Samsung’s Cutting-Edge Process Nodes: SF2Z and SF4U, Paving the Way for HPC and AI Chips in 2025 and 2027 respectively.

Samsung has recently announced the launch of two new advanced process nodes, SF2Z (2nm) and SF4U (4nm). The lower the nm number of the process node, the better. These cutting-edge process nodes are expected to enter mass production in 2025 for the 4nm node and 2027 for the 2nm node, primarily targeting HPC and AI chips.

Samsung’s new 2nm process node, SF2Z, incorporates a backside power delivery network (BSPDN), which enhances power, performance, and area (PPA) and also reduces voltage drop. On the other hand, the 4nm node achieves PPA improvements through optical shrink technology, allowing existing die designs to be scaled down without significant architectural changes.

PPA are the three variables used in deciding how to optimize semiconductor designs. The lower the PPA values, the more efficient the design is. This is why these advanced process nodes are such a big deal – they represent a major leap forward in semiconductor technology.

It is likely that these new technologies will transfer onto smartphone chips as well. This could very well be the next chapter in the Samsung-Apple rivalry, where each side tries to deliver cutting-edge technology and attract more customers. The race to create smaller transistors on a chip has been ongoing for years now, with Samsung leading this particular battle so far. However, Apple could soon catch up with its own advances in optical shrink technology and other areas. Only time will tell who will come out on top in this high-stakes game of technological one-upmanship.