Hopper GPU H100 Overview
The Hopper GPU, introduced as Nvidia H100 Tensor Core GPU, is implemented using the Taiwan Semiconductor (TMSC) 4N process customized for Nvidia with 80 billion transistors. The H100 architecture includes several noteworthy architectural advances.
The custom Nvidia H100 SXM5 module houses the H100
GPU and HBM3 RAM chips, and also provides connection to other systems via their fourth-generation NVLink and PCIe Gen 5 ports. (Figure 3). Note that these modules do
not include display connectors, Nvidia RT Cores for ray tracing acceleration, or an NVENC
encoder since they, like the A100, are data center modules.
The H100 GPU consists of up to 144 Streaming Multiprocessors (SM) per full GPU, which have many performance and efficiency
improvements over earlier versions.
An overview comparing the A100 and H100 architectures is shown in the following table.