NVIDIA’s GeForce RTX 40 series graphics cards based on the Ada Lovelace GPU architecture are expected to retain their existing PCIe Gen 4.0 compliance as reported by Kopite7kimi.
NVIDIA GeForce RTX 40 ‘AD102 GPU’ Graphics Cards To Retain PCIe Gen 4.0 Compliancy
NVIDIA will be launching its GeForce RTX 40 series graphics cards based on the brand new Ada Lovelace GPU architecture later this year. The specifications and specific configurations for the graphics card lineup have already been leaked but the design of the card themselves is a more interesting aspect.
— kopite7kimi (@kopite7kimi) April 24, 2022
So far, we know that the NVIDIA GeForce RTX 40 series graphics cards will adopt the new ATX 3.0 compliant 12PVHPWR 16-pin connector which allows for up to 600W of power draw through a new PCIe Gen 5 power connector interface. This power connector has already been featured on the GeForce RTX 3090 Ti graphics card and currently allows for up to 450W of power draw through a triple 8-pin adapter. But there’s another aspect to allow the full PCIe Gen 5.0 compliance and that’s the interface connector itself.
Currently, modern graphics cards communicate to the CPU through the PCIe Gen 4.0 protocol. The PCIe Gen 4.0 protocol allows for 64 GB/s of total and 32 GB/s of bi-directional bandwidth. But the latest platforms from Intel and AMD support the brand new PCIe Gen 5.0 interface protocoll. This new standard allows for up to 128 GB/s of total and 64 GB/s of bi-directional bandwidth. This will essentially double the bandwidth but it looks like upcoming graphics cards or at least the high-end GeForce RTX 40 graphics cards based on the AD102 GPU won’t feature PCIe Gen 5.0 interface just yet.
Based on a tweet from Kopite7kimi, the upcoming GeForce RTX 40 lineup will retain the PCIe Gen 4.0 protocol which is a bold move by NVIDIA for not hopping on the next-gen standard even though they are doing so in the HPC segment where their Hopper GPU will be amongst the first to use the new protocol. Now it makes sense that the HPC lineup features it because servers require a lot of bandwidth and the Gen 5.0 protocol will help those environments. As for consumers, the PCIe Gen 5.0 interface is just too much bandwidth and current GPUs are yet to fully stature the PCIe Gen 4.0 interface.
Now having PCIe Gen 4.0 bodes well for the entry-level lineup which doesn’t need to worry about bottlenecks if they are equipped with lower lanes as was the case with the Radeon RX 6500 and RX 6400 series which when switching over to Gen 3 standard end up with less than required graphics bandwidth, leading to poor performance versus as PCIe Gen 4.0 compliant standard. If the high-end lineup isn’t starving the Gen 4.0 standard, then the low-end lineup is far from hitting the max threshold. So far, we can’t say for sure if NVIDIA will truly retain PCIe Gen 4.0 on its upcoming RTX 40 series cards but that could change as marketing does like having the PCIe Gen 5.0 logo for the new cards.
Aside from the PCIe Gen 5.0 and PCIe Gen 4.0 support, NVIDIA is also seemingly going to make major changes to the way its CUDA cores are arranged within the Ada Lovelace architecture. The GPUs for the GeForce RTX 40 series will not just be a simple CUDA core bump from Ampere but could include a range of new mixed-precision cores that aren’t detailed yet. The lineup is still a few months away from introduction so a lot could change but we will make sure to keep you updated.
NVIDIA CUDA GPU (RUMORED) Preliminary:
|Flagship SKUs||RTX 2080 Ti||RTX 3090Ti||RTX4090?|
|Process||TSMC 12nm NFF||Samsung 8nm||TSMC 5nm|
|Graphics Processing Clusters (GPC)||6||7||12|
|Texture Processing Clusters (TPC)||36||42||72|
|Streaming Multiprocessors (SM)||72||84||144|
|Theoretical TFLOPs||16 TFLOPs||40 TFLOPs||~90 TFLOPs?|
|Memory Capacity||11GB (2080 Ti)||24GB (3090Ti)||24GB (4090?)|
|PCIeInterface||PCIe Gen 3.0||PCIe Gen 4.0||PCIe Gen 4.0|
|release||Sep 2018||Sept. twenty||2H 2022 (TBC)|