-bit memory controllers, which indicates a maximum 320-bit memory bus. Meanwhile, RTX 3080 Ti Laptop GPU comes with a 256-bit interface. Unfortunately, till NVIDIA releases the official block diagram of their new GPU, this will not be confirmed.

NVIDIA GA103 GPU, Source: Geekerwan

Geekerwan came up with an interesting way to demonstrate where does the GA103 sits in the lineup. For now, it is only being used by RTX 3080 Ti Laptop GPU, whereas the 3070Ti still relies on a smaller GPU called GA104.

According to the YouTuber, the GA103 GPU measures 496 mm², which means it is 26.5% bigger than GA104 while offering 25% more cores.

We are yet to hear about NVIDIA’s plans for GA103 GPU for desktops. One would expect that some GA103 will make their way RTX 3070+ series at some point in the future. After all, NVIDIA needs to sell chips with partially disabled (non-functional) CUDA cores at some point.

NVIDIA Ampere Graphics Processors
Architecture7nm Ampere8nm Ampere8nm Ampere8nm Ampere8nm Ampere8nm Ampere
Die Size826 mm²628 mm²~496 mm²392 mm²276 mm²TBC
Streaming MultiProcessors1288460483024
CUDA Cores8192107527680614438403072
RT Cores8460483024
Tensor Cores51233624019212096
Memory Bus6144-bit384-bit256-bit256-bit192-bit128-bit
Best SKUsA100 Tensor CoreRTX 3090 TiRTX 3080 Ti LaptopRTX 3070 Ti
RTX 3080 Laptop
RTX 3060 LaptopRTX 3050 Ti Laptop

Furthermore, after months of looking for GA107 GPU pictures, it appears that Olrak managed to find one. This GPU is not even the final retail version, but an engineering sample, hence it carries a different codename. Yet, it finally gave us an opportunity to see the full Ampere GPU family at once. Hello, Ampere.


[极客湾Geekerwan] 笔记本RTX3080Ti评测:和3080差别不大... (134,169 views)

Many thanks to ChengJed for the tip!

Comment Policy
  1. Comments must be written in English.
  2. Comments deemed to be spam or solely promotional in nature will be deleted. Including a link to relevant content is permitted, but comments should be relevant to the post topic. Discussions about politics are not allowed on this website.
  3. Comments and usernames containing language or concepts that could be deemed offensive will be deleted.
  4. Comments complaining about the post subject or its source will be removed.
  5. A failure to comply with these rules will result in a warning and, in extreme cases, a ban. In addition, please note that comments that attack or harass an individual directly will result in a ban without warning.
  6. VideoCardz has never been sponsored by AMD, Intel, or NVIDIA. Users claiming otherwise will be banned.
  7. VideoCardz Moderating Team reserves the right to edit or delete any comments submitted to the site without notice.
  8. If you have any questions about the commenting policy, please let us know through the Contact Page.
Hide Comment Policy