Analysis of information sources in references of the Wikipedia article "NVLink" in English language version.
Fifth-generation NVLink doubles the performance of fourth- generation NVLink in NVIDIA Hopper. While the new NVLink in Blackwell GPUs also uses two high-speed differential pairs in each direction to form a single link as in the Hopper GPU, NVIDIA Blackwell doubles the effective bandwidth per link to 50 GB/sec in each direction.
We considered various FLIT sizes and settled on 256 Bytes with 236 bytes of TLP payload and a TLP efficiency of 92%.
TU102 and TU104 are Nvidia's first desktop GPUs rocking the NVLink interconnect rather than a Multiple Input/Output (MIO) interface for SLI support. The former makes two x8 links available, while the latter is limited to one. Each link facilitates up to 50 GB/s of bidirectional bandwidth. So, GeForce RTX 2080 Ti is capable of up to 100 GB/s between cards and RTX 2080 can do half of that.