The GPU inside the VII is called Vega 20, which is a die-shrunk version of the Vega 10 in the Vega 64. The Vega 10 is built on GlobalFoundries’ 14nm process; the Vega 20 is built on TSMC’s 7nm process. This new process has enabled AMD to substantially boost the clock rate from a peak of 1564MHz in the Vega 64 to 1,800MHz in the VII. The new card’s memory subsystem has also been uprated: it’s still using HBM2, but it’s using 16GB clocked at 2Gb/s with a 4,096-bit bus compared to 8GB clocked at 1.89Gb/s with a 2,048-bit bus. This gives a total of 1TB/s memory bandwidth.
The new chip has 128 ROPs to the old chip’s 64, doubling the number of rendered rasterized pixels it can produce. However, it does fall behind its predecessor in one spec: it has only 60 compute units (3,840 stream processors) compared to 64 (4,096 stream processors).