AI Chip Mass Production

SEMIFIVE Begins Mass Production of HyperAccel AI Inference Accelerator on Samsung 4nm

SEMIFIVE, a leading global provider of custom AI semiconductor (ASIC) solutions, has begun mass production of a data center AI inference accelerator for HyperAccel on Samsung 4nm. This is SEMIFIVE's first large-scale mass production project using Samsung Foundry's 4nm advanced process node. The company secured initial mass production contract for Hyperaccel's AI inference accelerator, Bertha, with follow-on purchase orders anticipated as services expand. The chip is designed for AI inference workloads and is a "Big Die" of more than 500 mm². SEMIFive expanded its portfolio from security and HPC to data center, fueling mass production ramp-up following KRW 42.3 billion in H1 order intake.

Topics