NVIDIA's GeForce RTX 40 desktop graphics cards and mobility GPUs based on the Ada Lovelace architecture have leaked out with their PCI IDs.
NVIDIA GeForce RTX 40 Desktop Graphics Cards and Mobility GPU PCI IDs Leaked, GeForce RTX 4090 Confirmed
The GPU IDs for the NVIDIA GeForce RTX 40 series lineup which will be based on the Ada Lovelace GPU architecture were published over at LaptopVideo2Go and discovered by @Harukaze5719. The PCI IDs include several desktop and mobility SKUs which are expected to launch around this fall & the start of next year but don't expect all of the GPUs mentioned here to be launched in the market as some device IDs are set for preliminary engineering boards that never go out to retail.
So starting with the PCI Device IDs, first up we have the 'NVIDIA_DEV.268' which is said to be the top GeForce RTX 4090 graphics card that will be based on the AD102 GPU architecture. The RTX 4090 will be the flagship offering for 2022, offering almost 100 TFLOPs of compute performance that's hinted in previous leaks.
NVIDIA GeForce RTX 4090 'Rumored' Specifications
The NVIDIA GeForce RTX RTX 4090 graphics card is expected to be powered by the top AD102-300 GPU but it is only the 'Ti' variant that will feature the full chip. The Geforce RTX 4090 will utilize a slightly cut-down configuration.
The NVIDIA GeForce RTX 4090 will use 128 SMs of the 144 SMs for a total of 16,384 CUDA cores. The GPU will come packed with 96 MB of L2 cache and a total of 384 ROPs which is simply insane. The clock speeds are not confirmed yet but considering that the TSMC 4N process is being used, we are expecting clocks between the 2.0-3.0 GHz range.
As for memory specs, the GeForce RTX 4090 is expected to rock 24 GB GDDR6X capacities that will be clocked at 21 Gbps speeds across a 384-bit bus interface. This will provide up to 1 TB/s of bandwidth. This is the same bandwidth as the existing RTX 3090 Ti graphics card and as far as the power consumption is concerned, the TBP is said to be rated at 450W which means that TGP may end up lower than that. The card will be powered by a single 16-pin connector which delivers up to 600W of power. It is likely that we may get 500W+ custom designs as we saw with the RTX 3090 Ti.
GN21-X11 is based on AD103. So I don't think it will be called RTX 4080 Mobile.
And X9, AD104, X6 AD106, X4, X2 AD107.
I told you their power comsumption beforce, but no names.
Thank you for your information. 👍👍👍
— kopite7kimi (@kopite7kimi) July 10, 2022
The rest of the lineup is a mix of various NVIDIA GeForce RTX 40 Mobility GPUs which will be based on various GPU SKUs such as the AD103, AD104, AD106, & AD107 chips. Following is the complete breakdown. According to leaker Kopite7kimi, the GN21-X11 series SKUs will feature the AD103 GPU which will be followed by the GN21-X9 with AD104, GN21-X6 with AD106, and GN21-X4/X2 with the AD107 GPUs. The GN20 series was part of the Ampere family so it's easy to conclude that the GN21 lineup will be part of the Ada Lovelace family.
; AD103 - GN21-X11 Series
NVIDIA_DEV.2717 = “NVIDIA GN21-X11”
NVIDIA_DEV.2757 = “NVIDIA GN21-X11”
; AD104 - GN21-X9 Series
NVIDIA_DEV.2785 = “NVIDIA AD104”
NVIDIA_DEV.27A0 = “NVIDIA GN21-X9”
NVIDIA_DEV.27E0 = “NVIDIA GN21-X9”
; AD106 - GN21-X6 Series
NVIDIA_DEV.2820 = “NVIDIA GN21-X6”
NVIDIA_DEV.2860 = “NVIDIA GN21-X6”
; AD107 - GN21-X4 / X2 Series
NVIDIA_DEV.28A0 = “NVIDIA GN21-X4”
NVIDIA_DEV.28A1 = “NVIDIA GN21-X2”
NVIDIA_DEV.28E0 = “NVIDIA GN21-X4”
NVIDIA_DEV.28E1 = “NVIDIA GN21-X2”
A truth. The power limits:
AD103 (DT), 450W, AD103 (Mobile), 175W;
AD104 (DT), 400W, AD104 (Mobile), 175W;
AD106 (DT), 260W, AD106 (Mobile), 140W.
But I don't think we need to use the full power cap.
— kopite7kimi (@kopite7kimi) June 18, 2022
In a previous breakdown by the same leaker, it was reported that the NVIDIA AD103 Mobile SKU will have a max power limit of 175W which will also be retained for the AD104 SKUs, the AD106 GPU will have a 140W power limit while the AD107 will end up somewhere around or under the 100W range. The GeForce RTX 40 series graphics cards are expected to launch in Q4 2022 while mobility GPUs are expected around CES 2023.
News Source: Videocardz