The heart of the NEC SX Aurora TSUBASA architecture – the vector engine (VE) – offers a hitherto unparalleled performance especially for memory-bound applications. As a standard PCIe card, it fits effortlessly in a standard x86 server host environment. Each vector CPU has access to six extremely high-bandwidth HBM2 memory modules, which allows for unprecedented performance for memory-intensive applications. With the first generation of SX-Aurora TSUBASA, the world’s first implementation of a CPU design with six HBM2 memory modules using a “chip-on-wafer-on-sub-strate” technology (CoWoS) applications were provided with the world-record memory bandwidth of 1.22TB/s. The second generation of SX-Aurora TSUBASA equipped with the second generation VE is continuously leading the world’s highest memory bandwidth of 1.53TB/s.