AMD Radeon RX Vega 56 vs NVIDIA GeForce RTX 3080 Ti Laptop GPU vs AMD Radeon Pro WX Vega M GL

AMD’s Radeon RX Vega 56 is a high-end desktop GPU that was first introduced in August of 2017. It is based on the Vega architecture (Vega 10) and equipped with fast HBM2 VRAM. When it was first introduced, it was the second fastest AMD GPU available, only bested by the RX Vega 64 that launched on the very same day. At the time of writing, both GPUs have been replaced by their respective Radeon VII successors.

The RX Vega 56 reference design features 56 CUs running at 1,138-1,474 MHz (Boost) and 8 GB of HBM2 VRAM running at 800 MHz connected via a 2,048-bit memory bus resulting in a memory bandwidth of 409.6 GB/s.

Features

Vega 10 is still produced in a 10-nm manufacturing process. The die consists of roughly 12.5 billion transistors and measures 495 mm2 in size. The newer Vega 20 chip, which AMD’s current Radeon VII is based on, features around 13.2 billion transistors. Applications have access to a total of 3,584 shaders, but the GPU lacks the dedicated Raytracing and Tensor cores that can be found on Nvidia’s latest RTX generation of GPUs.

Performance

Performance-wise, the RX Vega 56 is comparable to an Nvidia GeForce GTX 1070, and thus best categorized as upper middle-class. Games released in 2018 and 2019 should run perfectly fine and smooth in high details on WQHD (2560 x 1440).

Power Consumption

According to AMD, the RX Vega 56’s maximum power consumption is 210 W. Given the GTX 1070’s power consumption of just 150 W, the Vega 56 cannot keep up with its direct competitor in regards to performance-per-watt ratio.

The Nvidia GeForce RTX 3080 Ti Laptop GPU or 3080 Ti Mobile (for laptops, GN20-E8) is the fastest graphics card for notebooks in early 2022. It is based on the GA103S Ampere chip and offers 7,424 shaders and 16 GB GDDR6 graphics memory with a 256 Bit memory bus. It supports PCIe 4.0 and will be available in different variants (80 - 175 Watt TGP currently known). The maximum Boost clock can vary from 1125 (80 W) to 1590 MHz (150W and up).

There is no more Max-Q variant (formerly used for the low power variants) but every OEM can choose to implement Max-Q technologies (Dynamic Boost, Whispermode).

The performance depends on the TGP setting and cooling of the laptop. Thanks to the higher core count, the RTX 3080 Ti should be clearly faster than the old RTX 3080 Mobile and therefore well suited for 4K gaming.

The GA103S chip offers 7,424 FP32 ALUs of which half can also execute INT32 instructions (i.e. 3,712 INT32 ALUs). With Turing all shaders could still execute FP32 or INT32 instructions. The GA103S integrates 58 Raytracing cores and 232 Tensor cores (e.g., for DLSS). The L2 cache is 4 MB. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1). Compared to the GA103, the GA103S integrates only a 256 Bit memory bus.

The GA103S chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip).